chore(ui): regen types

Crawled through a few custom nodes to figure out what I had missed.

docker/Dockerfile

@@ -18,8 +18,8 @@ ENV INVOKEAI_SRC=/opt/invokeai
 ENV VIRTUAL_ENV=/opt/venv/invokeai
 
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
-ARG TORCH_VERSION=2.1.0
-ARG TORCHVISION_VERSION=0.16
+ARG TORCH_VERSION=2.1.2
+ARG TORCHVISION_VERSION=0.16.2
 ARG GPU_DRIVER=cuda
 ARG TARGETPLATFORM="linux/amd64"
 # unused but available
@@ -35,7 +35,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     if [ "$TARGETPLATFORM" = "linux/arm64" ] || [ "$GPU_DRIVER" = "cpu" ]; then \
         extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cpu"; \
     elif [ "$GPU_DRIVER" = "rocm" ]; then \
-        extra_index_url_arg="--index-url https://download.pytorch.org/whl/rocm5.6"; \
+        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/rocm5.6"; \
     else \
         extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu121"; \
     fi &&\
@@ -54,7 +54,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     if [ "$GPU_DRIVER" = "cuda" ] && [ "$TARGETPLATFORM" = "linux/amd64" ]; then \
         pip install -e ".[xformers]"; \
     else \
-        pip install -e "."; \
+        pip install $extra_index_url_arg -e "."; \
     fi
 
 # #### Build the Web UI ------------------------------------

docker/README.md

@@ -28,7 +28,7 @@ This is done via Docker Desktop preferences
 
 ### Configure Invoke environment
 
-1. Make a copy of `env.sample` and name it `.env` (`cp env.sample .env` (Mac/Linux) or `copy example.env .env` (Windows)). Make changes as necessary. Set `INVOKEAI_ROOT` to an absolute path to:
+1. Make a copy of `.env.sample` and name it `.env` (`cp .env.sample .env` (Mac/Linux) or `copy example.env .env` (Windows)). Make changes as necessary. Set `INVOKEAI_ROOT` to an absolute path to:
     a. the desired location of the InvokeAI runtime directory, or
     b. an existing, v3.0.0 compatible runtime directory.
 1. Execute `run.sh`

docker/run.sh

@@ -21,7 +21,7 @@ run() {
     printf "%s\n" "$build_args"
   fi
 
-  docker compose build $build_args
+  docker compose build $build_args $service_name
   unset build_args
 
   printf "%s\n" "starting service $service_name"

docs/contributing/INVOCATIONS.md

@@ -9,11 +9,15 @@ complex functionality.
 
 ## Invocations Directory
 
-InvokeAI Nodes can be found in the `invokeai/app/invocations` directory. These can be used as examples to create your own nodes.
+InvokeAI Nodes can be found in the `invokeai/app/invocations` directory. These
+can be used as examples to create your own nodes.
 
-New nodes should be added to a subfolder in `nodes` direction found at the root level of the InvokeAI installation location. Nodes added to this folder will be able to be used upon application startup. 
+New nodes should be added to a subfolder in `nodes` direction found at the root
+level of the InvokeAI installation location. Nodes added to this folder will be
+able to be used upon application startup.
+
+Example `nodes` subfolder structure:
 
-Example `nodes`  subfolder structure:
 ```py
 ├── __init__.py # Invoke-managed custom node loader
 │
@@ -30,14 +34,14 @@ Example `nodes`  subfolder structure:
         └── fancy_node.py
 ```
 
-Each node folder must have an `__init__.py` file that imports its nodes. Only nodes imported in the `__init__.py` file are loaded.
- See the README in the nodes folder for more examples: 
+Each node folder must have an `__init__.py` file that imports its nodes. Only
+nodes imported in the `__init__.py` file are loaded. See the README in the nodes
+folder for more examples:
 
 ```py
 from .cool_node import CoolInvocation
 ```
 
-
 ## Creating A New Invocation
 
 In order to understand the process of creating a new Invocation, let us actually
@@ -131,7 +135,6 @@ from invokeai.app.invocations.primitives import ImageField
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
 
-    # Inputs
     image: ImageField = InputField(description="The input image")
     width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
@@ -167,7 +170,6 @@ from invokeai.app.invocations.primitives import ImageField
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
 
-    # Inputs
     image: ImageField = InputField(description="The input image")
     width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
@@ -197,7 +199,6 @@ from invokeai.app.invocations.image import ImageOutput
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
 
-    # Inputs
     image: ImageField = InputField(description="The input image")
     width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
@@ -229,30 +230,17 @@ class ResizeInvocation(BaseInvocation):
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        # Load the image using InvokeAI's predefined Image Service. Returns the PIL image.
-        image = context.services.images.get_pil_image(self.image.image_name)
+        # Load the input image as a PIL image
+        image = context.images.get_pil(self.image.image_name)
 
-        # Resizing the image
+        # Resize the image
         resized_image = image.resize((self.width, self.height))
 
-        # Save the image using InvokeAI's predefined Image Service. Returns the prepared PIL image.
-        output_image = context.services.images.create(
-            image=resized_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
+        # Save the image
+        image_dto = context.images.save(image=resized_image)
 
-        # Returning the Image
-        return ImageOutput(
-            image=ImageField(
-                image_name=output_image.image_name,
-            ),
-            width=output_image.width,
-            height=output_image.height,
-        )
+        # Return an ImageOutput
+        return ImageOutput.build(image_dto)
 ```
 
 **Note:** Do not be overwhelmed by the `ImageOutput` process. InvokeAI has a
@@ -343,27 +331,25 @@ class ImageColorStringOutput(BaseInvocationOutput):
 
 That's all there is to it.
 
-<!-- TODO: DANGER - we probably do not want people to create their own field types, because this requires a lot of work on the frontend to accomodate.
-
 ### Custom Input Fields
 
 Now that you know how to create your own Invocations, let us dive into slightly
 more advanced topics.
 
 While creating your own Invocations, you might run into a scenario where the
-existing input types in InvokeAI do not meet your requirements. In such cases,
-you can create your own input types.
+existing fields in InvokeAI do not meet your requirements. In such cases, you
+can create your own fields.
 
 Let us create one as an example. Let us say we want to create a color input
 field that represents a color code. But before we start on that here are some
 general good practices to keep in mind.
 
-**Good Practices**
+### Best Practices
 
 - There is no naming convention for input fields but we highly recommend that
   you name it something appropriate like `ColorField`.
 - It is not mandatory but it is heavily recommended to add a relevant
-  `docstring` to describe your input field.
+  `docstring` to describe your field.
 - Keep your field in the same file as the Invocation that it is made for or in
   another file where it is relevant.
 
@@ -378,10 +364,13 @@ class ColorField(BaseModel):
     pass
 ```
 
-Perfect. Now let us create our custom inputs for our field. This is exactly
-similar how you created input fields for your Invocation. All the same rules
-apply. Let us create four fields representing the _red(r)_, _blue(b)_,
-_green(g)_ and _alpha(a)_ channel of the color.
+Perfect. Now let us create the properties for our field. This is similar to how
+you created input fields for your Invocation. All the same rules apply. Let us
+create four fields representing the _red(r)_, _blue(b)_, _green(g)_ and
+_alpha(a)_ channel of the color.
+
+> Technically, the properties are _also_ called fields - but in this case, it
+> refers to a `pydantic` field.
 
 ```python
 class ColorField(BaseModel):
@@ -396,25 +385,11 @@ That's it. We now have a new input field type that we can use in our Invocations
 like this.
 
 ```python
-color: ColorField = Field(default=ColorField(r=0, g=0, b=0, a=0), description='Background color of an image')
+color: ColorField = InputField(default=ColorField(r=0, g=0, b=0, a=0), description='Background color of an image')
 ```
 
-### Custom Components For Frontend
+### Using the custom field
 
-Every backend input type should have a corresponding frontend component so the
-UI knows what to render when you use a particular field type.
+When you start the UI, your custom field will be automatically recognized.
 
-If you are using existing field types, we already have components for those. So
-you don't have to worry about creating anything new. But this might not always
-be the case. Sometimes you might want to create new field types and have the
-frontend UI deal with it in a different way.
-
-This is where we venture into the world of React and Javascript and create our
-own new components for our Invocations. Do not fear the world of JS. It's
-actually pretty straightforward.
-
-Let us create a new component for our custom color field we created above. When
-we use a color field, let us say we want the UI to display a color picker for
-the user to pick from rather than entering values. That is what we will build
-now.
--->
+Custom fields only support connection inputs in the Workflow Editor.

docs/features/CONTROLNET.md

@@ -94,6 +94,8 @@ A model that helps generate creative QR codes that still scan. Can also be used
 **Openpose**: 
 The OpenPose control model allows for the identification of the general pose of a character by pre-processing an existing image with a clear human structure. With advanced options, Openpose can also detect the face or hands in the image. 
 
+*Note:* The DWPose Processor has replaced the OpenPose processor in Invoke. Workflows and generations that relied on the OpenPose Processor will need to be updated to use the DWPose Processor instead.
+
 **Mediapipe Face**:
 
 The MediaPipe Face identification processor is able to clearly identify facial features in order to capture vivid expressions of human faces.

docs/installation/020_INSTALL_MANUAL.md

@@ -230,13 +230,13 @@ manager, please follow these steps:
         === "local Webserver"
 
             ```bash
-            invokeai --web
+            invokeai-web
             ```
 
         === "Public Webserver"
 
             ```bash
-            invokeai --web --host 0.0.0.0
+            invokeai-web --host 0.0.0.0
             ```
 
         === "CLI"
@@ -402,4 +402,4 @@ environment variable INVOKEAI_ROOT to point to the installation directory.
 Note that if you run into problems with the Conda installation, the InvokeAI
 staff will **not** be able to help you out. Caveat Emptor!
 
-[dev-chat]: https://discord.com/channels/1020123559063990373/1049495067846524939
+[dev-chat]: https://discord.com/channels/1020123559063990373/1049495067846524939

docs/installation/040_INSTALL_DOCKER.md

@@ -69,7 +69,7 @@ a token and copy it, since you will need in for the next step.
 
 ### Setup
 
-Set up your environmnent variables. In the `docker` directory, make a copy of `env.sample` and name it `.env`. Make changes as necessary.
+Set up your environmnent variables. In the `docker` directory, make a copy of `.env.sample` and name it `.env`. Make changes as necessary.
 
 Any environment variables supported by InvokeAI can be set here - please see the [CONFIGURATION](../features/CONFIGURATION.md) for further detail.
 

docs/nodes/communityNodes.md

@@ -42,6 +42,7 @@ To use a community workflow, download the the `.json` node graph file and load i
     + [Oobabooga](#oobabooga)
     + [Prompt Tools](#prompt-tools)
     + [Remote Image](#remote-image)
+    + [BriaAI Background Remove](#briaai-remove-background)
     + [Remove Background](#remove-background)    
     + [Retroize](#retroize)
     + [Size Stepper Nodes](#size-stepper-nodes)
@@ -434,6 +435,17 @@ See full docs here: https://github.com/skunkworxdark/Prompt-tools-nodes/edit/mai
 
 **Node Link:** https://github.com/fieldOfView/InvokeAI-remote_image
 
+--------------------------------
+
+### BriaAI Remove Background
+
+**Description**: Implements one click background removal with BriaAI's new version 1.4 model which seems to be be producing better results than any other previous background removal tool.
+
+**Node Link:** https://github.com/blessedcoolant/invoke_bria_rmbg
+
+**View**
+<img src="https://raw.githubusercontent.com/blessedcoolant/invoke_bria_rmbg/main/assets/preview.jpg" />
+
 --------------------------------
 ### Remove Background
 

docs/nodes/defaultNodes.md

@@ -81,7 +81,7 @@ their descriptions.
 | ONNX Text to Latents                                          | Generates latents from conditionings.                                                                                                                |
 | ONNX Model Loader                                             | Loads a main model, outputting its submodels.                                                                                                        |
 | OpenCV Inpaint                                                | Simple inpaint using opencv.                                                                                                                         |
-| Openpose Processor                                            | Applies Openpose processing to image                                                                                                                 |
+| DW Openpose Processor                                            | Applies Openpose processing to image                                                                                                                 |
 | PIDI Processor                                                | Applies PIDI processing to image                                                                                                                     |
 | Prompts from File                                             | Loads prompts from a text file                                                                                                                       |
 | Random Integer                                                | Outputs a single random integer.                                                                                                                     |

installer/create_installer.sh

@@ -14,11 +14,19 @@ function is_bin_in_path {
 }
 
 function git_show {
-    git show -s --format='%h %s' $1
+    git show -s --format=oneline --abbrev-commit "$1" | cat
 }
 
+if [[ -v "VIRTUAL_ENV" ]]; then
+    # we can't just call 'deactivate' because this function is not exported
+    # to the environment of this script from the bash process that runs the script
+    echo -e "${BRED}A virtual environment is activated. Please deactivate it before proceeding.${RESET}"
+    exit -1
+fi
+
 cd "$(dirname "$0")"
 
+echo
 echo -e "${BYELLOW}This script must be run from the installer directory!${RESET}"
 echo "The current working directory is $(pwd)"
 read -p "If that looks right, press any key to proceed, or CTRL-C to exit..."
@@ -32,13 +40,6 @@ if ! is_bin_in_path python && is_bin_in_path python3; then
     }
 fi
 
-if [[ -v "VIRTUAL_ENV" ]]; then
-    # we can't just call 'deactivate' because this function is not exported
-    # to the environment of this script from the bash process that runs the script
-    echo -e "${BRED}A virtual environment is activated. Please deactivate it before proceeding.${RESET}"
-    exit -1
-fi
-
 VERSION=$(
     cd ..
     python -c "from invokeai.version import __version__ as version; print(version)"
@@ -47,38 +48,9 @@ PATCH=""
 VERSION="v${VERSION}${PATCH}"
 
 echo -e "${BGREEN}HEAD${RESET}:"
-git_show
+git_show HEAD
 echo
 
-# ---------------------- FRONTEND ----------------------
-
-pushd ../invokeai/frontend/web >/dev/null
-echo
-echo "Installing frontend dependencies..."
-echo
-pnpm i --frozen-lockfile
-echo
-echo "Building frontend..."
-echo
-pnpm build
-popd
-
-# ---------------------- BACKEND ----------------------
-
-echo
-echo "Building wheel..."
-echo
-
-# install the 'build' package in the user site packages, if needed
-# could be improved by using a temporary venv, but it's tiny and harmless
-if [[ $(python -c 'from importlib.util import find_spec; print(find_spec("build") is None)') == "True" ]]; then
-    pip install --user build
-fi
-
-rm -rf ../build
-
-python -m build --wheel --outdir dist/ ../.
-
 # ----------------------
 
 echo
@@ -97,16 +69,13 @@ done
 mkdir InvokeAI-Installer/lib
 cp lib/*.py InvokeAI-Installer/lib
 
-# Move the wheel
-mv dist/*.whl InvokeAI-Installer/lib/
-
 # Install scripts
 # Mac/Linux
 cp install.sh.in InvokeAI-Installer/install.sh
 chmod a+x InvokeAI-Installer/install.sh
 
 # Windows
-perl -p -e "s/^set INVOKEAI_VERSION=.*/set INVOKEAI_VERSION=$VERSION/" install.bat.in >InvokeAI-Installer/install.bat
+cp install.bat.in InvokeAI-Installer/install.bat
 cp WinLongPathsEnabled.reg InvokeAI-Installer/
 
 # Zip everything up

installer/install.bat.in

@@ -15,7 +15,6 @@ if "%1" == "use-cache" (
 @rem Config
 @rem The version in the next line is replaced by an up to date release number
 @rem when create_installer.sh is run. Change the release number there.
-set INVOKEAI_VERSION=latest
 set INSTRUCTIONS=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/
 set TROUBLESHOOTING=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting
 set PYTHON_URL=https://www.python.org/downloads/windows/

installer/lib/installer.py

@@ -11,7 +11,7 @@ import sys
 import venv
 from pathlib import Path
 from tempfile import TemporaryDirectory
-from typing import Union
+from typing import Optional, Tuple
 
 SUPPORTED_PYTHON = ">=3.10.0,<=3.11.100"
 INSTALLER_REQS = ["rich", "semver", "requests", "plumbum", "prompt-toolkit"]
@@ -21,40 +21,20 @@ OS = platform.uname().system
 ARCH = platform.uname().machine
 VERSION = "latest"
 
-### Feature flags
-# Install the virtualenv into the runtime dir
-FF_VENV_IN_RUNTIME = True
-
-# Install the wheel packaged with the installer
-FF_USE_LOCAL_WHEEL = True
-
 
 class Installer:
     """
     Deploys an InvokeAI installation into a given path
     """
 
+    reqs: list[str] = INSTALLER_REQS
+
     def __init__(self) -> None:
-        self.reqs = INSTALLER_REQS
-        self.preflight()
         if os.getenv("VIRTUAL_ENV") is not None:
             print("A virtual environment is already activated. Please 'deactivate' before installation.")
             sys.exit(-1)
         self.bootstrap()
-
-    def preflight(self) -> None:
-        """
-        Preflight checks
-        """
-
-        # TODO
-        # verify python version
-        # on macOS verify XCode tools are present
-        # verify libmesa, libglx on linux
-        # check that the system arch is not i386 (?)
-        # check that the system has a GPU, and the type of GPU
-
-        pass
+        self.available_releases = get_github_releases()
 
     def mktemp_venv(self) -> TemporaryDirectory:
         """
@@ -78,12 +58,9 @@ class Installer:
 
         return venv_dir
 
-    def bootstrap(self, verbose: bool = False) -> TemporaryDirectory:
+    def bootstrap(self, verbose: bool = False) -> TemporaryDirectory | None:
         """
         Bootstrap the installer venv with packages required at install time
-
-        :return: path to the virtual environment directory that was bootstrapped
-        :rtype: TemporaryDirectory
         """
 
         print("Initializing the installer. This may take a minute - please wait...")
@@ -95,39 +72,27 @@ class Installer:
         cmd.extend(self.reqs)
 
         try:
-            res = subprocess.check_output(cmd).decode()
+            # upgrade pip to the latest version to avoid a confusing message
+            res = upgrade_pip(Path(venv_dir.name))
             if verbose:
                 print(res)
+
+            # run the install prerequisites installation
+            res = subprocess.check_output(cmd).decode()
+
+            if verbose:
+                print(res)
+
             return venv_dir
         except subprocess.CalledProcessError as e:
             print(e)
 
-    def app_venv(self, path: str = None):
+    def app_venv(self, venv_parent) -> Path:
         """
         Create a virtualenv for the InvokeAI installation
         """
 
-        # explicit venv location
-        # currently unused in normal operation
-        # useful for testing or special cases
-        if path is not None:
-            venv_dir = Path(path)
-
-        # experimental / testing
-        elif not FF_VENV_IN_RUNTIME:
-            if OS == "Windows":
-                venv_dir_parent = os.getenv("APPDATA", "~/AppData/Roaming")
-            elif OS == "Darwin":
-                # there is no environment variable on macOS to find this
-                # TODO: confirm this is working as expected
-                venv_dir_parent = "~/Library/Application Support"
-            elif OS == "Linux":
-                venv_dir_parent = os.getenv("XDG_DATA_DIR", "~/.local/share")
-            venv_dir = Path(venv_dir_parent).expanduser().resolve() / f"InvokeAI/{VERSION}/venv"
-
-        # stable / current
-        else:
-            venv_dir = self.dest / ".venv"
+        venv_dir = venv_parent / ".venv"
 
         # Prefer to copy python executables
         # so that updates to system python don't break InvokeAI
@@ -141,7 +106,7 @@ class Installer:
         return venv_dir
 
     def install(
-        self, root: str = "~/invokeai", version: str = "latest", yes_to_all=False, find_links: Path = None
+        self, version=None, root: str = "~/invokeai", yes_to_all=False, find_links: Optional[Path] = None
     ) -> None:
         """
         Install the InvokeAI application into the given runtime path
@@ -158,15 +123,20 @@ class Installer:
 
         import messages
 
-        messages.welcome()
+        messages.welcome(self.available_releases)
 
-        default_path = os.environ.get("INVOKEAI_ROOT") or Path(root).expanduser().resolve()
-        self.dest = default_path if yes_to_all else messages.dest_path(root)
+        version = messages.choose_version(self.available_releases)
+
+        auto_dest = Path(os.environ.get("INVOKEAI_ROOT", root)).expanduser().resolve()
+        destination = auto_dest if yes_to_all else messages.dest_path(root)
+        if destination is None:
+            print("Could not find or create the destination directory. Installation cancelled.")
+            sys.exit(0)
 
         # create the venv for the app
-        self.venv = self.app_venv()
+        self.venv = self.app_venv(venv_parent=destination)
 
-        self.instance = InvokeAiInstance(runtime=self.dest, venv=self.venv, version=version)
+        self.instance = InvokeAiInstance(runtime=destination, venv=self.venv, version=version)
 
         # install dependencies and the InvokeAI application
         (extra_index_url, optional_modules) = get_torch_source() if not yes_to_all else (None, None)
@@ -190,7 +160,7 @@ class InvokeAiInstance:
     A single runtime directory *may* be shared by multiple virtual environments, though this isn't currently tested or supported.
     """
 
-    def __init__(self, runtime: Path, venv: Path, version: str) -> None:
+    def __init__(self, runtime: Path, venv: Path, version: str = "stable") -> None:
         self.runtime = runtime
         self.venv = venv
         self.pip = get_pip_from_venv(venv)
@@ -199,6 +169,7 @@ class InvokeAiInstance:
         set_sys_path(venv)
         os.environ["INVOKEAI_ROOT"] = str(self.runtime.expanduser().resolve())
         os.environ["VIRTUAL_ENV"] = str(self.venv.expanduser().resolve())
+        upgrade_pip(venv)
 
     def get(self) -> tuple[Path, Path]:
         """
@@ -212,54 +183,7 @@ class InvokeAiInstance:
 
     def install(self, extra_index_url=None, optional_modules=None, find_links=None):
         """
-        Install this instance, including dependencies and the app itself
-
-        :param extra_index_url: the "--extra-index-url ..." line for pip to look in extra indexes.
-        :type extra_index_url: str
-        """
-
-        import messages
-
-        # install torch first to ensure the correct version gets installed.
-        # works with either source or wheel install with negligible impact on installation times.
-        messages.simple_banner("Installing PyTorch :fire:")
-        self.install_torch(extra_index_url, find_links)
-
-        messages.simple_banner("Installing the InvokeAI Application :art:")
-        self.install_app(extra_index_url, optional_modules, find_links)
-
-    def install_torch(self, extra_index_url=None, find_links=None):
-        """
-        Install PyTorch
-        """
-
-        from plumbum import FG, local
-
-        pip = local[self.pip]
-
-        (
-            pip[
-                "install",
-                "--require-virtualenv",
-                "numpy==1.26.3",  # choose versions that won't be uninstalled during phase 2
-                "urllib3~=1.26.0",
-                "requests~=2.28.0",
-                "torch==2.1.2",
-                "torchmetrics==0.11.4",
-                "torchvision==0.16.2",
-                "--force-reinstall",
-                "--find-links" if find_links is not None else None,
-                find_links,
-                "--extra-index-url" if extra_index_url is not None else None,
-                extra_index_url,
-            ]
-            & FG
-        )
-
-    def install_app(self, extra_index_url=None, optional_modules=None, find_links=None):
-        """
-        Install the application with pip.
-        Supports installation from PyPi or from a local source directory.
+        Install the package from PyPi.
 
         :param extra_index_url: the "--extra-index-url ..." line for pip to look in extra indexes.
         :type extra_index_url: str
@@ -271,53 +195,52 @@ class InvokeAiInstance:
         :type find_links: Path
         """
 
-        ## this only applies to pypi installs; TODO actually use this
-        if self.version == "pre":
+        import messages
+
+        # not currently used, but may be useful for "install most recent version" option
+        if self.version == "prerelease":
             version = None
-            pre = "--pre"
+            pre_flag = "--pre"
+        elif self.version == "stable":
+            version = None
+            pre_flag = None
         else:
             version = self.version
-            pre = None
+            pre_flag = None
 
-        ## TODO: only local wheel will be installed as of now; support for --version arg is TODO
-        if FF_USE_LOCAL_WHEEL:
-            # if no wheel, try to do a source install before giving up
-            try:
-                src = str(next(Path(__file__).parent.glob("InvokeAI-*.whl")))
-            except StopIteration:
-                try:
-                    src = Path(__file__).parents[1].expanduser().resolve()
-                    # if the above directory contains one of these files, we'll do a source install
-                    next(src.glob("pyproject.toml"))
-                    next(src.glob("invokeai"))
-                except StopIteration:
-                    print("Unable to find a wheel or perform a source install. Giving up.")
+        src = "invokeai"
+        if optional_modules:
+            src += optional_modules
+        if version:
+            src += f"=={version}"
 
-        elif version == "source":
-            # this makes an assumption about the location of the installer package in the source tree
-            src = Path(__file__).parents[1].expanduser().resolve()
-        else:
-            # will install from PyPi
-            src = f"invokeai=={version}" if version is not None else "invokeai"
+        messages.simple_banner("Installing the InvokeAI Application :art:")
 
-        from plumbum import FG, local
+        from plumbum import FG, ProcessExecutionError, local  # type: ignore
 
         pip = local[self.pip]
 
-        (
-            pip[
-                "install",
-                "--require-virtualenv",
-                "--use-pep517",
-                str(src) + (optional_modules if optional_modules else ""),
-                "--find-links" if find_links is not None else None,
-                find_links,
-                "--extra-index-url" if extra_index_url is not None else None,
-                extra_index_url,
-                pre,
-            ]
-            & FG
-        )
+        pipeline = pip[
+            "install",
+            "--require-virtualenv",
+            "--force-reinstall",
+            "--use-pep517",
+            str(src),
+            "--find-links" if find_links is not None else None,
+            find_links,
+            "--extra-index-url" if extra_index_url is not None else None,
+            extra_index_url,
+            pre_flag,
+        ]
+
+        try:
+            _ = pipeline & FG
+        except ProcessExecutionError as e:
+            print(f"Error: {e}")
+            print(
+                "Could not install InvokeAI. Please try downloading the latest version of the installer and install again."
+            )
+            sys.exit(1)
 
     def configure(self):
         """
@@ -373,7 +296,6 @@ class InvokeAiInstance:
 
         ext = "bat" if OS == "Windows" else "sh"
 
-        # scripts = ['invoke', 'update']
         scripts = ["invoke"]
 
         for script in scripts:
@@ -408,6 +330,23 @@ def get_pip_from_venv(venv_path: Path) -> str:
     return str(venv_path.expanduser().resolve() / pip)
 
 
+def upgrade_pip(venv_path: Path) -> str | None:
+    """
+    Upgrade the pip executable in the given virtual environment
+    """
+
+    python = "Scripts\\python.exe" if OS == "Windows" else "bin/python"
+    python = str(venv_path.expanduser().resolve() / python)
+
+    try:
+        result = subprocess.check_output([python, "-m", "pip", "install", "--upgrade", "pip"]).decode()
+    except subprocess.CalledProcessError as e:
+        print(e)
+        result = None
+
+    return result
+
+
 def set_sys_path(venv_path: Path) -> None:
     """
     Given a path to a virtual environment, set the sys.path, in a cross-platform fashion,
@@ -431,7 +370,43 @@ def set_sys_path(venv_path: Path) -> None:
     sys.path.append(str(Path(venv_path, lib, "site-packages").expanduser().resolve()))
 
 
-def get_torch_source() -> (Union[str, None], str):
+def get_github_releases() -> tuple[list, list] | None:
+    """
+    Query Github for published (pre-)release versions.
+    Return a tuple where the first element is a list of stable releases and the second element is a list of pre-releases.
+    Return None if the query fails for any reason.
+    """
+
+    import requests
+
+    ## get latest releases using github api
+    url = "https://api.github.com/repos/invoke-ai/InvokeAI/releases"
+    releases, pre_releases = [], []
+    try:
+        res = requests.get(url)
+        res.raise_for_status()
+        tag_info = res.json()
+        for tag in tag_info:
+            if not tag["prerelease"]:
+                releases.append(tag["tag_name"].lstrip("v"))
+            else:
+                pre_releases.append(tag["tag_name"].lstrip("v"))
+    except requests.HTTPError as e:
+        print(f"Error: {e}")
+        print("Could not fetch version information from GitHub. Please check your network connection and try again.")
+        return
+    except Exception as e:
+        print(f"Error: {e}")
+        print("An unexpected error occurred while trying to fetch version information from GitHub. Please try again.")
+        return
+
+    releases.sort(reverse=True)
+    pre_releases.sort(reverse=True)
+
+    return releases, pre_releases
+
+
+def get_torch_source() -> Tuple[str | None, str | None]:
     """
     Determine the extra index URL for pip to use for torch installation.
     This depends on the OS and the graphics accelerator in use.
@@ -446,25 +421,26 @@ def get_torch_source() -> (Union[str, None], str):
     :rtype: list
     """
 
-    from messages import graphical_accelerator
+    from messages import select_gpu
 
-    # device can be one of: "cuda", "rocm", "cpu", "idk"
-    device = graphical_accelerator()
+    # device can be one of: "cuda", "rocm", "cpu", "cuda_and_dml, autodetect"
+    device = select_gpu()
 
     url = None
     optional_modules = "[onnx]"
     if OS == "Linux":
-        if device == "rocm":
+        if device.value == "rocm":
             url = "https://download.pytorch.org/whl/rocm5.6"
-        elif device == "cpu":
+        elif device.value == "cpu":
             url = "https://download.pytorch.org/whl/cpu"
 
-    if device == "cuda":
-        url = "https://download.pytorch.org/whl/cu121"
-        optional_modules = "[xformers,onnx-cuda]"
-    if device == "cuda_and_dml":
-        url = "https://download.pytorch.org/whl/cu121"
-        optional_modules = "[xformers,onnx-directml]"
+    elif OS == "Windows":
+        if device.value == "cuda":
+            url = "https://download.pytorch.org/whl/cu121"
+            optional_modules = "[xformers,onnx-cuda]"
+        if device.value == "cuda_and_dml":
+            url = "https://download.pytorch.org/whl/cu121"
+            optional_modules = "[xformers,onnx-directml]"
 
     # in all other cases, Torch wheels should be coming from PyPi as of Torch 1.13
 

installer/lib/messages.py

@@ -5,10 +5,11 @@ Installer user interaction
 
 import os
 import platform
+from enum import Enum
 from pathlib import Path
 
 from prompt_toolkit import HTML, prompt
-from prompt_toolkit.completion import PathCompleter
+from prompt_toolkit.completion import FuzzyWordCompleter, PathCompleter
 from prompt_toolkit.validation import Validator
 from rich import box, print
 from rich.console import Console, Group, group
@@ -35,16 +36,26 @@ else:
     console = Console(style=Style(color="grey74", bgcolor="grey19"))
 
 
-def welcome():
+def welcome(available_releases: tuple | None = None) -> None:
     @group()
     def text():
-        if (platform_specific := _platform_specific_help()) != "":
+        if (platform_specific := _platform_specific_help()) is not None:
             yield platform_specific
             yield ""
         yield Text.from_markup(
             "Some of the installation steps take a long time to run. Please be patient. If the script appears to hang for more than 10 minutes, please interrupt with [i]Control-C[/] and retry.",
             justify="center",
         )
+        if available_releases is not None:
+            latest_stable = available_releases[0][0]
+            last_pre = available_releases[1][0]
+            yield ""
+            yield Text.from_markup(
+                f"[red3]🠶[/] Latest stable release (recommended): [b bright_white]{latest_stable}", justify="center"
+            )
+            yield Text.from_markup(
+                f"[red3]🠶[/] Last published pre-release version: [b bright_white]{last_pre}", justify="center"
+            )
 
     console.rule()
     print(
@@ -61,19 +72,30 @@ def welcome():
     console.line()
 
 
-def confirm_install(dest: Path) -> bool:
-    if dest.exists():
-        print(f":exclamation: Directory {dest} already exists :exclamation:")
-        dest_confirmed = Confirm.ask(
-            ":stop_sign: (re)install in this location?",
-            default=False,
-        )
-    else:
-        print(f"InvokeAI will be installed in {dest}")
-        dest_confirmed = Confirm.ask("Use this location?", default=True)
+def choose_version(available_releases: tuple | None = None) -> str:
+    """
+    Prompt the user to choose an Invoke version to install
+    """
+
+    # short circuit if we couldn't get a version list
+    # still try to install the latest stable version
+    if available_releases is None:
+        return "stable"
+
+    console.print(":grey_question: [orange3]Please choose an Invoke version to install.")
+
+    choices = available_releases[0] + available_releases[1]
+
+    response = prompt(
+        message=f"   <Enter> to install the recommended release ({choices[0]}). <Tab> or type to pick a version: ",
+        complete_while_typing=True,
+        completer=FuzzyWordCompleter(choices),
+    )
+    console.print(f"   Version {choices[0] if response == '' else response} will be installed.")
+
     console.line()
 
-    return dest_confirmed
+    return "stable" if response == "" else response
 
 
 def user_wants_auto_configuration() -> bool:
@@ -109,7 +131,23 @@ def user_wants_auto_configuration() -> bool:
     return choice.lower().startswith("a")
 
 
-def dest_path(dest=None) -> Path:
+def confirm_install(dest: Path) -> bool:
+    if dest.exists():
+        print(f":stop_sign: Directory {dest} already exists!")
+        print("   Is this location correct?")
+        default = False
+    else:
+        print(f":file_folder: InvokeAI will be installed in {dest}")
+        default = True
+
+    dest_confirmed = Confirm.ask("   Please confirm:", default=default)
+
+    console.line()
+
+    return dest_confirmed
+
+
+def dest_path(dest=None) -> Path | None:
     """
     Prompt the user for the destination path and create the path
 
@@ -124,25 +162,21 @@ def dest_path(dest=None) -> Path:
     else:
         dest = Path.cwd().expanduser().resolve()
     prev_dest = init_path = dest
-
-    dest_confirmed = confirm_install(dest)
+    dest_confirmed = False
 
     while not dest_confirmed:
-        # if the given destination already exists, the starting point for browsing is its parent directory.
-        # the user may have made a typo, or otherwise wants to place the root dir next to an existing one.
-        # if the destination dir does NOT exist, then the user must have changed their mind about the selection.
-        # since we can't read their mind, start browsing at Path.cwd().
-        browse_start = (prev_dest.parent if prev_dest.exists() else Path.cwd()).expanduser().resolve()
+        browse_start = (dest or Path.cwd()).expanduser().resolve()
 
         path_completer = PathCompleter(
             only_directories=True,
             expanduser=True,
-            get_paths=lambda: [browse_start],  # noqa: B023
+            get_paths=lambda: [str(browse_start)],  # noqa: B023
             # get_paths=lambda: [".."].extend(list(browse_start.iterdir()))
         )
 
         console.line()
-        console.print(f"[orange3]Please select the destination directory for the installation:[/] \\[{browse_start}]: ")
+
+        console.print(f":grey_question: [orange3]Please select the install destination:[/] \\[{browse_start}]: ")
         selected = prompt(
             ">>> ",
             complete_in_thread=True,
@@ -155,6 +189,7 @@ def dest_path(dest=None) -> Path:
         )
         prev_dest = dest
         dest = Path(selected)
+
         console.line()
 
         dest_confirmed = confirm_install(dest.expanduser().resolve())
@@ -182,41 +217,45 @@ def dest_path(dest=None) -> Path:
         console.rule("Goodbye!")
 
 
-def graphical_accelerator():
+class GpuType(Enum):
+    CUDA = "cuda"
+    CUDA_AND_DML = "cuda_and_dml"
+    ROCM = "rocm"
+    CPU = "cpu"
+    AUTODETECT = "autodetect"
+
+
+def select_gpu() -> GpuType:
     """
-    Prompt the user to select the graphical accelerator in their system
-    This does not validate user's choices (yet), but only offers choices
-    valid for the platform.
-    CUDA is the fallback.
-    We may be able to detect the GPU driver by shelling out to `modprobe` or `lspci`,
-    but this is not yet supported or reliable. Also, some users may have exotic preferences.
+    Prompt the user to select the GPU driver
     """
 
     if ARCH == "arm64" and OS != "Darwin":
         print(f"Only CPU acceleration is available on {ARCH} architecture. Proceeding with that.")
-        return "cpu"
+        return GpuType.CPU
 
     nvidia = (
         "an [gold1 b]NVIDIA[/] GPU (using CUDA™)",
-        "cuda",
+        GpuType.CUDA,
     )
     nvidia_with_dml = (
         "an [gold1 b]NVIDIA[/] GPU (using CUDA™, and DirectML™ for ONNX) -- ALPHA",
-        "cuda_and_dml",
+        GpuType.CUDA_AND_DML,
     )
     amd = (
         "an [gold1 b]AMD[/] GPU (using ROCm™)",
-        "rocm",
+        GpuType.ROCM,
     )
     cpu = (
-        "no compatible GPU, or specifically prefer to use the CPU",
-        "cpu",
+        "Do not install any GPU support, use CPU for generation (slow)",
+        GpuType.CPU,
     )
-    idk = (
+    autodetect = (
         "I'm not sure what to choose",
-        "idk",
+        GpuType.AUTODETECT,
     )
 
+    options = []
     if OS == "Windows":
         options = [nvidia, nvidia_with_dml, cpu]
     if OS == "Linux":
@@ -230,7 +269,7 @@ def graphical_accelerator():
         return options[0][1]
 
     # "I don't know" is always added the last option
-    options.append(idk)
+    options.append(autodetect)  # type: ignore
 
     options = {str(i): opt for i, opt in enumerate(options, 1)}
 
@@ -265,9 +304,9 @@ def graphical_accelerator():
         ),
     )
 
-    if options[choice][1] == "idk":
+    if options[choice][1] is GpuType.AUTODETECT:
         console.print(
-            "No problem. We will try to install a version that [i]should[/i] be compatible. :crossed_fingers:"
+            "No problem. We will install CUDA support first :crossed_fingers: If Invoke does not detect a GPU, please re-run the installer and select one of the other GPU types."
         )
 
     return options[choice][1]
@@ -291,7 +330,7 @@ def windows_long_paths_registry() -> None:
     """
 
     with open(str(Path(__file__).parent / "WinLongPathsEnabled.reg"), "r", encoding="utf-16le") as code:
-        syntax = Syntax(code.read(), line_numbers=True)
+        syntax = Syntax(code.read(), line_numbers=True, lexer="regedit")
 
     console.print(
         Panel(
@@ -301,7 +340,7 @@ def windows_long_paths_registry() -> None:
                         "We will now apply a registry fix to enable long paths on Windows. InvokeAI needs this to function correctly. We are asking your permission to modify the Windows Registry on your behalf.",
                         "",
                         "This is the change that will be applied:",
-                        syntax,
+                        str(syntax),
                     ]
                 )
             ),
@@ -340,7 +379,7 @@ def introduction() -> None:
     console.line(2)
 
 
-def _platform_specific_help() -> str:
+def _platform_specific_help() -> Text | None:
     if OS == "Darwin":
         text = Text.from_markup(
             """[b wheat1]macOS Users![/]\n\nPlease be sure you have the [b wheat1]Xcode command-line tools[/] installed before continuing.\nIf not, cancel with [i]Control-C[/] and follow the Xcode install instructions at [deep_sky_blue1]https://www.freecodecamp.org/news/install-xcode-command-line-tools/[/]."""
@@ -354,5 +393,5 @@ def _platform_specific_help() -> str:
      [deep_sky_blue1]https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170[/]"""
         )
     else:
-        text = ""
+        return
     return text

installer/templates/invoke.bat.in

@@ -15,7 +15,7 @@ echo 4. Download and install models
 echo 5. Change InvokeAI startup options
 echo 6. Re-run the configure script to fix a broken install or to complete a major upgrade
 echo 7. Open the developer console
-echo 8. Update InvokeAI
+echo 8. Update InvokeAI (DEPRECATED - please use the installer)
 echo 9. Run the InvokeAI image database maintenance script
 echo 10. Command-line help
 echo Q - Quit
@@ -52,8 +52,10 @@ IF /I "%choice%" == "1" (
     echo *** Type `exit` to quit this shell and deactivate the Python virtual environment ***
     call cmd /k
 ) ELSE IF /I "%choice%" == "8" (
-   echo Running invokeai-update...
-   python -m invokeai.frontend.install.invokeai_update
+    echo UPDATING FROM WITHIN THE APP IS BEING DEPRECATED.
+    echo Please download the installer from https://github.com/invoke-ai/InvokeAI/releases/latest and run it to update your installation.
+    timeout 4
+    python -m invokeai.frontend.install.invokeai_update
 ) ELSE IF /I "%choice%" == "9" (
    echo Running the db maintenance script...
    python .venv\Scripts\invokeai-db-maintenance.exe
@@ -77,4 +79,3 @@ pause
 
 :ending
 exit /b
-

installer/templates/invoke.sh.in

@@ -90,7 +90,9 @@ do_choice() {
         ;;
     8)
         clear
-        printf "Update InvokeAI\n"
+        printf "UPDATING FROM WITHIN THE APP IS BEING DEPRECATED\n"
+        printf "Please download the installer from https://github.com/invoke-ai/InvokeAI/releases/latest and run it to update your installation.\n"
+        sleep 4
         python -m invokeai.frontend.install.invokeai_update
         ;;
     9)
@@ -122,7 +124,7 @@ do_dialog() {
         5 "Change InvokeAI startup options"
         6 "Re-run the configure script to fix a broken install or to complete a major upgrade"
         7 "Open the developer console"
-        8 "Update InvokeAI"
+        8 "Update InvokeAI (DEPRECATED - please use the installer)"
 	9 "Run the InvokeAI image database maintenance script"
 	10 "Command-line help"
     )

installer/templates/update.bat.in

@@ -1,72 +0,0 @@
-@echo off
-setlocal EnableExtensions EnableDelayedExpansion
-
-PUSHD "%~dp0"
-
-set INVOKE_AI_VERSION=latest
-set arg=%1
-if "%arg%" neq "" (
-   if "%arg:~0,2%" equ "/?" (
-       echo Usage: update.bat ^<release name or branch^>
-       echo Updates InvokeAI to use the indicated version of the code base.
-       echo Find the version or branch for the release you want, and pass it as the argument.
-       echo For example '.\update.bat v2.2.5' for release 2.2.5.
-       echo             '.\update.bat main' for the latest development version
-       echo.
-       echo If no argument provided then will install the most recent release, equivalent to
-       echo '.\update.bat latest'
-       exit /b
-   ) else (
-       set INVOKE_AI_VERSION=%arg%
-   )
-)
-
-set INVOKE_AI_SRC="https://github.com/invoke-ai/InvokeAI/archive/!INVOKE_AI_VERSION!.zip"
-set INVOKE_AI_DEP=https://raw.githubusercontent.com/invoke-ai/InvokeAI/!INVOKE_AI_VERSION!/environments-and-requirements/requirements-base.txt
-set INVOKE_AI_MODELS=https://raw.githubusercontent.com/invoke-ai/InvokeAI/$INVOKE_AI_VERSION/configs/INITIAL_MODELS.yaml
-
-call curl -I "%INVOKE_AI_DEP%" -fs >.tmp.out
-if %errorlevel% neq 0 (
-    echo '!INVOKE_AI_VERSION!' is not a known branch name or tag. Please check the version and try again.
-    echo "Press any key to continue"
-    pause
-    exit /b
-)
-del .tmp.out
-
-echo This script will update InvokeAI and all its dependencies to !INVOKE_AI_SRC!.
-echo If you do not want to do this, press control-C now!
-pause
-
-call curl -L "%INVOKE_AI_DEP%" > environments-and-requirements/requirements-base.txt
-call curl -L "%INVOKE_AI_MODELS%" > configs/INITIAL_MODELS.yaml
-
-
-call .venv\Scripts\activate.bat
-call .venv\Scripts\python -mpip install -r requirements.txt
-if %errorlevel% neq 0 (
-   echo Installation of requirements failed. See https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting for suggestions.
-   pause
-   exit /b
-)
-
-call .venv\Scripts\python -mpip install !INVOKE_AI_SRC!
-if %errorlevel% neq 0 (
-   echo Installation of InvokeAI failed. See https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting for suggestions.
-   pause
-   exit /b
-)
-
-@rem call .venv\Scripts\invokeai-configure --root=.
-
-@rem if %errorlevel% neq 0 (
-@rem    echo Configuration InvokeAI failed. See https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting for suggestions.
-@rem    pause
-@rem    exit /b
-@rem )
-
-echo InvokeAI has been updated to '%INVOKE_AI_VERSION%'
-
-echo "Press any key to continue"
-pause
-endlocal

installer/templates/update.sh.in

@@ -1,58 +0,0 @@
-#!/usr/bin/env bash
-
-set -eu
-
-if [ $# -ge 1 ] && [ "${1:0:2}" == "-h" ]; then
-    echo "Usage: update.sh <release>"
-    echo "Updates InvokeAI to use the indicated version of the code base."
-    echo "Find the version or branch for the release you want, and pass it as the argument."
-    echo "For example: update.sh v2.2.5 for release 2.2.5."
-    echo "             update.sh main for the current development version."
-    echo ""
-    echo "If no argument provided then will install the version tagged with 'latest', equivalent to"
-    echo "update.sh latest"
-    exit -1
-fi
-
-INVOKE_AI_VERSION=${1:-latest}
-
-INVOKE_AI_SRC="https://github.com/invoke-ai/InvokeAI/archive/$INVOKE_AI_VERSION.zip"
-INVOKE_AI_DEP=https://raw.githubusercontent.com/invoke-ai/InvokeAI/$INVOKE_AI_VERSION/environments-and-requirements/requirements-base.txt
-INVOKE_AI_MODELS=https://raw.githubusercontent.com/invoke-ai/InvokeAI/$INVOKE_AI_VERSION/configs/INITIAL_MODELS.yaml
-
-# ensure we're in the correct folder in case user's CWD is somewhere else
-scriptdir=$(dirname "$0")
-cd "$scriptdir"
-
-function _err_exit {
-    if test "$1" -ne 0
-    then
-	echo "Something went wrong while installing InvokeAI and/or its requirements."
-	echo "Update cannot continue. Please report this error to https://github.com/invoke-ai/InvokeAI/issues"
-        echo -e "Error code $1; Error caught was '$2'"
-        read -p "Press any key to exit..."
-        exit
-    fi
-}
-
-if ! curl -I "$INVOKE_AI_DEP" -fs >/dev/null; then
-    echo \'$INVOKE_AI_VERSION\' is not a known branch name or tag. Please check the version and try again.
-    exit
-fi
-
-echo This script will update InvokeAI and all its dependencies to version \'$INVOKE_AI_VERSION\'.
-echo If you do not want to do this, press control-C now!
-read -p "Press any key to continue, or CTRL-C to exit..."
-
-curl -L "$INVOKE_AI_DEP" > environments-and-requirements/requirements-base.txt
-curl -L "$INVOKE_AI_MODELS" > configs/INITIAL_MODELS.yaml
-
-. .venv/bin/activate
-
-./.venv/bin/python -mpip install -r requirements.txt
-_err_exit $? "The pip program failed to install InvokeAI's requirements."
-
-./.venv/bin/python -mpip install $INVOKE_AI_SRC
-_err_exit $? "The pip program failed to install InvokeAI."
-
-echo InvokeAI updated to \'$INVOKE_AI_VERSION\'

invokeai/app/api/dependencies.py

@@ -2,9 +2,14 @@
 
 from logging import Logger
 
+import torch
+
 from invokeai.app.services.item_storage.item_storage_memory import ItemStorageMemory
+from invokeai.app.services.object_serializer.object_serializer_disk import ObjectSerializerDisk
+from invokeai.app.services.object_serializer.object_serializer_forward_cache import ObjectSerializerForwardCache
 from invokeai.app.services.shared.sqlite.sqlite_util import init_db
 from invokeai.backend.model_manager.metadata import ModelMetadataStore
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningFieldData
 from invokeai.backend.util.logging import InvokeAILogger
 from invokeai.version.invokeai_version import __version__
 
@@ -23,8 +28,6 @@ from ..services.invocation_queue.invocation_queue_memory import MemoryInvocation
 from ..services.invocation_services import InvocationServices
 from ..services.invocation_stats.invocation_stats_default import InvocationStatsService
 from ..services.invoker import Invoker
-from ..services.latents_storage.latents_storage_disk import DiskLatentsStorage
-from ..services.latents_storage.latents_storage_forward_cache import ForwardCacheLatentsStorage
 from ..services.model_install import ModelInstallService
 from ..services.model_manager.model_manager_default import ModelManagerService
 from ..services.model_records import ModelRecordServiceSQL
@@ -68,6 +71,9 @@ class ApiDependencies:
         logger.debug(f"Internet connectivity is {config.internet_available}")
 
         output_folder = config.output_path
+        if output_folder is None:
+            raise ValueError("Output folder is not set")
+
         image_files = DiskImageFileStorage(f"{output_folder}/images")
 
         db = init_db(config=config, logger=logger, image_files=image_files)
@@ -84,7 +90,12 @@ class ApiDependencies:
         image_records = SqliteImageRecordStorage(db=db)
         images = ImageService()
         invocation_cache = MemoryInvocationCache(max_cache_size=config.node_cache_size)
-        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f"{output_folder}/latents"))
+        tensors = ObjectSerializerForwardCache(
+            ObjectSerializerDisk[torch.Tensor](output_folder / "tensors", ephemeral=True)
+        )
+        conditioning = ObjectSerializerForwardCache(
+            ObjectSerializerDisk[ConditioningFieldData](output_folder / "conditioning", ephemeral=True)
+        )
         model_manager = ModelManagerService(config, logger)
         model_record_service = ModelRecordServiceSQL(db=db)
         download_queue_service = DownloadQueueService(event_bus=events)
@@ -117,7 +128,6 @@ class ApiDependencies:
             image_records=image_records,
             images=images,
             invocation_cache=invocation_cache,
-            latents=latents,
             logger=logger,
             model_manager=model_manager,
             model_records=model_record_service,
@@ -131,6 +141,8 @@ class ApiDependencies:
             session_queue=session_queue,
             urls=urls,
             workflow_records=workflow_records,
+            tensors=tensors,
+            conditioning=conditioning,
         )
 
         ApiDependencies.invoker = Invoker(services)

invokeai/app/api/routers/images.py

@@ -8,7 +8,7 @@ from fastapi.routing import APIRouter
 from PIL import Image
 from pydantic import BaseModel, Field, ValidationError
 
-from invokeai.app.invocations.baseinvocation import MetadataField, MetadataFieldValidator
+from invokeai.app.invocations.fields import MetadataField, MetadataFieldValidator
 from invokeai.app.services.image_records.image_records_common import ImageCategory, ImageRecordChanges, ResourceOrigin
 from invokeai.app.services.images.images_common import ImageDTO, ImageUrlsDTO
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults

invokeai/app/api/sockets.py

@@ -14,7 +14,7 @@ class SocketIO:
 
     def __init__(self, app: FastAPI):
         self.__sio = AsyncServer(async_mode="asgi", cors_allowed_origins="*")
-        self.__app = ASGIApp(socketio_server=self.__sio, socketio_path="socket.io")
+        self.__app = ASGIApp(socketio_server=self.__sio, socketio_path="/ws/socket.io")
         app.mount("/ws", self.__app)
 
         self.__sio.on("subscribe_queue", handler=self._handle_sub_queue)

invokeai/app/api_app.py

@@ -6,6 +6,7 @@ import sys
 from invokeai.app.api.no_cache_staticfiles import NoCacheStaticFiles
 from invokeai.version.invokeai_version import __version__
 
+from .invocations.fields import InputFieldJSONSchemaExtra, OutputFieldJSONSchemaExtra
 from .services.config import InvokeAIAppConfig
 
 app_config = InvokeAIAppConfig.get_config()
@@ -57,8 +58,6 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
     from .api.sockets import SocketIO
     from .invocations.baseinvocation import (
         BaseInvocation,
-        InputFieldJSONSchemaExtra,
-        OutputFieldJSONSchemaExtra,
         UIConfigBase,
     )
 

invokeai/app/invocations/baseinvocation.py

@@ -12,13 +12,16 @@ from types import UnionType
 from typing import TYPE_CHECKING, Any, Callable, ClassVar, Iterable, Literal, Optional, Type, TypeVar, Union, cast
 
 import semver
-from pydantic import BaseModel, ConfigDict, Field, RootModel, TypeAdapter, create_model
-from pydantic.fields import FieldInfo, _Unset
+from pydantic import BaseModel, ConfigDict, Field, create_model
+from pydantic.fields import FieldInfo
 from pydantic_core import PydanticUndefined
 
+from invokeai.app.invocations.fields import (
+    FieldKind,
+    Input,
+)
 from invokeai.app.services.config.config_default import InvokeAIAppConfig
-from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.metaenum import MetaEnum
 from invokeai.app.util.misc import uuid_string
 from invokeai.backend.util.logging import InvokeAILogger
@@ -52,393 +55,6 @@ class Classification(str, Enum, metaclass=MetaEnum):
     Prototype = "prototype"
 
 
-class Input(str, Enum, metaclass=MetaEnum):
-    """
-    The type of input a field accepts.
-    - `Input.Direct`: The field must have its value provided directly, when the invocation and field \
-      are instantiated.
-    - `Input.Connection`: The field must have its value provided by a connection.
-    - `Input.Any`: The field may have its value provided either directly or by a connection.
-    """
-
-    Connection = "connection"
-    Direct = "direct"
-    Any = "any"
-
-
-class FieldKind(str, Enum, metaclass=MetaEnum):
-    """
-    The kind of field.
-    - `Input`: An input field on a node.
-    - `Output`: An output field on a node.
-    - `Internal`: A field which is treated as an input, but cannot be used in node definitions. Metadata is
-    one example. It is provided to nodes via the WithMetadata class, and we want to reserve the field name
-    "metadata" for this on all nodes. `FieldKind` is used to short-circuit the field name validation logic,
-    allowing "metadata" for that field.
-    - `NodeAttribute`: The field is a node attribute. These are fields which are not inputs or outputs,
-    but which are used to store information about the node. For example, the `id` and `type` fields are node
-    attributes.
-
-    The presence of this in `json_schema_extra["field_kind"]` is used when initializing node schemas on app
-    startup, and when generating the OpenAPI schema for the workflow editor.
-    """
-
-    Input = "input"
-    Output = "output"
-    Internal = "internal"
-    NodeAttribute = "node_attribute"
-
-
-class UIType(str, Enum, metaclass=MetaEnum):
-    """
-    Type hints for the UI for situations in which the field type is not enough to infer the correct UI type.
-
-    - Model Fields
-    The most common node-author-facing use will be for model fields. Internally, there is no difference
-    between SD-1, SD-2 and SDXL model fields - they all use the class `MainModelField`. To ensure the
-    base-model-specific UI is rendered, use e.g. `ui_type=UIType.SDXLMainModelField` to indicate that
-    the field is an SDXL main model field.
-
-    - Any Field
-    We cannot infer the usage of `typing.Any` via schema parsing, so you *must* use `ui_type=UIType.Any` to
-    indicate that the field accepts any type. Use with caution. This cannot be used on outputs.
-
-    - Scheduler Field
-    Special handling in the UI is needed for this field, which otherwise would be parsed as a plain enum field.
-
-    - Internal Fields
-    Similar to the Any Field, the `collect` and `iterate` nodes make use of `typing.Any`. To facilitate
-    handling these types in the client, we use `UIType._Collection` and `UIType._CollectionItem`. These
-    should not be used by node authors.
-
-    - DEPRECATED Fields
-    These types are deprecated and should not be used by node authors. A warning will be logged if one is
-    used, and the type will be ignored. They are included here for backwards compatibility.
-    """
-
-    # region Model Field Types
-    SDXLMainModel = "SDXLMainModelField"
-    SDXLRefinerModel = "SDXLRefinerModelField"
-    ONNXModel = "ONNXModelField"
-    VaeModel = "VAEModelField"
-    LoRAModel = "LoRAModelField"
-    ControlNetModel = "ControlNetModelField"
-    IPAdapterModel = "IPAdapterModelField"
-    # endregion
-
-    # region Misc Field Types
-    Scheduler = "SchedulerField"
-    Any = "AnyField"
-    # endregion
-
-    # region Internal Field Types
-    _Collection = "CollectionField"
-    _CollectionItem = "CollectionItemField"
-    # endregion
-
-    # region DEPRECATED
-    Boolean = "DEPRECATED_Boolean"
-    Color = "DEPRECATED_Color"
-    Conditioning = "DEPRECATED_Conditioning"
-    Control = "DEPRECATED_Control"
-    Float = "DEPRECATED_Float"
-    Image = "DEPRECATED_Image"
-    Integer = "DEPRECATED_Integer"
-    Latents = "DEPRECATED_Latents"
-    String = "DEPRECATED_String"
-    BooleanCollection = "DEPRECATED_BooleanCollection"
-    ColorCollection = "DEPRECATED_ColorCollection"
-    ConditioningCollection = "DEPRECATED_ConditioningCollection"
-    ControlCollection = "DEPRECATED_ControlCollection"
-    FloatCollection = "DEPRECATED_FloatCollection"
-    ImageCollection = "DEPRECATED_ImageCollection"
-    IntegerCollection = "DEPRECATED_IntegerCollection"
-    LatentsCollection = "DEPRECATED_LatentsCollection"
-    StringCollection = "DEPRECATED_StringCollection"
-    BooleanPolymorphic = "DEPRECATED_BooleanPolymorphic"
-    ColorPolymorphic = "DEPRECATED_ColorPolymorphic"
-    ConditioningPolymorphic = "DEPRECATED_ConditioningPolymorphic"
-    ControlPolymorphic = "DEPRECATED_ControlPolymorphic"
-    FloatPolymorphic = "DEPRECATED_FloatPolymorphic"
-    ImagePolymorphic = "DEPRECATED_ImagePolymorphic"
-    IntegerPolymorphic = "DEPRECATED_IntegerPolymorphic"
-    LatentsPolymorphic = "DEPRECATED_LatentsPolymorphic"
-    StringPolymorphic = "DEPRECATED_StringPolymorphic"
-    MainModel = "DEPRECATED_MainModel"
-    UNet = "DEPRECATED_UNet"
-    Vae = "DEPRECATED_Vae"
-    CLIP = "DEPRECATED_CLIP"
-    Collection = "DEPRECATED_Collection"
-    CollectionItem = "DEPRECATED_CollectionItem"
-    Enum = "DEPRECATED_Enum"
-    WorkflowField = "DEPRECATED_WorkflowField"
-    IsIntermediate = "DEPRECATED_IsIntermediate"
-    BoardField = "DEPRECATED_BoardField"
-    MetadataItem = "DEPRECATED_MetadataItem"
-    MetadataItemCollection = "DEPRECATED_MetadataItemCollection"
-    MetadataItemPolymorphic = "DEPRECATED_MetadataItemPolymorphic"
-    MetadataDict = "DEPRECATED_MetadataDict"
-    # endregion
-
-
-class UIComponent(str, Enum, metaclass=MetaEnum):
-    """
-    The type of UI component to use for a field, used to override the default components, which are
-    inferred from the field type.
-    """
-
-    None_ = "none"
-    Textarea = "textarea"
-    Slider = "slider"
-
-
-class InputFieldJSONSchemaExtra(BaseModel):
-    """
-    Extra attributes to be added to input fields and their OpenAPI schema. Used during graph execution,
-    and by the workflow editor during schema parsing and UI rendering.
-    """
-
-    input: Input
-    orig_required: bool
-    field_kind: FieldKind
-    default: Optional[Any] = None
-    orig_default: Optional[Any] = None
-    ui_hidden: bool = False
-    ui_type: Optional[UIType] = None
-    ui_component: Optional[UIComponent] = None
-    ui_order: Optional[int] = None
-    ui_choice_labels: Optional[dict[str, str]] = None
-
-    model_config = ConfigDict(
-        validate_assignment=True,
-        json_schema_serialization_defaults_required=True,
-    )
-
-
-class OutputFieldJSONSchemaExtra(BaseModel):
-    """
-    Extra attributes to be added to input fields and their OpenAPI schema. Used by the workflow editor
-    during schema parsing and UI rendering.
-    """
-
-    field_kind: FieldKind
-    ui_hidden: bool
-    ui_type: Optional[UIType]
-    ui_order: Optional[int]
-
-    model_config = ConfigDict(
-        validate_assignment=True,
-        json_schema_serialization_defaults_required=True,
-    )
-
-
-def InputField(
-    # copied from pydantic's Field
-    # TODO: Can we support default_factory?
-    default: Any = _Unset,
-    default_factory: Callable[[], Any] | None = _Unset,
-    title: str | None = _Unset,
-    description: str | None = _Unset,
-    pattern: str | None = _Unset,
-    strict: bool | None = _Unset,
-    gt: float | None = _Unset,
-    ge: float | None = _Unset,
-    lt: float | None = _Unset,
-    le: float | None = _Unset,
-    multiple_of: float | None = _Unset,
-    allow_inf_nan: bool | None = _Unset,
-    max_digits: int | None = _Unset,
-    decimal_places: int | None = _Unset,
-    min_length: int | None = _Unset,
-    max_length: int | None = _Unset,
-    # custom
-    input: Input = Input.Any,
-    ui_type: Optional[UIType] = None,
-    ui_component: Optional[UIComponent] = None,
-    ui_hidden: bool = False,
-    ui_order: Optional[int] = None,
-    ui_choice_labels: Optional[dict[str, str]] = None,
-) -> Any:
-    """
-    Creates an input field for an invocation.
-
-    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/latest/api/fields/#pydantic.fields.Field) \
-    that adds a few extra parameters to support graph execution and the node editor UI.
-
-    :param Input input: [Input.Any] The kind of input this field requires. \
-      `Input.Direct` means a value must be provided on instantiation. \
-      `Input.Connection` means the value must be provided by a connection. \
-      `Input.Any` means either will do.
-
-    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
-      In some situations, the field's type is not enough to infer the correct UI type. \
-      For example, model selection fields should render a dropdown UI component to select a model. \
-      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
-      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
-      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
-
-    :param UIComponent ui_component: [None] Optionally specifies a specific component to use in the UI. \
-      The UI will always render a suitable component, but sometimes you want something different than the default. \
-      For example, a `string` field will default to a single-line input, but you may want a multi-line textarea instead. \
-      For this case, you could provide `UIComponent.Textarea`.
-
-    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI.
-
-    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI.
-
-    :param dict[str, str] ui_choice_labels: [None] Specifies the labels to use for the choices in an enum field.
-    """
-
-    json_schema_extra_ = InputFieldJSONSchemaExtra(
-        input=input,
-        ui_type=ui_type,
-        ui_component=ui_component,
-        ui_hidden=ui_hidden,
-        ui_order=ui_order,
-        ui_choice_labels=ui_choice_labels,
-        field_kind=FieldKind.Input,
-        orig_required=True,
-    )
-
-    """
-    There is a conflict between the typing of invocation definitions and the typing of an invocation's
-    `invoke()` function.
-
-    On instantiation of a node, the invocation definition is used to create the python class. At this time,
-    any number of fields may be optional, because they may be provided by connections.
-
-    On calling of `invoke()`, however, those fields may be required.
-
-    For example, consider an ResizeImageInvocation with an `image: ImageField` field.
-
-    `image` is required during the call to `invoke()`, but when the python class is instantiated,
-    the field may not be present. This is fine, because that image field will be provided by a
-    connection from an ancestor node, which outputs an image.
-
-    This means we want to type the `image` field as optional for the node class definition, but required
-    for the `invoke()` function.
-
-    If we use `typing.Optional` in the node class definition, the field will be typed as optional in the
-    `invoke()` method, and we'll have to do a lot of runtime checks to ensure the field is present - or
-    any static type analysis tools will complain.
-
-    To get around this, in node class definitions, we type all fields correctly for the `invoke()` function,
-    but secretly make them optional in `InputField()`. We also store the original required bool and/or default
-    value. When we call `invoke()`, we use this stored information to do an additional check on the class.
-    """
-
-    if default_factory is not _Unset and default_factory is not None:
-        default = default_factory()
-        logger.warn('"default_factory" is not supported, calling it now to set "default"')
-
-    # These are the args we may wish pass to the pydantic `Field()` function
-    field_args = {
-        "default": default,
-        "title": title,
-        "description": description,
-        "pattern": pattern,
-        "strict": strict,
-        "gt": gt,
-        "ge": ge,
-        "lt": lt,
-        "le": le,
-        "multiple_of": multiple_of,
-        "allow_inf_nan": allow_inf_nan,
-        "max_digits": max_digits,
-        "decimal_places": decimal_places,
-        "min_length": min_length,
-        "max_length": max_length,
-    }
-
-    # We only want to pass the args that were provided, otherwise the `Field()`` function won't work as expected
-    provided_args = {k: v for (k, v) in field_args.items() if v is not PydanticUndefined}
-
-    # Because we are manually making fields optional, we need to store the original required bool for reference later
-    json_schema_extra_.orig_required = default is PydanticUndefined
-
-    # Make Input.Any and Input.Connection fields optional, providing None as a default if the field doesn't already have one
-    if input is Input.Any or input is Input.Connection:
-        default_ = None if default is PydanticUndefined else default
-        provided_args.update({"default": default_})
-        if default is not PydanticUndefined:
-            # Before invoking, we'll check for the original default value and set it on the field if the field has no value
-            json_schema_extra_.default = default
-            json_schema_extra_.orig_default = default
-    elif default is not PydanticUndefined:
-        default_ = default
-        provided_args.update({"default": default_})
-        json_schema_extra_.orig_default = default_
-
-    return Field(
-        **provided_args,
-        json_schema_extra=json_schema_extra_.model_dump(exclude_none=True),
-    )
-
-
-def OutputField(
-    # copied from pydantic's Field
-    default: Any = _Unset,
-    title: str | None = _Unset,
-    description: str | None = _Unset,
-    pattern: str | None = _Unset,
-    strict: bool | None = _Unset,
-    gt: float | None = _Unset,
-    ge: float | None = _Unset,
-    lt: float | None = _Unset,
-    le: float | None = _Unset,
-    multiple_of: float | None = _Unset,
-    allow_inf_nan: bool | None = _Unset,
-    max_digits: int | None = _Unset,
-    decimal_places: int | None = _Unset,
-    min_length: int | None = _Unset,
-    max_length: int | None = _Unset,
-    # custom
-    ui_type: Optional[UIType] = None,
-    ui_hidden: bool = False,
-    ui_order: Optional[int] = None,
-) -> Any:
-    """
-    Creates an output field for an invocation output.
-
-    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/1.10/usage/schema/#field-customization) \
-    that adds a few extra parameters to support graph execution and the node editor UI.
-
-    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
-      In some situations, the field's type is not enough to infer the correct UI type. \
-      For example, model selection fields should render a dropdown UI component to select a model. \
-      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
-      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
-      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
-
-    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI. \
-
-    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
-    """
-    return Field(
-        default=default,
-        title=title,
-        description=description,
-        pattern=pattern,
-        strict=strict,
-        gt=gt,
-        ge=ge,
-        lt=lt,
-        le=le,
-        multiple_of=multiple_of,
-        allow_inf_nan=allow_inf_nan,
-        max_digits=max_digits,
-        decimal_places=decimal_places,
-        min_length=min_length,
-        max_length=max_length,
-        json_schema_extra=OutputFieldJSONSchemaExtra(
-            ui_type=ui_type,
-            ui_hidden=ui_hidden,
-            ui_order=ui_order,
-            field_kind=FieldKind.Output,
-        ).model_dump(exclude_none=True),
-    )
-
-
 class UIConfigBase(BaseModel):
     """
     Provides additional node configuration to the UI.
@@ -460,33 +76,6 @@ class UIConfigBase(BaseModel):
     )
 
 
-class InvocationContext:
-    """Initialized and provided to on execution of invocations."""
-
-    services: InvocationServices
-    graph_execution_state_id: str
-    queue_id: str
-    queue_item_id: int
-    queue_batch_id: str
-    workflow: Optional[WorkflowWithoutID]
-
-    def __init__(
-        self,
-        services: InvocationServices,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        graph_execution_state_id: str,
-        workflow: Optional[WorkflowWithoutID],
-    ):
-        self.services = services
-        self.graph_execution_state_id = graph_execution_state_id
-        self.queue_id = queue_id
-        self.queue_item_id = queue_item_id
-        self.queue_batch_id = queue_batch_id
-        self.workflow = workflow
-
-
 class BaseInvocationOutput(BaseModel):
     """
     Base class for all invocation outputs.
@@ -632,7 +221,7 @@ class BaseInvocation(ABC, BaseModel):
         """Invoke with provided context and return outputs."""
         pass
 
-    def invoke_internal(self, context: InvocationContext) -> BaseInvocationOutput:
+    def invoke_internal(self, context: InvocationContext, services: "InvocationServices") -> BaseInvocationOutput:
         """
         Internal invoke method, calls `invoke()` after some prep.
         Handles optional fields that are required to call `invoke()` and invocation cache.
@@ -657,23 +246,23 @@ class BaseInvocation(ABC, BaseModel):
                     raise MissingInputException(self.model_fields["type"].default, field_name)
 
         # skip node cache codepath if it's disabled
-        if context.services.configuration.node_cache_size == 0:
+        if services.configuration.node_cache_size == 0:
             return self.invoke(context)
 
         output: BaseInvocationOutput
         if self.use_cache:
-            key = context.services.invocation_cache.create_key(self)
-            cached_value = context.services.invocation_cache.get(key)
+            key = services.invocation_cache.create_key(self)
+            cached_value = services.invocation_cache.get(key)
             if cached_value is None:
-                context.services.logger.debug(f'Invocation cache miss for type "{self.get_type()}": {self.id}')
+                services.logger.debug(f'Invocation cache miss for type "{self.get_type()}": {self.id}')
                 output = self.invoke(context)
-                context.services.invocation_cache.save(key, output)
+                services.invocation_cache.save(key, output)
                 return output
             else:
-                context.services.logger.debug(f'Invocation cache hit for type "{self.get_type()}": {self.id}')
+                services.logger.debug(f'Invocation cache hit for type "{self.get_type()}": {self.id}')
                 return cached_value
         else:
-            context.services.logger.debug(f'Skipping invocation cache for "{self.get_type()}": {self.id}')
+            services.logger.debug(f'Skipping invocation cache for "{self.get_type()}": {self.id}')
             return self.invoke(context)
 
     id: str = Field(
@@ -714,9 +303,7 @@ RESERVED_NODE_ATTRIBUTE_FIELD_NAMES = {
     "workflow",
 }
 
-RESERVED_INPUT_FIELD_NAMES = {
-    "metadata",
-}
+RESERVED_INPUT_FIELD_NAMES = {"metadata", "board"}
 
 RESERVED_OUTPUT_FIELD_NAMES = {"type"}
 
@@ -926,37 +513,3 @@ def invocation_output(
         return cls
 
     return wrapper
-
-
-class MetadataField(RootModel):
-    """
-    Pydantic model for metadata with custom root of type dict[str, Any].
-    Metadata is stored without a strict schema.
-    """
-
-    root: dict[str, Any] = Field(description="The metadata")
-
-
-MetadataFieldValidator = TypeAdapter(MetadataField)
-
-
-class WithMetadata(BaseModel):
-    metadata: Optional[MetadataField] = Field(
-        default=None,
-        description=FieldDescriptions.metadata,
-        json_schema_extra=InputFieldJSONSchemaExtra(
-            field_kind=FieldKind.Internal,
-            input=Input.Connection,
-            orig_required=False,
-        ).model_dump(exclude_none=True),
-    )
-
-
-class WithWorkflow:
-    workflow = None
-
-    def __init_subclass__(cls) -> None:
-        logger.warn(
-            f"{cls.__module__.split('.')[0]}.{cls.__name__}: WithWorkflow is deprecated. Use `context.workflow` to access the workflow."
-        )
-        super().__init_subclass__()

invokeai/app/invocations/collections.py

@@ -5,9 +5,11 @@ import numpy as np
 from pydantic import ValidationInfo, field_validator
 
 from invokeai.app.invocations.primitives import IntegerCollectionOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import SEED_MAX
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField
 
 
 @invocation(

invokeai/app/invocations/compel.py

@@ -1,14 +1,21 @@
-from dataclasses import dataclass
 from typing import List, Optional, Union
 
 import torch
 from compel import Compel, ReturnedEmbeddingsType
 from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
 
-from invokeai.app.invocations.primitives import ConditioningField, ConditioningOutput
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    Input,
+    InputField,
+    OutputField,
+    UIComponent,
+)
+from invokeai.app.invocations.primitives import ConditioningOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
     BasicConditioningInfo,
+    ConditioningFieldData,
     ExtraConditioningInfo,
     SDXLConditioningInfo,
 )
@@ -20,21 +27,12 @@ from ..util.ti_utils import extract_ti_triggers_from_prompt
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
     invocation,
     invocation_output,
 )
 from .model import ClipField
 
-
-@dataclass
-class ConditioningFieldData:
-    conditionings: List[BasicConditioningInfo]
-    # unconditioned: Optional[torch.Tensor]
+# unconditioned: Optional[torch.Tensor]
 
 
 # class ConditioningAlgo(str, Enum):
@@ -48,7 +46,7 @@ class ConditioningFieldData:
     title="Prompt",
     tags=["prompt", "compel"],
     category="conditioning",
-    version="1.0.0",
+    version="1.0.1",
 )
 class CompelInvocation(BaseInvocation):
     """Parse prompt using compel package to conditioning."""
@@ -66,25 +64,17 @@ class CompelInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        tokenizer_info = context.services.model_manager.get_model(
-            **self.clip.tokenizer.model_dump(),
-            context=context,
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **self.clip.text_encoder.model_dump(),
-            context=context,
-        )
+        tokenizer_info = context.models.load(**self.clip.tokenizer.model_dump())
+        text_encoder_info = context.models.load(**self.clip.text_encoder.model_dump())
 
         def _lora_loader():
             for lora in self.clip.loras:
-                lora_info = context.services.model_manager.get_model(
-                    **lora.model_dump(exclude={"weight"}), context=context
-                )
+                lora_info = context.models.load(**lora.model_dump(exclude={"weight"}))
                 yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
 
-        # loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+        # loras = [(context.models.get(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
         ti_list = []
         for trigger in extract_ti_triggers_from_prompt(self.prompt):
@@ -93,11 +83,10 @@ class CompelInvocation(BaseInvocation):
                 ti_list.append(
                     (
                         name,
-                        context.services.model_manager.get_model(
+                        context.models.load(
                             model_name=name,
                             base_model=self.clip.text_encoder.base_model,
                             model_type=ModelType.TextualInversion,
-                            context=context,
                         ).context.model,
                     )
                 )
@@ -128,7 +117,7 @@ class CompelInvocation(BaseInvocation):
 
             conjunction = Compel.parse_prompt_string(self.prompt)
 
-            if context.services.configuration.log_tokenization:
+            if context.config.get().log_tokenization:
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
             c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
@@ -149,14 +138,9 @@ class CompelInvocation(BaseInvocation):
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 class SDXLPromptInvocationBase:
@@ -169,14 +153,8 @@ class SDXLPromptInvocationBase:
         lora_prefix: str,
         zero_on_empty: bool,
     ):
-        tokenizer_info = context.services.model_manager.get_model(
-            **clip_field.tokenizer.model_dump(),
-            context=context,
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **clip_field.text_encoder.model_dump(),
-            context=context,
-        )
+        tokenizer_info = context.models.load(**clip_field.tokenizer.model_dump())
+        text_encoder_info = context.models.load(**clip_field.text_encoder.model_dump())
 
         # return zero on empty
         if prompt == "" and zero_on_empty:
@@ -200,14 +178,12 @@ class SDXLPromptInvocationBase:
 
         def _lora_loader():
             for lora in clip_field.loras:
-                lora_info = context.services.model_manager.get_model(
-                    **lora.model_dump(exclude={"weight"}), context=context
-                )
+                lora_info = context.models.load(**lora.model_dump(exclude={"weight"}))
                 yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
 
-        # loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+        # loras = [(context.models.get(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
         ti_list = []
         for trigger in extract_ti_triggers_from_prompt(prompt):
@@ -216,11 +192,10 @@ class SDXLPromptInvocationBase:
                 ti_list.append(
                     (
                         name,
-                        context.services.model_manager.get_model(
+                        context.models.load(
                             model_name=name,
                             base_model=clip_field.text_encoder.base_model,
                             model_type=ModelType.TextualInversion,
-                            context=context,
                         ).context.model,
                     )
                 )
@@ -253,7 +228,7 @@ class SDXLPromptInvocationBase:
 
             conjunction = Compel.parse_prompt_string(prompt)
 
-            if context.services.configuration.log_tokenization:
+            if context.config.get().log_tokenization:
                 # TODO: better logging for and syntax
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
@@ -286,7 +261,7 @@ class SDXLPromptInvocationBase:
     title="SDXL Prompt",
     tags=["sdxl", "compel", "prompt"],
     category="conditioning",
-    version="1.0.0",
+    version="1.0.1",
 )
 class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
@@ -368,14 +343,9 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 @invocation(
@@ -383,7 +353,7 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     title="SDXL Refiner Prompt",
     tags=["sdxl", "compel", "prompt"],
     category="conditioning",
-    version="1.0.0",
+    version="1.0.1",
 )
 class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
@@ -421,14 +391,9 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 @invocation_output("clip_skip_output")

invokeai/app/invocations/constants.py

@@ -0,0 +1,14 @@
+from typing import Literal
+
+from invokeai.backend.stable_diffusion.schedulers import SCHEDULER_MAP
+
+LATENT_SCALE_FACTOR = 8
+"""
+HACK: Many nodes are currently hard-coded to use a fixed latent scale factor of 8. This is fragile, and will need to
+be addressed if future models use a different latent scale factor. Also, note that there may be places where the scale
+factor is hard-coded to a literal '8' rather than using this constant.
+The ratio of image:latent dimensions is LATENT_SCALE_FACTOR:1, or 8:1.
+"""
+
+SCHEDULER_NAME_VALUES = Literal[tuple(SCHEDULER_MAP.keys())]
+"""A literal type representing the valid scheduler names."""

invokeai/app/invocations/controlnet_image_processors.py

@@ -17,7 +17,6 @@ from controlnet_aux import (
     MidasDetector,
     MLSDdetector,
     NormalBaeDetector,
-    OpenposeDetector,
     PidiNetDetector,
     SamDetector,
     ZoeDetector,
@@ -26,21 +25,25 @@ from controlnet_aux.util import HWC3, ade_palette
 from PIL import Image
 from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
 
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    ImageField,
+    Input,
+    InputField,
+    OutputField,
+    WithBoard,
+    WithMetadata,
+)
+from invokeai.app.invocations.primitives import ImageOutput
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.image_util.depth_anything import DepthAnythingDetector
+from invokeai.backend.image_util.dw_openpose import DWOpenposeDetector
+from invokeai.backend.model_management.models.base import BaseModelType
 
-from ...backend.model_management import BaseModelType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    WithMetadata,
     invocation,
     invocation_output,
 )
@@ -140,7 +143,7 @@ class ControlNetInvocation(BaseInvocation):
 
 
 # This invocation exists for other invocations to subclass it - do not register with @invocation!
-class ImageProcessorInvocation(BaseInvocation, WithMetadata):
+class ImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Base class for invocations that preprocess images for ControlNet"""
 
     image: ImageField = InputField(description="The image to process")
@@ -150,22 +153,13 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata):
         return image
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        raw_image = context.services.images.get_pil_image(self.image.image_name)
+        raw_image = context.images.get_pil(self.image.image_name)
         # image type should be PIL.PngImagePlugin.PngImageFile ?
         processed_image = self.run_processor(raw_image)
 
         # currently can't see processed image in node UI without a showImage node,
         #    so for now setting image_type to RESULT instead of INTERMEDIATE so will get saved in gallery
-        image_dto = context.services.images.create(
-            image=processed_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.CONTROL,
-            session_id=context.graph_execution_state_id,
-            node_id=self.id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=processed_image)
 
         """Builds an ImageOutput and its ImageField"""
         processed_image_field = ImageField(image_name=image_dto.image_name)
@@ -184,7 +178,7 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata):
     title="Canny Processor",
     tags=["controlnet", "canny"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class CannyImageProcessorInvocation(ImageProcessorInvocation):
     """Canny edge detection for ControlNet"""
@@ -207,7 +201,7 @@ class CannyImageProcessorInvocation(ImageProcessorInvocation):
     title="HED (softedge) Processor",
     tags=["controlnet", "hed", "softedge"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class HedImageProcessorInvocation(ImageProcessorInvocation):
     """Applies HED edge detection to image"""
@@ -236,7 +230,7 @@ class HedImageProcessorInvocation(ImageProcessorInvocation):
     title="Lineart Processor",
     tags=["controlnet", "lineart"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class LineartImageProcessorInvocation(ImageProcessorInvocation):
     """Applies line art processing to image"""
@@ -258,7 +252,7 @@ class LineartImageProcessorInvocation(ImageProcessorInvocation):
     title="Lineart Anime Processor",
     tags=["controlnet", "lineart", "anime"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies line art anime processing to image"""
@@ -276,37 +270,12 @@ class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "openpose_image_processor",
-    title="Openpose Processor",
-    tags=["controlnet", "openpose", "pose"],
-    category="controlnet",
-    version="1.2.0",
-)
-class OpenposeImageProcessorInvocation(ImageProcessorInvocation):
-    """Applies Openpose processing to image"""
-
-    hand_and_face: bool = InputField(default=False, description="Whether to use hands and face mode")
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
-
-    def run_processor(self, image):
-        openpose_processor = OpenposeDetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = openpose_processor(
-            image,
-            detect_resolution=self.detect_resolution,
-            image_resolution=self.image_resolution,
-            hand_and_face=self.hand_and_face,
-        )
-        return processed_image
-
-
 @invocation(
     "midas_depth_image_processor",
     title="Midas Depth Processor",
     tags=["controlnet", "midas"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Midas depth processing to image"""
@@ -333,7 +302,7 @@ class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
     title="Normal BAE Processor",
     tags=["controlnet"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies NormalBae processing to image"""
@@ -350,7 +319,7 @@ class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
 
 
 @invocation(
-    "mlsd_image_processor", title="MLSD Processor", tags=["controlnet", "mlsd"], category="controlnet", version="1.2.0"
+    "mlsd_image_processor", title="MLSD Processor", tags=["controlnet", "mlsd"], category="controlnet", version="1.2.1"
 )
 class MlsdImageProcessorInvocation(ImageProcessorInvocation):
     """Applies MLSD processing to image"""
@@ -373,7 +342,7 @@ class MlsdImageProcessorInvocation(ImageProcessorInvocation):
 
 
 @invocation(
-    "pidi_image_processor", title="PIDI Processor", tags=["controlnet", "pidi"], category="controlnet", version="1.2.0"
+    "pidi_image_processor", title="PIDI Processor", tags=["controlnet", "pidi"], category="controlnet", version="1.2.1"
 )
 class PidiImageProcessorInvocation(ImageProcessorInvocation):
     """Applies PIDI processing to image"""
@@ -400,7 +369,7 @@ class PidiImageProcessorInvocation(ImageProcessorInvocation):
     title="Content Shuffle Processor",
     tags=["controlnet", "contentshuffle"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
     """Applies content shuffle processing to image"""
@@ -430,7 +399,7 @@ class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
     title="Zoe (Depth) Processor",
     tags=["controlnet", "zoe", "depth"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Zoe depth processing to image"""
@@ -446,7 +415,7 @@ class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
     title="Mediapipe Face Processor",
     tags=["controlnet", "mediapipe", "face"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     """Applies mediapipe face processing to image"""
@@ -469,7 +438,7 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     title="Leres (Depth) Processor",
     tags=["controlnet", "leres", "depth"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class LeresImageProcessorInvocation(ImageProcessorInvocation):
     """Applies leres processing to image"""
@@ -498,7 +467,7 @@ class LeresImageProcessorInvocation(ImageProcessorInvocation):
     title="Tile Resample Processor",
     tags=["controlnet", "tile"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class TileResamplerProcessorInvocation(ImageProcessorInvocation):
     """Tile resampler processor"""
@@ -538,7 +507,7 @@ class TileResamplerProcessorInvocation(ImageProcessorInvocation):
     title="Segment Anything Processor",
     tags=["controlnet", "segmentanything"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class SegmentAnythingProcessorInvocation(ImageProcessorInvocation):
     """Applies segment anything processing to image"""
@@ -580,7 +549,7 @@ class SamDetectorReproducibleColors(SamDetector):
     title="Color Map Processor",
     tags=["controlnet"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
     """Generates a color map from the provided image"""
@@ -624,7 +593,7 @@ class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
     resolution: int = InputField(default=512, ge=64, multiple_of=64, description=FieldDescriptions.image_res)
     offload: bool = InputField(default=False)
 
-    def run_processor(self, image):
+    def run_processor(self, image: Image.Image):
         depth_anything_detector = DepthAnythingDetector()
         depth_anything_detector.load_model(model_size=self.model_size)
 
@@ -633,3 +602,30 @@ class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
 
         processed_image = depth_anything_detector(image=image, resolution=self.resolution, offload=self.offload)
         return processed_image
+
+
+@invocation(
+    "dw_openpose_image_processor",
+    title="DW Openpose Image Processor",
+    tags=["controlnet", "dwpose", "openpose"],
+    category="controlnet",
+    version="1.0.0",
+)
+class DWOpenposeImageProcessorInvocation(ImageProcessorInvocation):
+    """Generates an openpose pose from an image using DWPose"""
+
+    draw_body: bool = InputField(default=True)
+    draw_face: bool = InputField(default=False)
+    draw_hands: bool = InputField(default=False)
+    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+
+    def run_processor(self, image):
+        dw_openpose = DWOpenposeDetector()
+        processed_image = dw_openpose(
+            image,
+            draw_face=self.draw_face,
+            draw_hands=self.draw_hands,
+            draw_body=self.draw_body,
+            resolution=self.image_resolution,
+        )
+        return processed_image

invokeai/app/invocations/cv.py

@@ -5,22 +5,24 @@ import cv2 as cv
 import numpy
 from PIL import Image, ImageOps
 
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, WithBoard, WithMetadata
 
 
-@invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.2.0")
-class CvInpaintInvocation(BaseInvocation, WithMetadata):
+@invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.2.1")
+class CvInpaintInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Simple inpaint using opencv."""
 
     image: ImageField = InputField(description="The image to inpaint")
     mask: ImageField = InputField(description="The mask to use when inpainting")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-        mask = context.services.images.get_pil_image(self.mask.image_name)
+        image = context.images.get_pil(self.image.image_name)
+        mask = context.images.get_pil(self.mask.image_name)
 
         # Convert to cv image/mask
         # TODO: consider making these utility functions
@@ -34,18 +36,6 @@ class CvInpaintInvocation(BaseInvocation, WithMetadata):
         # TODO: consider making a utility function
         image_inpainted = Image.fromarray(cv.cvtColor(cv_inpainted, cv.COLOR_BGR2RGB))
 
-        image_dto = context.services.images.create(
-            image=image_inpainted,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=image_inpainted)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/facetools.py

@@ -13,15 +13,13 @@ from pydantic import field_validator
 import invokeai.assets.fonts as font_assets
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
-    InputField,
-    InvocationContext,
-    OutputField,
-    WithMetadata,
     invocation,
     invocation_output,
 )
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField, InputField, OutputField, WithBoard, WithMetadata
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.image_records.image_records_common import ImageCategory
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 
 @invocation_output("face_mask_output")
@@ -306,37 +304,37 @@ def extract_face(
 
     # Adjust the crop boundaries to stay within the original image's dimensions
     if x_min < 0:
-        context.services.logger.warning("FaceTools --> -X-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> -X-axis padding reached image edge.")
         x_max -= x_min
         x_min = 0
     elif x_max > mask.width:
-        context.services.logger.warning("FaceTools --> +X-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> +X-axis padding reached image edge.")
         x_min -= x_max - mask.width
         x_max = mask.width
 
     if y_min < 0:
-        context.services.logger.warning("FaceTools --> +Y-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> +Y-axis padding reached image edge.")
         y_max -= y_min
         y_min = 0
     elif y_max > mask.height:
-        context.services.logger.warning("FaceTools --> -Y-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> -Y-axis padding reached image edge.")
         y_min -= y_max - mask.height
         y_max = mask.height
 
     # Ensure the crop is square and adjust the boundaries if needed
     if x_max - x_min != crop_size:
-        context.services.logger.warning("FaceTools --> Limiting x-axis padding to constrain bounding box to a square.")
+        context.logger.warning("FaceTools --> Limiting x-axis padding to constrain bounding box to a square.")
         diff = crop_size - (x_max - x_min)
         x_min -= diff // 2
         x_max += diff - diff // 2
 
     if y_max - y_min != crop_size:
-        context.services.logger.warning("FaceTools --> Limiting y-axis padding to constrain bounding box to a square.")
+        context.logger.warning("FaceTools --> Limiting y-axis padding to constrain bounding box to a square.")
         diff = crop_size - (y_max - y_min)
         y_min -= diff // 2
         y_max += diff - diff // 2
 
-    context.services.logger.info(f"FaceTools --> Calculated bounding box (8 multiple): {crop_size}")
+    context.logger.info(f"FaceTools --> Calculated bounding box (8 multiple): {crop_size}")
 
     # Crop the output image to the specified size with the center of the face mesh as the center.
     mask = mask.crop((x_min, y_min, x_max, y_max))
@@ -368,7 +366,7 @@ def get_faces_list(
 
     # Generate the face box mask and get the center of the face.
     if not should_chunk:
-        context.services.logger.info("FaceTools --> Attempting full image face detection.")
+        context.logger.info("FaceTools --> Attempting full image face detection.")
         result = generate_face_box_mask(
             context=context,
             minimum_confidence=minimum_confidence,
@@ -380,7 +378,7 @@ def get_faces_list(
             draw_mesh=draw_mesh,
         )
     if should_chunk or len(result) == 0:
-        context.services.logger.info("FaceTools --> Chunking image (chunk toggled on, or no face found in full image).")
+        context.logger.info("FaceTools --> Chunking image (chunk toggled on, or no face found in full image).")
         width, height = image.size
         image_chunks = []
         x_offsets = []
@@ -399,7 +397,7 @@ def get_faces_list(
                 x_offsets.append(x)
                 y_offsets.append(0)
                 fx += increment
-                context.services.logger.info(f"FaceTools --> Chunk starting at x = {x}")
+                context.logger.info(f"FaceTools --> Chunk starting at x = {x}")
         elif height > width:
             # Portrait - slice the image vertically
             fy = 0.0
@@ -411,10 +409,10 @@ def get_faces_list(
                 x_offsets.append(0)
                 y_offsets.append(y)
                 fy += increment
-                context.services.logger.info(f"FaceTools --> Chunk starting at y = {y}")
+                context.logger.info(f"FaceTools --> Chunk starting at y = {y}")
 
         for idx in range(len(image_chunks)):
-            context.services.logger.info(f"FaceTools --> Evaluating faces in chunk {idx}")
+            context.logger.info(f"FaceTools --> Evaluating faces in chunk {idx}")
             result = result + generate_face_box_mask(
                 context=context,
                 minimum_confidence=minimum_confidence,
@@ -428,7 +426,7 @@ def get_faces_list(
 
         if len(result) == 0:
             # Give up
-            context.services.logger.warning(
+            context.logger.warning(
                 "FaceTools --> No face detected in chunked input image. Passing through original image."
             )
 
@@ -437,7 +435,7 @@ def get_faces_list(
     return all_faces
 
 
-@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.2.0")
+@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.2.1")
 class FaceOffInvocation(BaseInvocation, WithMetadata):
     """Bound, extract, and mask a face from an image using MediaPipe detection"""
 
@@ -470,11 +468,11 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         )
 
         if len(all_faces) == 0:
-            context.services.logger.warning("FaceOff --> No faces detected. Passing through original image.")
+            context.logger.warning("FaceOff --> No faces detected. Passing through original image.")
             return None
 
         if self.face_id > len(all_faces) - 1:
-            context.services.logger.warning(
+            context.logger.warning(
                 f"FaceOff --> Face ID {self.face_id} is outside of the number of faces detected ({len(all_faces)}). Passing through original image."
             )
             return None
@@ -486,7 +484,7 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         return face_data
 
     def invoke(self, context: InvocationContext) -> FaceOffOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result = self.faceoff(context=context, image=image)
 
         if result is None:
@@ -500,24 +498,9 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
             x = result["x_min"]
             y = result["y_min"]
 
-        image_dto = context.services.images.create(
-            image=result_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result_image)
 
-        mask_dto = context.services.images.create(
-            image=result_mask,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.MASK,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
+        mask_dto = context.images.save(image=result_mask, image_category=ImageCategory.MASK)
 
         output = FaceOffOutput(
             image=ImageField(image_name=image_dto.image_name),
@@ -531,7 +514,7 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         return output
 
 
-@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.2.0")
+@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.2.1")
 class FaceMaskInvocation(BaseInvocation, WithMetadata):
     """Face mask creation using mediapipe face detection"""
 
@@ -580,7 +563,7 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
 
             if len(intersected_face_ids) == 0:
                 id_range_str = ",".join([str(id) for id in id_range])
-                context.services.logger.warning(
+                context.logger.warning(
                     f"Face IDs must be in range of detected faces - requested {self.face_ids}, detected {id_range_str}. Passing through original image."
                 )
                 return FaceMaskResult(
@@ -616,27 +599,12 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
         )
 
     def invoke(self, context: InvocationContext) -> FaceMaskOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result = self.facemask(context=context, image=image)
 
-        image_dto = context.services.images.create(
-            image=result["image"],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result["image"])
 
-        mask_dto = context.services.images.create(
-            image=result["mask"],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.MASK,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
+        mask_dto = context.images.save(image=result["mask"], image_category=ImageCategory.MASK)
 
         output = FaceMaskOutput(
             image=ImageField(image_name=image_dto.image_name),
@@ -649,9 +617,9 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
 
 
 @invocation(
-    "face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.2.0"
+    "face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.2.1"
 )
-class FaceIdentifierInvocation(BaseInvocation, WithMetadata):
+class FaceIdentifierInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Outputs an image with detected face IDs printed on each face. For use with other FaceTools."""
 
     image: ImageField = InputField(description="Image to face detect")
@@ -705,21 +673,9 @@ class FaceIdentifierInvocation(BaseInvocation, WithMetadata):
         return image
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result_image = self.faceidentifier(context=context, image=image)
 
-        image_dto = context.services.images.create(
-            image=result_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result_image)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/fields.py

@@ -0,0 +1,565 @@
+from enum import Enum
+from typing import Any, Callable, Optional, Tuple
+
+from pydantic import BaseModel, ConfigDict, Field, RootModel, TypeAdapter
+from pydantic.fields import _Unset
+from pydantic_core import PydanticUndefined
+
+from invokeai.app.util.metaenum import MetaEnum
+from invokeai.backend.util.logging import InvokeAILogger
+
+logger = InvokeAILogger.get_logger()
+
+
+class UIType(str, Enum, metaclass=MetaEnum):
+    """
+    Type hints for the UI for situations in which the field type is not enough to infer the correct UI type.
+
+    - Model Fields
+    The most common node-author-facing use will be for model fields. Internally, there is no difference
+    between SD-1, SD-2 and SDXL model fields - they all use the class `MainModelField`. To ensure the
+    base-model-specific UI is rendered, use e.g. `ui_type=UIType.SDXLMainModelField` to indicate that
+    the field is an SDXL main model field.
+
+    - Any Field
+    We cannot infer the usage of `typing.Any` via schema parsing, so you *must* use `ui_type=UIType.Any` to
+    indicate that the field accepts any type. Use with caution. This cannot be used on outputs.
+
+    - Scheduler Field
+    Special handling in the UI is needed for this field, which otherwise would be parsed as a plain enum field.
+
+    - Internal Fields
+    Similar to the Any Field, the `collect` and `iterate` nodes make use of `typing.Any`. To facilitate
+    handling these types in the client, we use `UIType._Collection` and `UIType._CollectionItem`. These
+    should not be used by node authors.
+
+    - DEPRECATED Fields
+    These types are deprecated and should not be used by node authors. A warning will be logged if one is
+    used, and the type will be ignored. They are included here for backwards compatibility.
+    """
+
+    # region Model Field Types
+    SDXLMainModel = "SDXLMainModelField"
+    SDXLRefinerModel = "SDXLRefinerModelField"
+    ONNXModel = "ONNXModelField"
+    VaeModel = "VAEModelField"
+    LoRAModel = "LoRAModelField"
+    ControlNetModel = "ControlNetModelField"
+    IPAdapterModel = "IPAdapterModelField"
+    # endregion
+
+    # region Misc Field Types
+    Scheduler = "SchedulerField"
+    Any = "AnyField"
+    # endregion
+
+    # region Internal Field Types
+    _Collection = "CollectionField"
+    _CollectionItem = "CollectionItemField"
+    # endregion
+
+    # region DEPRECATED
+    Boolean = "DEPRECATED_Boolean"
+    Color = "DEPRECATED_Color"
+    Conditioning = "DEPRECATED_Conditioning"
+    Control = "DEPRECATED_Control"
+    Float = "DEPRECATED_Float"
+    Image = "DEPRECATED_Image"
+    Integer = "DEPRECATED_Integer"
+    Latents = "DEPRECATED_Latents"
+    String = "DEPRECATED_String"
+    BooleanCollection = "DEPRECATED_BooleanCollection"
+    ColorCollection = "DEPRECATED_ColorCollection"
+    ConditioningCollection = "DEPRECATED_ConditioningCollection"
+    ControlCollection = "DEPRECATED_ControlCollection"
+    FloatCollection = "DEPRECATED_FloatCollection"
+    ImageCollection = "DEPRECATED_ImageCollection"
+    IntegerCollection = "DEPRECATED_IntegerCollection"
+    LatentsCollection = "DEPRECATED_LatentsCollection"
+    StringCollection = "DEPRECATED_StringCollection"
+    BooleanPolymorphic = "DEPRECATED_BooleanPolymorphic"
+    ColorPolymorphic = "DEPRECATED_ColorPolymorphic"
+    ConditioningPolymorphic = "DEPRECATED_ConditioningPolymorphic"
+    ControlPolymorphic = "DEPRECATED_ControlPolymorphic"
+    FloatPolymorphic = "DEPRECATED_FloatPolymorphic"
+    ImagePolymorphic = "DEPRECATED_ImagePolymorphic"
+    IntegerPolymorphic = "DEPRECATED_IntegerPolymorphic"
+    LatentsPolymorphic = "DEPRECATED_LatentsPolymorphic"
+    StringPolymorphic = "DEPRECATED_StringPolymorphic"
+    MainModel = "DEPRECATED_MainModel"
+    UNet = "DEPRECATED_UNet"
+    Vae = "DEPRECATED_Vae"
+    CLIP = "DEPRECATED_CLIP"
+    Collection = "DEPRECATED_Collection"
+    CollectionItem = "DEPRECATED_CollectionItem"
+    Enum = "DEPRECATED_Enum"
+    WorkflowField = "DEPRECATED_WorkflowField"
+    IsIntermediate = "DEPRECATED_IsIntermediate"
+    BoardField = "DEPRECATED_BoardField"
+    MetadataItem = "DEPRECATED_MetadataItem"
+    MetadataItemCollection = "DEPRECATED_MetadataItemCollection"
+    MetadataItemPolymorphic = "DEPRECATED_MetadataItemPolymorphic"
+    MetadataDict = "DEPRECATED_MetadataDict"
+
+
+class UIComponent(str, Enum, metaclass=MetaEnum):
+    """
+    The type of UI component to use for a field, used to override the default components, which are
+    inferred from the field type.
+    """
+
+    None_ = "none"
+    Textarea = "textarea"
+    Slider = "slider"
+
+
+class FieldDescriptions:
+    denoising_start = "When to start denoising, expressed a percentage of total steps"
+    denoising_end = "When to stop denoising, expressed a percentage of total steps"
+    cfg_scale = "Classifier-Free Guidance scale"
+    cfg_rescale_multiplier = "Rescale multiplier for CFG guidance, used for models trained with zero-terminal SNR"
+    scheduler = "Scheduler to use during inference"
+    positive_cond = "Positive conditioning tensor"
+    negative_cond = "Negative conditioning tensor"
+    noise = "Noise tensor"
+    clip = "CLIP (tokenizer, text encoder, LoRAs) and skipped layer count"
+    unet = "UNet (scheduler, LoRAs)"
+    vae = "VAE"
+    cond = "Conditioning tensor"
+    controlnet_model = "ControlNet model to load"
+    vae_model = "VAE model to load"
+    lora_model = "LoRA model to load"
+    main_model = "Main model (UNet, VAE, CLIP) to load"
+    sdxl_main_model = "SDXL Main model (UNet, VAE, CLIP1, CLIP2) to load"
+    sdxl_refiner_model = "SDXL Refiner Main Modde (UNet, VAE, CLIP2) to load"
+    onnx_main_model = "ONNX Main model (UNet, VAE, CLIP) to load"
+    lora_weight = "The weight at which the LoRA is applied to each model"
+    compel_prompt = "Prompt to be parsed by Compel to create a conditioning tensor"
+    raw_prompt = "Raw prompt text (no parsing)"
+    sdxl_aesthetic = "The aesthetic score to apply to the conditioning tensor"
+    skipped_layers = "Number of layers to skip in text encoder"
+    seed = "Seed for random number generation"
+    steps = "Number of steps to run"
+    width = "Width of output (px)"
+    height = "Height of output (px)"
+    control = "ControlNet(s) to apply"
+    ip_adapter = "IP-Adapter to apply"
+    t2i_adapter = "T2I-Adapter(s) to apply"
+    denoised_latents = "Denoised latents tensor"
+    latents = "Latents tensor"
+    strength = "Strength of denoising (proportional to steps)"
+    metadata = "Optional metadata to be saved with the image"
+    metadata_collection = "Collection of Metadata"
+    metadata_item_polymorphic = "A single metadata item or collection of metadata items"
+    metadata_item_label = "Label for this metadata item"
+    metadata_item_value = "The value for this metadata item (may be any type)"
+    workflow = "Optional workflow to be saved with the image"
+    interp_mode = "Interpolation mode"
+    torch_antialias = "Whether or not to apply antialiasing (bilinear or bicubic only)"
+    fp32 = "Whether or not to use full float32 precision"
+    precision = "Precision to use"
+    tiled = "Processing using overlapping tiles (reduce memory consumption)"
+    detect_res = "Pixel resolution for detection"
+    image_res = "Pixel resolution for output image"
+    safe_mode = "Whether or not to use safe mode"
+    scribble_mode = "Whether or not to use scribble mode"
+    scale_factor = "The factor by which to scale"
+    blend_alpha = (
+        "Blending factor. 0.0 = use input A only, 1.0 = use input B only, 0.5 = 50% mix of input A and input B."
+    )
+    num_1 = "The first number"
+    num_2 = "The second number"
+    mask = "The mask to use for the operation"
+    board = "The board to save the image to"
+    image = "The image to process"
+    tile_size = "Tile size"
+    inclusive_low = "The inclusive low value"
+    exclusive_high = "The exclusive high value"
+    decimal_places = "The number of decimal places to round to"
+    freeu_s1 = 'Scaling factor for stage 1 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
+    freeu_s2 = 'Scaling factor for stage 2 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
+    freeu_b1 = "Scaling factor for stage 1 to amplify the contributions of backbone features."
+    freeu_b2 = "Scaling factor for stage 2 to amplify the contributions of backbone features."
+
+
+class ImageField(BaseModel):
+    """An image primitive field"""
+
+    image_name: str = Field(description="The name of the image")
+
+
+class BoardField(BaseModel):
+    """A board primitive field"""
+
+    board_id: str = Field(description="The id of the board")
+
+
+class DenoiseMaskField(BaseModel):
+    """An inpaint mask field"""
+
+    mask_name: str = Field(description="The name of the mask image")
+    masked_latents_name: Optional[str] = Field(default=None, description="The name of the masked image latents")
+
+
+class LatentsField(BaseModel):
+    """A latents tensor primitive field"""
+
+    latents_name: str = Field(description="The name of the latents")
+    seed: Optional[int] = Field(default=None, description="Seed used to generate this latents")
+
+
+class ColorField(BaseModel):
+    """A color primitive field"""
+
+    r: int = Field(ge=0, le=255, description="The red component")
+    g: int = Field(ge=0, le=255, description="The green component")
+    b: int = Field(ge=0, le=255, description="The blue component")
+    a: int = Field(ge=0, le=255, description="The alpha component")
+
+    def tuple(self) -> Tuple[int, int, int, int]:
+        return (self.r, self.g, self.b, self.a)
+
+
+class ConditioningField(BaseModel):
+    """A conditioning tensor primitive value"""
+
+    conditioning_name: str = Field(description="The name of conditioning tensor")
+    # endregion
+
+
+class MetadataField(RootModel):
+    """
+    Pydantic model for metadata with custom root of type dict[str, Any].
+    Metadata is stored without a strict schema.
+    """
+
+    root: dict[str, Any] = Field(description="The metadata")
+
+
+MetadataFieldValidator = TypeAdapter(MetadataField)
+
+
+class Input(str, Enum, metaclass=MetaEnum):
+    """
+    The type of input a field accepts.
+    - `Input.Direct`: The field must have its value provided directly, when the invocation and field \
+      are instantiated.
+    - `Input.Connection`: The field must have its value provided by a connection.
+    - `Input.Any`: The field may have its value provided either directly or by a connection.
+    """
+
+    Connection = "connection"
+    Direct = "direct"
+    Any = "any"
+
+
+class FieldKind(str, Enum, metaclass=MetaEnum):
+    """
+    The kind of field.
+    - `Input`: An input field on a node.
+    - `Output`: An output field on a node.
+    - `Internal`: A field which is treated as an input, but cannot be used in node definitions. Metadata is
+    one example. It is provided to nodes via the WithMetadata class, and we want to reserve the field name
+    "metadata" for this on all nodes. `FieldKind` is used to short-circuit the field name validation logic,
+    allowing "metadata" for that field.
+    - `NodeAttribute`: The field is a node attribute. These are fields which are not inputs or outputs,
+    but which are used to store information about the node. For example, the `id` and `type` fields are node
+    attributes.
+
+    The presence of this in `json_schema_extra["field_kind"]` is used when initializing node schemas on app
+    startup, and when generating the OpenAPI schema for the workflow editor.
+    """
+
+    Input = "input"
+    Output = "output"
+    Internal = "internal"
+    NodeAttribute = "node_attribute"
+
+
+class InputFieldJSONSchemaExtra(BaseModel):
+    """
+    Extra attributes to be added to input fields and their OpenAPI schema. Used during graph execution,
+    and by the workflow editor during schema parsing and UI rendering.
+    """
+
+    input: Input
+    orig_required: bool
+    field_kind: FieldKind
+    default: Optional[Any] = None
+    orig_default: Optional[Any] = None
+    ui_hidden: bool = False
+    ui_type: Optional[UIType] = None
+    ui_component: Optional[UIComponent] = None
+    ui_order: Optional[int] = None
+    ui_choice_labels: Optional[dict[str, str]] = None
+
+    model_config = ConfigDict(
+        validate_assignment=True,
+        json_schema_serialization_defaults_required=True,
+    )
+
+
+class WithMetadata(BaseModel):
+    """
+    Inherit from this class if your node needs a metadata input field.
+    """
+
+    metadata: Optional[MetadataField] = Field(
+        default=None,
+        description=FieldDescriptions.metadata,
+        json_schema_extra=InputFieldJSONSchemaExtra(
+            field_kind=FieldKind.Internal,
+            input=Input.Connection,
+            orig_required=False,
+        ).model_dump(exclude_none=True),
+    )
+
+
+class WithWorkflow:
+    workflow = None
+
+    def __init_subclass__(cls) -> None:
+        logger.warn(
+            f"{cls.__module__.split('.')[0]}.{cls.__name__}: WithWorkflow is deprecated. Use `context.workflow` to access the workflow."
+        )
+        super().__init_subclass__()
+
+
+class WithBoard(BaseModel):
+    """
+    Inherit from this class if your node needs a board input field.
+    """
+
+    board: Optional[BoardField] = Field(
+        default=None,
+        description=FieldDescriptions.board,
+        json_schema_extra=InputFieldJSONSchemaExtra(
+            field_kind=FieldKind.Internal,
+            input=Input.Direct,
+            orig_required=False,
+        ).model_dump(exclude_none=True),
+    )
+
+
+class OutputFieldJSONSchemaExtra(BaseModel):
+    """
+    Extra attributes to be added to input fields and their OpenAPI schema. Used by the workflow editor
+    during schema parsing and UI rendering.
+    """
+
+    field_kind: FieldKind
+    ui_hidden: bool
+    ui_type: Optional[UIType]
+    ui_order: Optional[int]
+
+    model_config = ConfigDict(
+        validate_assignment=True,
+        json_schema_serialization_defaults_required=True,
+    )
+
+
+def InputField(
+    # copied from pydantic's Field
+    # TODO: Can we support default_factory?
+    default: Any = _Unset,
+    default_factory: Callable[[], Any] | None = _Unset,
+    title: str | None = _Unset,
+    description: str | None = _Unset,
+    pattern: str | None = _Unset,
+    strict: bool | None = _Unset,
+    gt: float | None = _Unset,
+    ge: float | None = _Unset,
+    lt: float | None = _Unset,
+    le: float | None = _Unset,
+    multiple_of: float | None = _Unset,
+    allow_inf_nan: bool | None = _Unset,
+    max_digits: int | None = _Unset,
+    decimal_places: int | None = _Unset,
+    min_length: int | None = _Unset,
+    max_length: int | None = _Unset,
+    # custom
+    input: Input = Input.Any,
+    ui_type: Optional[UIType] = None,
+    ui_component: Optional[UIComponent] = None,
+    ui_hidden: bool = False,
+    ui_order: Optional[int] = None,
+    ui_choice_labels: Optional[dict[str, str]] = None,
+) -> Any:
+    """
+    Creates an input field for an invocation.
+
+    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/latest/api/fields/#pydantic.fields.Field) \
+    that adds a few extra parameters to support graph execution and the node editor UI.
+
+    :param Input input: [Input.Any] The kind of input this field requires. \
+      `Input.Direct` means a value must be provided on instantiation. \
+      `Input.Connection` means the value must be provided by a connection. \
+      `Input.Any` means either will do.
+
+    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
+      In some situations, the field's type is not enough to infer the correct UI type. \
+      For example, model selection fields should render a dropdown UI component to select a model. \
+      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
+      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
+      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
+
+    :param UIComponent ui_component: [None] Optionally specifies a specific component to use in the UI. \
+      The UI will always render a suitable component, but sometimes you want something different than the default. \
+      For example, a `string` field will default to a single-line input, but you may want a multi-line textarea instead. \
+      For this case, you could provide `UIComponent.Textarea`.
+
+    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI.
+
+    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI.
+
+    :param dict[str, str] ui_choice_labels: [None] Specifies the labels to use for the choices in an enum field.
+    """
+
+    json_schema_extra_ = InputFieldJSONSchemaExtra(
+        input=input,
+        ui_type=ui_type,
+        ui_component=ui_component,
+        ui_hidden=ui_hidden,
+        ui_order=ui_order,
+        ui_choice_labels=ui_choice_labels,
+        field_kind=FieldKind.Input,
+        orig_required=True,
+    )
+
+    """
+    There is a conflict between the typing of invocation definitions and the typing of an invocation's
+    `invoke()` function.
+
+    On instantiation of a node, the invocation definition is used to create the python class. At this time,
+    any number of fields may be optional, because they may be provided by connections.
+
+    On calling of `invoke()`, however, those fields may be required.
+
+    For example, consider an ResizeImageInvocation with an `image: ImageField` field.
+
+    `image` is required during the call to `invoke()`, but when the python class is instantiated,
+    the field may not be present. This is fine, because that image field will be provided by a
+    connection from an ancestor node, which outputs an image.
+
+    This means we want to type the `image` field as optional for the node class definition, but required
+    for the `invoke()` function.
+
+    If we use `typing.Optional` in the node class definition, the field will be typed as optional in the
+    `invoke()` method, and we'll have to do a lot of runtime checks to ensure the field is present - or
+    any static type analysis tools will complain.
+
+    To get around this, in node class definitions, we type all fields correctly for the `invoke()` function,
+    but secretly make them optional in `InputField()`. We also store the original required bool and/or default
+    value. When we call `invoke()`, we use this stored information to do an additional check on the class.
+    """
+
+    if default_factory is not _Unset and default_factory is not None:
+        default = default_factory()
+        logger.warn('"default_factory" is not supported, calling it now to set "default"')
+
+    # These are the args we may wish pass to the pydantic `Field()` function
+    field_args = {
+        "default": default,
+        "title": title,
+        "description": description,
+        "pattern": pattern,
+        "strict": strict,
+        "gt": gt,
+        "ge": ge,
+        "lt": lt,
+        "le": le,
+        "multiple_of": multiple_of,
+        "allow_inf_nan": allow_inf_nan,
+        "max_digits": max_digits,
+        "decimal_places": decimal_places,
+        "min_length": min_length,
+        "max_length": max_length,
+    }
+
+    # We only want to pass the args that were provided, otherwise the `Field()`` function won't work as expected
+    provided_args = {k: v for (k, v) in field_args.items() if v is not PydanticUndefined}
+
+    # Because we are manually making fields optional, we need to store the original required bool for reference later
+    json_schema_extra_.orig_required = default is PydanticUndefined
+
+    # Make Input.Any and Input.Connection fields optional, providing None as a default if the field doesn't already have one
+    if input is Input.Any or input is Input.Connection:
+        default_ = None if default is PydanticUndefined else default
+        provided_args.update({"default": default_})
+        if default is not PydanticUndefined:
+            # Before invoking, we'll check for the original default value and set it on the field if the field has no value
+            json_schema_extra_.default = default
+            json_schema_extra_.orig_default = default
+    elif default is not PydanticUndefined:
+        default_ = default
+        provided_args.update({"default": default_})
+        json_schema_extra_.orig_default = default_
+
+    return Field(
+        **provided_args,
+        json_schema_extra=json_schema_extra_.model_dump(exclude_none=True),
+    )
+
+
+def OutputField(
+    # copied from pydantic's Field
+    default: Any = _Unset,
+    title: str | None = _Unset,
+    description: str | None = _Unset,
+    pattern: str | None = _Unset,
+    strict: bool | None = _Unset,
+    gt: float | None = _Unset,
+    ge: float | None = _Unset,
+    lt: float | None = _Unset,
+    le: float | None = _Unset,
+    multiple_of: float | None = _Unset,
+    allow_inf_nan: bool | None = _Unset,
+    max_digits: int | None = _Unset,
+    decimal_places: int | None = _Unset,
+    min_length: int | None = _Unset,
+    max_length: int | None = _Unset,
+    # custom
+    ui_type: Optional[UIType] = None,
+    ui_hidden: bool = False,
+    ui_order: Optional[int] = None,
+) -> Any:
+    """
+    Creates an output field for an invocation output.
+
+    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/1.10/usage/schema/#field-customization) \
+    that adds a few extra parameters to support graph execution and the node editor UI.
+
+    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
+      In some situations, the field's type is not enough to infer the correct UI type. \
+      For example, model selection fields should render a dropdown UI component to select a model. \
+      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
+      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
+      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
+
+    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI. \
+
+    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
+    """
+    return Field(
+        default=default,
+        title=title,
+        description=description,
+        pattern=pattern,
+        strict=strict,
+        gt=gt,
+        ge=ge,
+        lt=lt,
+        le=le,
+        multiple_of=multiple_of,
+        allow_inf_nan=allow_inf_nan,
+        max_digits=max_digits,
+        decimal_places=decimal_places,
+        min_length=min_length,
+        max_length=max_length,
+        json_schema_extra=OutputFieldJSONSchemaExtra(
+            ui_type=ui_type,
+            ui_hidden=ui_hidden,
+            ui_order=ui_order,
+            field_kind=FieldKind.Output,
+        ).model_dump(exclude_none=True),
+    )

invokeai/app/invocations/infill.py

@@ -6,14 +6,16 @@ from typing import Literal, Optional, get_args
 import numpy as np
 from PIL import Image, ImageOps
 
-from invokeai.app.invocations.primitives import ColorField, ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ColorField, ImageField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import SEED_MAX
 from invokeai.backend.image_util.cv2_inpaint import cv2_inpaint
 from invokeai.backend.image_util.lama import LaMA
 from invokeai.backend.image_util.patchmatch import PatchMatch
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, WithBoard, WithMetadata
 from .image import PIL_RESAMPLING_MAP, PIL_RESAMPLING_MODES
 
 
@@ -118,8 +120,8 @@ def tile_fill_missing(im: Image.Image, tile_size: int = 16, seed: Optional[int]
     return si
 
 
-@invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class InfillColorInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
+class InfillColorInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image with a solid color"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -129,33 +131,20 @@ class InfillColorInvocation(BaseInvocation, WithMetadata):
     )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         solid_bg = Image.new("RGBA", image.size, self.color.tuple())
         infilled = Image.alpha_composite(solid_bg, image.convert("RGBA"))
 
         infilled.paste(image, (0, 0), image.split()[-1])
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
-@invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
-class InfillTileInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2")
+class InfillTileInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image with tiles of the image"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -168,33 +157,20 @@ class InfillTileInvocation(BaseInvocation, WithMetadata):
     )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         infilled = tile_fill_missing(image.copy(), seed=self.seed, tile_size=self.tile_size)
         infilled.paste(image, (0, 0), image.split()[-1])
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
 @invocation(
-    "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0"
+    "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1"
 )
-class InfillPatchMatchInvocation(BaseInvocation, WithMetadata):
+class InfillPatchMatchInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image using the PatchMatch algorithm"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -202,7 +178,7 @@ class InfillPatchMatchInvocation(BaseInvocation, WithMetadata):
     resample_mode: PIL_RESAMPLING_MODES = InputField(default="bicubic", description="The resampling mode")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name).convert("RGBA")
+        image = context.images.get_pil(self.image.image_name).convert("RGBA")
 
         resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
 
@@ -227,77 +203,38 @@ class InfillPatchMatchInvocation(BaseInvocation, WithMetadata):
         infilled.paste(image, (0, 0), mask=image.split()[-1])
         # image.paste(infilled, (0, 0), mask=image.split()[-1])
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
-@invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class LaMaInfillInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
+class LaMaInfillInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image using the LaMa model"""
 
     image: ImageField = InputField(description="The image to infill")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         infilled = infill_lama(image.copy())
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
-@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class CV2InfillInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
+class CV2InfillInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image using OpenCV Inpainting"""
 
     image: ImageField = InputField(description="The image to infill")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         infilled = infill_cv2(image.copy())
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/ip_adapter.py

@@ -7,16 +7,13 @@ from pydantic import BaseModel, ConfigDict, Field, field_validator, model_valida
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField
 from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.model_management.models.base import BaseModelType, ModelType
 from invokeai.backend.model_management.models.ip_adapter import get_ip_adapter_image_encoder_model_id
 
@@ -65,7 +62,7 @@ class IPAdapterOutput(BaseInvocationOutput):
     ip_adapter: IPAdapterField = OutputField(description=FieldDescriptions.ip_adapter, title="IP-Adapter")
 
 
-@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.1.1")
+@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.1.2")
 class IPAdapterInvocation(BaseInvocation):
     """Collects IP-Adapter info to pass to other nodes."""
 
@@ -98,7 +95,7 @@ class IPAdapterInvocation(BaseInvocation):
 
     def invoke(self, context: InvocationContext) -> IPAdapterOutput:
         # Lookup the CLIP Vision encoder that is intended to be used with the IP-Adapter model.
-        ip_adapter_info = context.services.model_manager.model_info(
+        ip_adapter_info = context.models.get_info(
             self.ip_adapter_model.model_name, self.ip_adapter_model.base_model, ModelType.IPAdapter
         )
         # HACK(ryand): This is bad for a couple of reasons: 1) we are bypassing the model manager to read the model
@@ -107,7 +104,7 @@ class IPAdapterInvocation(BaseInvocation):
         # is currently messy due to differences between how the model info is generated when installing a model from
         # disk vs. downloading the model.
         image_encoder_model_id = get_ip_adapter_image_encoder_model_id(
-            os.path.join(context.services.configuration.get_config().models_path, ip_adapter_info["path"])
+            os.path.join(context.config.get().models_path, ip_adapter_info["path"])
         )
         image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
         image_encoder_model = CLIPVisionModelField(

invokeai/app/invocations/latent.py

@@ -23,21 +23,29 @@ from diffusers.schedulers import SchedulerMixin as Scheduler
 from pydantic import field_validator
 from torchvision.transforms.functional import resize as tv_resize
 
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR, SCHEDULER_NAME_VALUES
+from invokeai.app.invocations.fields import (
+    ConditioningField,
+    DenoiseMaskField,
+    FieldDescriptions,
+    ImageField,
+    Input,
+    InputField,
+    LatentsField,
+    OutputField,
+    UIType,
+    WithBoard,
+    WithMetadata,
+)
 from invokeai.app.invocations.ip_adapter import IPAdapterField
 from invokeai.app.invocations.primitives import (
-    DenoiseMaskField,
     DenoiseMaskOutput,
-    ImageField,
     ImageOutput,
-    LatentsField,
     LatentsOutput,
-    build_latents_output,
 )
 from invokeai.app.invocations.t2i_adapter import T2IAdapterField
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.controlnet_utils import prepare_control_image
-from invokeai.app.util.step_callback import stable_diffusion_step_callback
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter, IPAdapterPlus
 from invokeai.backend.model_management.models import ModelType, SilenceWarnings
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningData, IPAdapterConditioningInfo
@@ -59,16 +67,9 @@ from ...backend.util.devices import choose_precision, choose_torch_device
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIType,
-    WithMetadata,
     invocation,
     invocation_output,
 )
-from .compel import ConditioningField
 from .controlnet_image_processors import ControlField
 from .model import ModelInfo, UNetField, VaeField
 
@@ -77,18 +78,10 @@ if choose_torch_device() == torch.device("mps"):
 
 DEFAULT_PRECISION = choose_precision(choose_torch_device())
 
-SAMPLER_NAME_VALUES = Literal[tuple(SCHEDULER_MAP.keys())]
-
-# HACK: Many nodes are currently hard-coded to use a fixed latent scale factor of 8. This is fragile, and will need to
-# be addressed if future models use a different latent scale factor. Also, note that there may be places where the scale
-# factor is hard-coded to a literal '8' rather than using this constant.
-# The ratio of image:latent dimensions is LATENT_SCALE_FACTOR:1, or 8:1.
-LATENT_SCALE_FACTOR = 8
-
 
 @invocation_output("scheduler_output")
 class SchedulerOutput(BaseInvocationOutput):
-    scheduler: SAMPLER_NAME_VALUES = OutputField(description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler)
+    scheduler: SCHEDULER_NAME_VALUES = OutputField(description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler)
 
 
 @invocation(
@@ -101,7 +94,7 @@ class SchedulerOutput(BaseInvocationOutput):
 class SchedulerInvocation(BaseInvocation):
     """Selects a scheduler."""
 
-    scheduler: SAMPLER_NAME_VALUES = InputField(
+    scheduler: SCHEDULER_NAME_VALUES = InputField(
         default="euler",
         description=FieldDescriptions.scheduler,
         ui_type=UIType.Scheduler,
@@ -116,7 +109,7 @@ class SchedulerInvocation(BaseInvocation):
     title="Create Denoise Mask",
     tags=["mask", "denoise"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class CreateDenoiseMaskInvocation(BaseInvocation):
     """Creates mask for denoising model run."""
@@ -144,7 +137,7 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> DenoiseMaskOutput:
         if self.image is not None:
-            image = context.services.images.get_pil_image(self.image.image_name)
+            image = context.images.get_pil(self.image.image_name)
             image = image_resized_to_grid_as_tensor(image.convert("RGB"))
             if image.dim() == 3:
                 image = image.unsqueeze(0)
@@ -152,33 +145,26 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
             image = None
 
         mask = self.prep_mask_tensor(
-            context.services.images.get_pil_image(self.mask.image_name),
+            context.images.get_pil(self.mask.image_name),
         )
 
         if image is not None:
-            vae_info = context.services.model_manager.get_model(
-                **self.vae.vae.model_dump(),
-                context=context,
-            )
+            vae_info = context.models.load(**self.vae.vae.model_dump())
 
             img_mask = tv_resize(mask, image.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
             masked_image = image * torch.where(img_mask < 0.5, 0.0, 1.0)
             # TODO:
             masked_latents = ImageToLatentsInvocation.vae_encode(vae_info, self.fp32, self.tiled, masked_image.clone())
 
-            masked_latents_name = f"{context.graph_execution_state_id}__{self.id}_masked_latents"
-            context.services.latents.save(masked_latents_name, masked_latents)
+            masked_latents_name = context.tensors.save(tensor=masked_latents)
         else:
             masked_latents_name = None
 
-        mask_name = f"{context.graph_execution_state_id}__{self.id}_mask"
-        context.services.latents.save(mask_name, mask)
+        mask_name = context.tensors.save(tensor=mask)
 
-        return DenoiseMaskOutput(
-            denoise_mask=DenoiseMaskField(
-                mask_name=mask_name,
-                masked_latents_name=masked_latents_name,
-            ),
+        return DenoiseMaskOutput.build(
+            mask_name=mask_name,
+            masked_latents_name=masked_latents_name,
         )
 
 
@@ -189,10 +175,7 @@ def get_scheduler(
     seed: int,
 ) -> Scheduler:
     scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP["ddim"])
-    orig_scheduler_info = context.services.model_manager.get_model(
-        **scheduler_info.model_dump(),
-        context=context,
-    )
+    orig_scheduler_info = context.models.load(**scheduler_info.model_dump())
     with orig_scheduler_info as orig_scheduler:
         scheduler_config = orig_scheduler.config
 
@@ -221,7 +204,7 @@ def get_scheduler(
     title="Denoise Latents",
     tags=["latents", "denoise", "txt2img", "t2i", "t2l", "img2img", "i2i", "l2l"],
     category="latents",
-    version="1.5.1",
+    version="1.5.2",
 )
 class DenoiseLatentsInvocation(BaseInvocation):
     """Denoises noisy latents to decodable images"""
@@ -249,7 +232,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         description=FieldDescriptions.denoising_start,
     )
     denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
-    scheduler: SAMPLER_NAME_VALUES = InputField(
+    scheduler: SCHEDULER_NAME_VALUES = InputField(
         default="euler",
         description=FieldDescriptions.scheduler,
         ui_type=UIType.Scheduler,
@@ -307,22 +290,6 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 raise ValueError("cfg_scale must be greater than 1")
         return v
 
-    # TODO: pass this an emitter method or something? or a session for dispatching?
-    def dispatch_progress(
-        self,
-        context: InvocationContext,
-        source_node_id: str,
-        intermediate_state: PipelineIntermediateState,
-        base_model: BaseModelType,
-    ) -> None:
-        stable_diffusion_step_callback(
-            context=context,
-            intermediate_state=intermediate_state,
-            node=self.model_dump(),
-            source_node_id=source_node_id,
-            base_model=base_model,
-        )
-
     def get_conditioning_data(
         self,
         context: InvocationContext,
@@ -330,11 +297,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
         unet,
         seed,
     ) -> ConditioningData:
-        positive_cond_data = context.services.latents.get(self.positive_conditioning.conditioning_name)
+        positive_cond_data = context.conditioning.load(self.positive_conditioning.conditioning_name)
         c = positive_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
         extra_conditioning_info = c.extra_conditioning
 
-        negative_cond_data = context.services.latents.get(self.negative_conditioning.conditioning_name)
+        negative_cond_data = context.conditioning.load(self.negative_conditioning.conditioning_name)
         uc = negative_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
 
         conditioning_data = ConditioningData(
@@ -422,17 +389,16 @@ class DenoiseLatentsInvocation(BaseInvocation):
         controlnet_data = []
         for control_info in control_list:
             control_model = exit_stack.enter_context(
-                context.services.model_manager.get_model(
+                context.models.load(
                     model_name=control_info.control_model.model_name,
                     model_type=ModelType.ControlNet,
                     base_model=control_info.control_model.base_model,
-                    context=context,
                 )
             )
 
             # control_models.append(control_model)
             control_image_field = control_info.image
-            input_image = context.services.images.get_pil_image(control_image_field.image_name)
+            input_image = context.images.get_pil(control_image_field.image_name)
             # self.image.image_type, self.image.image_name
             # FIXME: still need to test with different widths, heights, devices, dtypes
             #        and add in batch_size, num_images_per_prompt?
@@ -490,19 +456,17 @@ class DenoiseLatentsInvocation(BaseInvocation):
         conditioning_data.ip_adapter_conditioning = []
         for single_ip_adapter in ip_adapter:
             ip_adapter_model: Union[IPAdapter, IPAdapterPlus] = exit_stack.enter_context(
-                context.services.model_manager.get_model(
+                context.models.load(
                     model_name=single_ip_adapter.ip_adapter_model.model_name,
                     model_type=ModelType.IPAdapter,
                     base_model=single_ip_adapter.ip_adapter_model.base_model,
-                    context=context,
                 )
             )
 
-            image_encoder_model_info = context.services.model_manager.get_model(
+            image_encoder_model_info = context.models.load(
                 model_name=single_ip_adapter.image_encoder_model.model_name,
                 model_type=ModelType.CLIPVision,
                 base_model=single_ip_adapter.image_encoder_model.base_model,
-                context=context,
             )
 
             # `single_ip_adapter.image` could be a list or a single ImageField. Normalize to a list here.
@@ -510,7 +474,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
             if not isinstance(single_ipa_images, list):
                 single_ipa_images = [single_ipa_images]
 
-            single_ipa_images = [context.services.images.get_pil_image(image.image_name) for image in single_ipa_images]
+            single_ipa_images = [context.images.get_pil(image.image_name) for image in single_ipa_images]
 
             # TODO(ryand): With some effort, the step of running the CLIP Vision encoder could be done before any other
             # models are needed in memory. This would help to reduce peak memory utilization in low-memory environments.
@@ -554,13 +518,12 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         t2i_adapter_data = []
         for t2i_adapter_field in t2i_adapter:
-            t2i_adapter_model_info = context.services.model_manager.get_model(
+            t2i_adapter_model_info = context.models.load(
                 model_name=t2i_adapter_field.t2i_adapter_model.model_name,
                 model_type=ModelType.T2IAdapter,
                 base_model=t2i_adapter_field.t2i_adapter_model.base_model,
-                context=context,
             )
-            image = context.services.images.get_pil_image(t2i_adapter_field.image.image_name)
+            image = context.images.get_pil(t2i_adapter_field.image.image_name)
 
             # The max_unet_downscale is the maximum amount that the UNet model downscales the latent image internally.
             if t2i_adapter_field.t2i_adapter_model.base_model == BaseModelType.StableDiffusion1:
@@ -647,14 +610,14 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         return num_inference_steps, timesteps, init_timestep
 
-    def prep_inpaint_mask(self, context, latents):
+    def prep_inpaint_mask(self, context: InvocationContext, latents):
         if self.denoise_mask is None:
             return None, None
 
-        mask = context.services.latents.get(self.denoise_mask.mask_name)
+        mask = context.tensors.load(self.denoise_mask.mask_name)
         mask = tv_resize(mask, latents.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
         if self.denoise_mask.masked_latents_name is not None:
-            masked_latents = context.services.latents.get(self.denoise_mask.masked_latents_name)
+            masked_latents = context.tensors.load(self.denoise_mask.masked_latents_name)
         else:
             masked_latents = None
 
@@ -666,11 +629,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
             seed = None
             noise = None
             if self.noise is not None:
-                noise = context.services.latents.get(self.noise.latents_name)
+                noise = context.tensors.load(self.noise.latents_name)
                 seed = self.noise.seed
 
             if self.latents is not None:
-                latents = context.services.latents.get(self.latents.latents_name)
+                latents = context.tensors.load(self.latents.latents_name)
                 if seed is None:
                     seed = self.latents.seed
 
@@ -696,27 +659,17 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 do_classifier_free_guidance=True,
             )
 
-            # Get the source node id (we are invoking the prepared node)
-            graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
-            source_node_id = graph_execution_state.prepared_source_mapping[self.id]
-
             def step_callback(state: PipelineIntermediateState):
-                self.dispatch_progress(context, source_node_id, state, self.unet.unet.base_model)
+                context.util.sd_step_callback(state, self.unet.unet.base_model)
 
             def _lora_loader():
                 for lora in self.unet.loras:
-                    lora_info = context.services.model_manager.get_model(
-                        **lora.model_dump(exclude={"weight"}),
-                        context=context,
-                    )
+                    lora_info = context.models.load(**lora.model_dump(exclude={"weight"}))
                     yield (lora_info.context.model, lora.weight)
                     del lora_info
                 return
 
-            unet_info = context.services.model_manager.get_model(
-                **self.unet.unet.model_dump(),
-                context=context,
-            )
+            unet_info = context.models.load(**self.unet.unet.model_dump())
             with (
                 ExitStack() as exit_stack,
                 ModelPatcher.apply_freeu(unet_info.context.model, self.unet.freeu_config),
@@ -792,9 +745,8 @@ class DenoiseLatentsInvocation(BaseInvocation):
             if choose_torch_device() == torch.device("mps"):
                 mps.empty_cache()
 
-            name = f"{context.graph_execution_state_id}__{self.id}"
-            context.services.latents.save(name, result_latents)
-        return build_latents_output(latents_name=name, latents=result_latents, seed=seed)
+            name = context.tensors.save(tensor=result_latents)
+        return LatentsOutput.build(latents_name=name, latents=result_latents, seed=seed)
 
 
 @invocation(
@@ -802,9 +754,9 @@ class DenoiseLatentsInvocation(BaseInvocation):
     title="Latents to Image",
     tags=["latents", "image", "vae", "l2i"],
     category="latents",
-    version="1.2.0",
+    version="1.2.1",
 )
-class LatentsToImageInvocation(BaseInvocation, WithMetadata):
+class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Generates an image from latents."""
 
     latents: LatentsField = InputField(
@@ -820,12 +772,9 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.model_dump(),
-            context=context,
-        )
+        vae_info = context.models.load(**self.vae.vae.model_dump())
 
         with set_seamless(vae_info.context.model, self.vae.seamless_axes), vae_info as vae:
             latents = latents.to(vae.device)
@@ -854,15 +803,15 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
                 vae.to(dtype=torch.float16)
                 latents = latents.half()
 
-            if self.tiled or context.services.configuration.tiled_decode:
+            if self.tiled or context.config.get().tiled_decode:
                 vae.enable_tiling()
             else:
                 vae.disable_tiling()
 
             # clear memory as vae decode can request a lot
-            # torch.cuda.empty_cache()
-            # if choose_torch_device() == torch.device("mps"):
-            #     mps.empty_cache()
+            torch.cuda.empty_cache()
+            if choose_torch_device() == torch.device("mps"):
+                mps.empty_cache()
 
             with torch.inference_mode():
                 # copied from diffusers pipeline
@@ -874,26 +823,13 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
 
                 image = VaeImageProcessor.numpy_to_pil(np_image)[0]
 
-        # torch.cuda.empty_cache()
-        # if choose_torch_device() == torch.device("mps"):
-        #     mps.empty_cache()
+        torch.cuda.empty_cache()
+        if choose_torch_device() == torch.device("mps"):
+            mps.empty_cache()
 
-        image_dto = context.services.images.create(
-            image=image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=image)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
 LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear", "bilinear", "bicubic", "trilinear", "area", "nearest-exact"]
@@ -904,7 +840,7 @@ LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear", "bilinear", "bicubic",
     title="Resize Latents",
     tags=["latents", "resize"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class ResizeLatentsInvocation(BaseInvocation):
     """Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8."""
@@ -927,7 +863,7 @@ class ResizeLatentsInvocation(BaseInvocation):
     antialias: bool = InputField(default=False, description=FieldDescriptions.torch_antialias)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
         # TODO:
         device = choose_torch_device()
@@ -945,10 +881,8 @@ class ResizeLatentsInvocation(BaseInvocation):
         if device == torch.device("mps"):
             mps.empty_cache()
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        # context.services.latents.set(name, resized_latents)
-        context.services.latents.save(name, resized_latents)
-        return build_latents_output(latents_name=name, latents=resized_latents, seed=self.latents.seed)
+        name = context.tensors.save(tensor=resized_latents)
+        return LatentsOutput.build(latents_name=name, latents=resized_latents, seed=self.latents.seed)
 
 
 @invocation(
@@ -956,7 +890,7 @@ class ResizeLatentsInvocation(BaseInvocation):
     title="Scale Latents",
     tags=["latents", "resize"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class ScaleLatentsInvocation(BaseInvocation):
     """Scales latents by a given factor."""
@@ -970,7 +904,7 @@ class ScaleLatentsInvocation(BaseInvocation):
     antialias: bool = InputField(default=False, description=FieldDescriptions.torch_antialias)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
         # TODO:
         device = choose_torch_device()
@@ -989,10 +923,8 @@ class ScaleLatentsInvocation(BaseInvocation):
         if device == torch.device("mps"):
             mps.empty_cache()
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        # context.services.latents.set(name, resized_latents)
-        context.services.latents.save(name, resized_latents)
-        return build_latents_output(latents_name=name, latents=resized_latents, seed=self.latents.seed)
+        name = context.tensors.save(tensor=resized_latents)
+        return LatentsOutput.build(latents_name=name, latents=resized_latents, seed=self.latents.seed)
 
 
 @invocation(
@@ -1000,7 +932,7 @@ class ScaleLatentsInvocation(BaseInvocation):
     title="Image to Latents",
     tags=["latents", "image", "vae", "i2l"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class ImageToLatentsInvocation(BaseInvocation):
     """Encodes an image into latents."""
@@ -1061,12 +993,9 @@ class ImageToLatentsInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.model_dump(),
-            context=context,
-        )
+        vae_info = context.models.load(**self.vae.vae.model_dump())
 
         image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
         if image_tensor.dim() == 3:
@@ -1074,10 +1003,9 @@ class ImageToLatentsInvocation(BaseInvocation):
 
         latents = self.vae_encode(vae_info, self.fp32, self.tiled, image_tensor)
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
         latents = latents.to("cpu")
-        context.services.latents.save(name, latents)
-        return build_latents_output(latents_name=name, latents=latents, seed=None)
+        name = context.tensors.save(tensor=latents)
+        return LatentsOutput.build(latents_name=name, latents=latents, seed=None)
 
     @singledispatchmethod
     @staticmethod
@@ -1097,7 +1025,7 @@ class ImageToLatentsInvocation(BaseInvocation):
     title="Blend Latents",
     tags=["latents", "blend"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class BlendLatentsInvocation(BaseInvocation):
     """Blend two latents using a given alpha. Latents must have same size."""
@@ -1113,8 +1041,8 @@ class BlendLatentsInvocation(BaseInvocation):
     alpha: float = InputField(default=0.5, description=FieldDescriptions.blend_alpha)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents_a = context.services.latents.get(self.latents_a.latents_name)
-        latents_b = context.services.latents.get(self.latents_b.latents_name)
+        latents_a = context.tensors.load(self.latents_a.latents_name)
+        latents_b = context.tensors.load(self.latents_b.latents_name)
 
         if latents_a.shape != latents_b.shape:
             raise Exception("Latents to blend must be the same size.")
@@ -1168,10 +1096,8 @@ class BlendLatentsInvocation(BaseInvocation):
         if device == torch.device("mps"):
             mps.empty_cache()
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        # context.services.latents.set(name, resized_latents)
-        context.services.latents.save(name, blended_latents)
-        return build_latents_output(latents_name=name, latents=blended_latents)
+        name = context.tensors.save(tensor=blended_latents)
+        return LatentsOutput.build(latents_name=name, latents=blended_latents)
 
 
 # The Crop Latents node was copied from @skunkworxdark's implementation here:
@@ -1181,7 +1107,7 @@ class BlendLatentsInvocation(BaseInvocation):
     title="Crop Latents",
     tags=["latents", "crop"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 # TODO(ryand): Named `CropLatentsCoreInvocation` to prevent a conflict with custom node `CropLatentsInvocation`.
 # Currently, if the class names conflict then 'GET /openapi.json' fails.
@@ -1216,7 +1142,7 @@ class CropLatentsCoreInvocation(BaseInvocation):
     )
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
         x1 = self.x // LATENT_SCALE_FACTOR
         y1 = self.y // LATENT_SCALE_FACTOR
@@ -1225,10 +1151,9 @@ class CropLatentsCoreInvocation(BaseInvocation):
 
         cropped_latents = latents[..., y1:y2, x1:x2]
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        context.services.latents.save(name, cropped_latents)
+        name = context.tensors.save(tensor=cropped_latents)
 
-        return build_latents_output(latents_name=name, latents=cropped_latents)
+        return LatentsOutput.build(latents_name=name, latents=cropped_latents)
 
 
 @invocation_output("ideal_size_output")

invokeai/app/invocations/math.py

@@ -5,10 +5,11 @@ from typing import Literal
 import numpy as np
 from pydantic import ValidationInfo, field_validator
 
+from invokeai.app.invocations.fields import FieldDescriptions, InputField
 from invokeai.app.invocations.primitives import FloatOutput, IntegerOutput
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, invocation
 
 
 @invocation("add", title="Add Integers", tags=["math", "add"], category="math", version="1.0.0")

invokeai/app/invocations/metadata.py

@@ -5,20 +5,22 @@ from pydantic import BaseModel, ConfigDict, Field
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    InputField,
-    InvocationContext,
-    MetadataField,
-    OutputField,
-    UIType,
     invocation,
     invocation_output,
 )
 from invokeai.app.invocations.controlnet_image_processors import ControlField
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    ImageField,
+    InputField,
+    MetadataField,
+    OutputField,
+    UIType,
+)
 from invokeai.app.invocations.ip_adapter import IPAdapterModelField
 from invokeai.app.invocations.model import LoRAModelField, MainModelField, VAEModelField
-from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.t2i_adapter import T2IAdapterField
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 from ...version import __version__
 

invokeai/app/invocations/model.py

@@ -3,17 +3,14 @@ from typing import List, Optional
 
 from pydantic import BaseModel, ConfigDict, Field
 
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.shared.models import FreeUConfig
 
 from ...backend.model_management import BaseModelType, ModelType, SubModelType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
@@ -105,7 +102,7 @@ class LoRAModelField(BaseModel):
     title="Main Model",
     tags=["model"],
     category="model",
-    version="1.0.0",
+    version="1.0.1",
 )
 class MainModelLoaderInvocation(BaseInvocation):
     """Loads a main model, outputting its submodels."""
@@ -119,7 +116,7 @@ class MainModelLoaderInvocation(BaseInvocation):
         model_type = ModelType.Main
 
         # TODO: not found exceptions
-        if not context.services.model_manager.model_exists(
+        if not context.models.exists(
             model_name=model_name,
             base_model=base_model,
             model_type=model_type,
@@ -206,7 +203,7 @@ class LoraLoaderOutput(BaseInvocationOutput):
     clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
 
 
-@invocation("lora_loader", title="LoRA", tags=["model"], category="model", version="1.0.0")
+@invocation("lora_loader", title="LoRA", tags=["model"], category="model", version="1.0.1")
 class LoraLoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
 
@@ -232,7 +229,7 @@ class LoraLoaderInvocation(BaseInvocation):
         base_model = self.lora.base_model
         lora_name = self.lora.model_name
 
-        if not context.services.model_manager.model_exists(
+        if not context.models.exists(
             base_model=base_model,
             model_name=lora_name,
             model_type=ModelType.Lora,
@@ -288,7 +285,7 @@ class SDXLLoraLoaderOutput(BaseInvocationOutput):
     title="SDXL LoRA",
     tags=["lora", "model"],
     category="model",
-    version="1.0.0",
+    version="1.0.1",
 )
 class SDXLLoraLoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
@@ -321,7 +318,7 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
         base_model = self.lora.base_model
         lora_name = self.lora.model_name
 
-        if not context.services.model_manager.model_exists(
+        if not context.models.exists(
             base_model=base_model,
             model_name=lora_name,
             model_type=ModelType.Lora,
@@ -387,7 +384,7 @@ class VAEModelField(BaseModel):
     model_config = ConfigDict(protected_namespaces=())
 
 
-@invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.0")
+@invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.1")
 class VaeLoaderInvocation(BaseInvocation):
     """Loads a VAE model, outputting a VaeLoaderOutput"""
 
@@ -402,7 +399,7 @@ class VaeLoaderInvocation(BaseInvocation):
         model_name = self.vae_model.model_name
         model_type = ModelType.Vae
 
-        if not context.services.model_manager.model_exists(
+        if not context.models.exists(
             base_model=base_model,
             model_name=model_name,
             model_type=model_type,

invokeai/app/invocations/noise.py

@@ -4,17 +4,15 @@
 import torch
 from pydantic import field_validator
 
-from invokeai.app.invocations.latent import LatentsField
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
+from invokeai.app.invocations.fields import FieldDescriptions, InputField, LatentsField, OutputField
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import SEED_MAX
 
 from ...backend.util.devices import choose_torch_device, torch_dtype
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
@@ -69,13 +67,13 @@ class NoiseOutput(BaseInvocationOutput):
     width: int = OutputField(description=FieldDescriptions.width)
     height: int = OutputField(description=FieldDescriptions.height)
 
-
-def build_noise_output(latents_name: str, latents: torch.Tensor, seed: int):
-    return NoiseOutput(
-        noise=LatentsField(latents_name=latents_name, seed=seed),
-        width=latents.size()[3] * 8,
-        height=latents.size()[2] * 8,
-    )
+    @classmethod
+    def build(cls, latents_name: str, latents: torch.Tensor, seed: int) -> "NoiseOutput":
+        return cls(
+            noise=LatentsField(latents_name=latents_name, seed=seed),
+            width=latents.size()[3] * LATENT_SCALE_FACTOR,
+            height=latents.size()[2] * LATENT_SCALE_FACTOR,
+        )
 
 
 @invocation(
@@ -96,13 +94,13 @@ class NoiseInvocation(BaseInvocation):
     )
     width: int = InputField(
         default=512,
-        multiple_of=8,
+        multiple_of=LATENT_SCALE_FACTOR,
         gt=0,
         description=FieldDescriptions.width,
     )
     height: int = InputField(
         default=512,
-        multiple_of=8,
+        multiple_of=LATENT_SCALE_FACTOR,
         gt=0,
         description=FieldDescriptions.height,
     )
@@ -124,6 +122,5 @@ class NoiseInvocation(BaseInvocation):
             seed=self.seed,
             use_cpu=self.use_cpu,
         )
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        context.services.latents.save(name, noise)
-        return build_noise_output(latents_name=name, latents=noise, seed=self.seed)
+        name = context.tensors.save(tensor=noise)
+        return NoiseOutput.build(latents_name=name, latents=noise, seed=self.seed)

invokeai/app/invocations/onnx.py

@@ -1,508 +0,0 @@
-# Copyright (c) 2023 Borisov Sergey (https://github.com/StAlKeR7779)
-
-import inspect
-
-# from contextlib import ExitStack
-from typing import List, Literal, Union
-
-import numpy as np
-import torch
-from diffusers.image_processor import VaeImageProcessor
-from pydantic import BaseModel, ConfigDict, Field, field_validator
-from tqdm import tqdm
-
-from invokeai.app.invocations.primitives import ConditioningField, ConditioningOutput, ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
-from invokeai.app.shared.fields import FieldDescriptions
-from invokeai.app.util.step_callback import stable_diffusion_step_callback
-from invokeai.backend import BaseModelType, ModelType, SubModelType
-
-from ...backend.model_management import ONNXModelPatcher
-from ...backend.stable_diffusion import PipelineIntermediateState
-from ...backend.util import choose_torch_device
-from ..util.ti_utils import extract_ti_triggers_from_prompt
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
-    UIType,
-    WithMetadata,
-    invocation,
-    invocation_output,
-)
-from .controlnet_image_processors import ControlField
-from .latent import SAMPLER_NAME_VALUES, LatentsField, LatentsOutput, build_latents_output, get_scheduler
-from .model import ClipField, ModelInfo, UNetField, VaeField
-
-ORT_TO_NP_TYPE = {
-    "tensor(bool)": np.bool_,
-    "tensor(int8)": np.int8,
-    "tensor(uint8)": np.uint8,
-    "tensor(int16)": np.int16,
-    "tensor(uint16)": np.uint16,
-    "tensor(int32)": np.int32,
-    "tensor(uint32)": np.uint32,
-    "tensor(int64)": np.int64,
-    "tensor(uint64)": np.uint64,
-    "tensor(float16)": np.float16,
-    "tensor(float)": np.float32,
-    "tensor(double)": np.float64,
-}
-
-PRECISION_VALUES = Literal[tuple(ORT_TO_NP_TYPE.keys())]
-
-
-@invocation("prompt_onnx", title="ONNX Prompt (Raw)", tags=["prompt", "onnx"], category="conditioning", version="1.0.0")
-class ONNXPromptInvocation(BaseInvocation):
-    prompt: str = InputField(default="", description=FieldDescriptions.raw_prompt, ui_component=UIComponent.Textarea)
-    clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
-
-    def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        tokenizer_info = context.services.model_manager.get_model(
-            **self.clip.tokenizer.model_dump(),
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **self.clip.text_encoder.model_dump(),
-        )
-        with tokenizer_info as orig_tokenizer, text_encoder_info as text_encoder:  # , ExitStack() as stack:
-            loras = [
-                (
-                    context.services.model_manager.get_model(**lora.model_dump(exclude={"weight"})).context.model,
-                    lora.weight,
-                )
-                for lora in self.clip.loras
-            ]
-
-            ti_list = []
-            for trigger in extract_ti_triggers_from_prompt(self.prompt):
-                name = trigger[1:-1]
-                try:
-                    ti_list.append(
-                        (
-                            name,
-                            context.services.model_manager.get_model(
-                                model_name=name,
-                                base_model=self.clip.text_encoder.base_model,
-                                model_type=ModelType.TextualInversion,
-                            ).context.model,
-                        )
-                    )
-                except Exception:
-                    # print(e)
-                    # import traceback
-                    # print(traceback.format_exc())
-                    print(f'Warn: trigger: "{trigger}" not found')
-            if loras or ti_list:
-                text_encoder.release_session()
-            with (
-                ONNXModelPatcher.apply_lora_text_encoder(text_encoder, loras),
-                ONNXModelPatcher.apply_ti(orig_tokenizer, text_encoder, ti_list) as (tokenizer, ti_manager),
-            ):
-                text_encoder.create_session()
-
-                # copy from
-                # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L153
-                text_inputs = tokenizer(
-                    self.prompt,
-                    padding="max_length",
-                    max_length=tokenizer.model_max_length,
-                    truncation=True,
-                    return_tensors="np",
-                )
-                text_input_ids = text_inputs.input_ids
-                """
-                untruncated_ids = tokenizer(prompt, padding="max_length", return_tensors="np").input_ids
-
-                if not np.array_equal(text_input_ids, untruncated_ids):
-                    removed_text = self.tokenizer.batch_decode(
-                        untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1]
-                    )
-                    logger.warning(
-                        "The following part of your input was truncated because CLIP can only handle sequences up to"
-                        f" {self.tokenizer.model_max_length} tokens: {removed_text}"
-                    )
-                """
-
-                prompt_embeds = text_encoder(input_ids=text_input_ids.astype(np.int32))[0]
-
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-
-        # TODO: hacky but works ;D maybe rename latents somehow?
-        context.services.latents.save(conditioning_name, (prompt_embeds, None))
-
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
-
-
-# Text to image
-@invocation(
-    "t2l_onnx",
-    title="ONNX Text to Latents",
-    tags=["latents", "inference", "txt2img", "onnx"],
-    category="latents",
-    version="1.0.0",
-)
-class ONNXTextToLatentsInvocation(BaseInvocation):
-    """Generates latents from conditionings."""
-
-    positive_conditioning: ConditioningField = InputField(
-        description=FieldDescriptions.positive_cond,
-        input=Input.Connection,
-    )
-    negative_conditioning: ConditioningField = InputField(
-        description=FieldDescriptions.negative_cond,
-        input=Input.Connection,
-    )
-    noise: LatentsField = InputField(
-        description=FieldDescriptions.noise,
-        input=Input.Connection,
-    )
-    steps: int = InputField(default=10, gt=0, description=FieldDescriptions.steps)
-    cfg_scale: Union[float, List[float]] = InputField(
-        default=7.5,
-        ge=1,
-        description=FieldDescriptions.cfg_scale,
-    )
-    scheduler: SAMPLER_NAME_VALUES = InputField(
-        default="euler", description=FieldDescriptions.scheduler, input=Input.Direct, ui_type=UIType.Scheduler
-    )
-    precision: PRECISION_VALUES = InputField(default="tensor(float16)", description=FieldDescriptions.precision)
-    unet: UNetField = InputField(
-        description=FieldDescriptions.unet,
-        input=Input.Connection,
-    )
-    control: Union[ControlField, list[ControlField]] = InputField(
-        default=None,
-        description=FieldDescriptions.control,
-    )
-    # seamless:   bool = InputField(default=False, description="Whether or not to generate an image that can tile without seams", )
-    # seamless_axes: str = InputField(default="", description="The axes to tile the image on, 'x' and/or 'y'")
-
-    @field_validator("cfg_scale")
-    def ge_one(cls, v):
-        """validate that all cfg_scale values are >= 1"""
-        if isinstance(v, list):
-            for i in v:
-                if i < 1:
-                    raise ValueError("cfg_scale must be greater than 1")
-        else:
-            if v < 1:
-                raise ValueError("cfg_scale must be greater than 1")
-        return v
-
-    # based on
-    # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L375
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
-        c, _ = context.services.latents.get(self.positive_conditioning.conditioning_name)
-        uc, _ = context.services.latents.get(self.negative_conditioning.conditioning_name)
-        graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
-        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
-        if isinstance(c, torch.Tensor):
-            c = c.cpu().numpy()
-        if isinstance(uc, torch.Tensor):
-            uc = uc.cpu().numpy()
-        device = torch.device(choose_torch_device())
-        prompt_embeds = np.concatenate([uc, c])
-
-        latents = context.services.latents.get(self.noise.latents_name)
-        if isinstance(latents, torch.Tensor):
-            latents = latents.cpu().numpy()
-
-        # TODO: better execution device handling
-        latents = latents.astype(ORT_TO_NP_TYPE[self.precision])
-
-        # get the initial random noise unless the user supplied it
-        do_classifier_free_guidance = True
-        # latents_dtype = prompt_embeds.dtype
-        # latents_shape = (batch_size * num_images_per_prompt, 4, height // 8, width // 8)
-        # if latents.shape != latents_shape:
-        #    raise ValueError(f"Unexpected latents shape, got {latents.shape}, expected {latents_shape}")
-
-        scheduler = get_scheduler(
-            context=context,
-            scheduler_info=self.unet.scheduler,
-            scheduler_name=self.scheduler,
-            seed=0,  # TODO: refactor this node
-        )
-
-        def torch2numpy(latent: torch.Tensor):
-            return latent.cpu().numpy()
-
-        def numpy2torch(latent, device):
-            return torch.from_numpy(latent).to(device)
-
-        def dispatch_progress(
-            self, context: InvocationContext, source_node_id: str, intermediate_state: PipelineIntermediateState
-        ) -> None:
-            stable_diffusion_step_callback(
-                context=context,
-                intermediate_state=intermediate_state,
-                node=self.model_dump(),
-                source_node_id=source_node_id,
-            )
-
-        scheduler.set_timesteps(self.steps)
-        latents = latents * np.float64(scheduler.init_noise_sigma)
-
-        extra_step_kwargs = {}
-        if "eta" in set(inspect.signature(scheduler.step).parameters.keys()):
-            extra_step_kwargs.update(
-                eta=0.0,
-            )
-
-        unet_info = context.services.model_manager.get_model(**self.unet.unet.model_dump())
-
-        with unet_info as unet:  # , ExitStack() as stack:
-            # loras = [(stack.enter_context(context.services.model_manager.get_model(**lora.dict(exclude={"weight"}))), lora.weight) for lora in self.unet.loras]
-            loras = [
-                (
-                    context.services.model_manager.get_model(**lora.model_dump(exclude={"weight"})).context.model,
-                    lora.weight,
-                )
-                for lora in self.unet.loras
-            ]
-
-            if loras:
-                unet.release_session()
-            with ONNXModelPatcher.apply_lora_unet(unet, loras):
-                # TODO:
-                _, _, h, w = latents.shape
-                unet.create_session(h, w)
-
-                timestep_dtype = next(
-                    (input.type for input in unet.session.get_inputs() if input.name == "timestep"), "tensor(float16)"
-                )
-                timestep_dtype = ORT_TO_NP_TYPE[timestep_dtype]
-                for i in tqdm(range(len(scheduler.timesteps))):
-                    t = scheduler.timesteps[i]
-                    # expand the latents if we are doing classifier free guidance
-                    latent_model_input = np.concatenate([latents] * 2) if do_classifier_free_guidance else latents
-                    latent_model_input = scheduler.scale_model_input(numpy2torch(latent_model_input, device), t)
-                    latent_model_input = latent_model_input.cpu().numpy()
-
-                    # predict the noise residual
-                    timestep = np.array([t], dtype=timestep_dtype)
-                    noise_pred = unet(sample=latent_model_input, timestep=timestep, encoder_hidden_states=prompt_embeds)
-                    noise_pred = noise_pred[0]
-
-                    # perform guidance
-                    if do_classifier_free_guidance:
-                        noise_pred_uncond, noise_pred_text = np.split(noise_pred, 2)
-                        noise_pred = noise_pred_uncond + self.cfg_scale * (noise_pred_text - noise_pred_uncond)
-
-                    # compute the previous noisy sample x_t -> x_t-1
-                    scheduler_output = scheduler.step(
-                        numpy2torch(noise_pred, device), t, numpy2torch(latents, device), **extra_step_kwargs
-                    )
-                    latents = torch2numpy(scheduler_output.prev_sample)
-
-                    state = PipelineIntermediateState(
-                        run_id="test", step=i, timestep=timestep, latents=scheduler_output.prev_sample
-                    )
-                    dispatch_progress(self, context=context, source_node_id=source_node_id, intermediate_state=state)
-
-                    # call the callback, if provided
-                    # if callback is not None and i % callback_steps == 0:
-                    #    callback(i, t, latents)
-
-        torch.cuda.empty_cache()
-
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        context.services.latents.save(name, latents)
-        return build_latents_output(latents_name=name, latents=torch.from_numpy(latents))
-
-
-# Latent to image
-@invocation(
-    "l2i_onnx",
-    title="ONNX Latents to Image",
-    tags=["latents", "image", "vae", "onnx"],
-    category="image",
-    version="1.2.0",
-)
-class ONNXLatentsToImageInvocation(BaseInvocation, WithMetadata):
-    """Generates an image from latents."""
-
-    latents: LatentsField = InputField(
-        description=FieldDescriptions.denoised_latents,
-        input=Input.Connection,
-    )
-    vae: VaeField = InputField(
-        description=FieldDescriptions.vae,
-        input=Input.Connection,
-    )
-    # tiled: bool = InputField(default=False, description="Decode latents by overlaping tiles(less memory consumption)")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
-
-        if self.vae.vae.submodel != SubModelType.VaeDecoder:
-            raise Exception(f"Expected vae_decoder, found: {self.vae.vae.model_type}")
-
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.model_dump(),
-        )
-
-        # clear memory as vae decode can request a lot
-        torch.cuda.empty_cache()
-
-        with vae_info as vae:
-            vae.create_session()
-
-            # copied from
-            # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L427
-            latents = 1 / 0.18215 * latents
-            # image = self.vae_decoder(latent_sample=latents)[0]
-            # it seems likes there is a strange result for using half-precision vae decoder if batchsize>1
-            image = np.concatenate([vae(latent_sample=latents[i : i + 1])[0] for i in range(latents.shape[0])])
-
-            image = np.clip(image / 2 + 0.5, 0, 1)
-            image = image.transpose((0, 2, 3, 1))
-            image = VaeImageProcessor.numpy_to_pil(image)[0]
-
-        torch.cuda.empty_cache()
-
-        image_dto = context.services.images.create(
-            image=image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-@invocation_output("model_loader_output_onnx")
-class ONNXModelLoaderOutput(BaseInvocationOutput):
-    """Model loader output"""
-
-    unet: UNetField = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
-    clip: ClipField = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
-    vae_decoder: VaeField = OutputField(default=None, description=FieldDescriptions.vae, title="VAE Decoder")
-    vae_encoder: VaeField = OutputField(default=None, description=FieldDescriptions.vae, title="VAE Encoder")
-
-
-class OnnxModelField(BaseModel):
-    """Onnx model field"""
-
-    model_name: str = Field(description="Name of the model")
-    base_model: BaseModelType = Field(description="Base model")
-    model_type: ModelType = Field(description="Model Type")
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
-@invocation("onnx_model_loader", title="ONNX Main Model", tags=["onnx", "model"], category="model", version="1.0.0")
-class OnnxModelLoaderInvocation(BaseInvocation):
-    """Loads a main model, outputting its submodels."""
-
-    model: OnnxModelField = InputField(
-        description=FieldDescriptions.onnx_main_model, input=Input.Direct, ui_type=UIType.ONNXModel
-    )
-
-    def invoke(self, context: InvocationContext) -> ONNXModelLoaderOutput:
-        base_model = self.model.base_model
-        model_name = self.model.model_name
-        model_type = ModelType.ONNX
-
-        # TODO: not found exceptions
-        if not context.services.model_manager.model_exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
-
-        """
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.Tokenizer,
-        ):
-            raise Exception(
-                f"Failed to find tokenizer submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.TextEncoder,
-        ):
-            raise Exception(
-                f"Failed to find text_encoder submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.UNet,
-        ):
-            raise Exception(
-                f"Failed to find unet submodel from {self.model_name}! Check if model corrupted"
-            )
-        """
-
-        return ONNXModelLoaderOutput(
-            unet=UNetField(
-                unet=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.UNet,
-                ),
-                scheduler=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Scheduler,
-                ),
-                loras=[],
-            ),
-            clip=ClipField(
-                tokenizer=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Tokenizer,
-                ),
-                text_encoder=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.TextEncoder,
-                ),
-                loras=[],
-                skipped_layers=0,
-            ),
-            vae_decoder=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.VaeDecoder,
-                ),
-            ),
-            vae_encoder=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.VaeEncoder,
-                ),
-            ),
-        )

invokeai/app/invocations/param_easing.py

@@ -40,8 +40,10 @@ from easing_functions import (
 from matplotlib.ticker import MaxNLocator
 
 from invokeai.app.invocations.primitives import FloatCollectionOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField
 
 
 @invocation(
@@ -109,7 +111,7 @@ EASING_FUNCTION_KEYS = Literal[tuple(EASING_FUNCTIONS_MAP.keys())]
     title="Step Param Easing",
     tags=["step", "easing"],
     category="step",
-    version="1.0.0",
+    version="1.0.1",
 )
 class StepParamEasingInvocation(BaseInvocation):
     """Experimental per-step parameter easing for denoising steps"""
@@ -148,19 +150,19 @@ class StepParamEasingInvocation(BaseInvocation):
         postlist = list(num_poststeps * [self.post_end_value])
 
         if log_diagnostics:
-            context.services.logger.debug("start_step: " + str(start_step))
-            context.services.logger.debug("end_step: " + str(end_step))
-            context.services.logger.debug("num_easing_steps: " + str(num_easing_steps))
-            context.services.logger.debug("num_presteps: " + str(num_presteps))
-            context.services.logger.debug("num_poststeps: " + str(num_poststeps))
-            context.services.logger.debug("prelist size: " + str(len(prelist)))
-            context.services.logger.debug("postlist size: " + str(len(postlist)))
-            context.services.logger.debug("prelist: " + str(prelist))
-            context.services.logger.debug("postlist: " + str(postlist))
+            context.logger.debug("start_step: " + str(start_step))
+            context.logger.debug("end_step: " + str(end_step))
+            context.logger.debug("num_easing_steps: " + str(num_easing_steps))
+            context.logger.debug("num_presteps: " + str(num_presteps))
+            context.logger.debug("num_poststeps: " + str(num_poststeps))
+            context.logger.debug("prelist size: " + str(len(prelist)))
+            context.logger.debug("postlist size: " + str(len(postlist)))
+            context.logger.debug("prelist: " + str(prelist))
+            context.logger.debug("postlist: " + str(postlist))
 
         easing_class = EASING_FUNCTIONS_MAP[self.easing]
         if log_diagnostics:
-            context.services.logger.debug("easing class: " + str(easing_class))
+            context.logger.debug("easing class: " + str(easing_class))
         easing_list = []
         if self.mirror:  # "expected" mirroring
             # if number of steps is even, squeeze duration down to (number_of_steps)/2
@@ -171,7 +173,7 @@ class StepParamEasingInvocation(BaseInvocation):
 
             base_easing_duration = int(np.ceil(num_easing_steps / 2.0))
             if log_diagnostics:
-                context.services.logger.debug("base easing duration: " + str(base_easing_duration))
+                context.logger.debug("base easing duration: " + str(base_easing_duration))
             even_num_steps = num_easing_steps % 2 == 0  # even number of steps
             easing_function = easing_class(
                 start=self.start_value,
@@ -183,14 +185,14 @@ class StepParamEasingInvocation(BaseInvocation):
                 easing_val = easing_function.ease(step_index)
                 base_easing_vals.append(easing_val)
                 if log_diagnostics:
-                    context.services.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(easing_val))
+                    context.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(easing_val))
             if even_num_steps:
                 mirror_easing_vals = list(reversed(base_easing_vals))
             else:
                 mirror_easing_vals = list(reversed(base_easing_vals[0:-1]))
             if log_diagnostics:
-                context.services.logger.debug("base easing vals: " + str(base_easing_vals))
-                context.services.logger.debug("mirror easing vals: " + str(mirror_easing_vals))
+                context.logger.debug("base easing vals: " + str(base_easing_vals))
+                context.logger.debug("mirror easing vals: " + str(mirror_easing_vals))
             easing_list = base_easing_vals + mirror_easing_vals
 
         # FIXME: add alt_mirror option (alternative to default or mirror), or remove entirely
@@ -225,12 +227,12 @@ class StepParamEasingInvocation(BaseInvocation):
                 step_val = easing_function.ease(step_index)
                 easing_list.append(step_val)
                 if log_diagnostics:
-                    context.services.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
+                    context.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
 
         if log_diagnostics:
-            context.services.logger.debug("prelist size: " + str(len(prelist)))
-            context.services.logger.debug("easing_list size: " + str(len(easing_list)))
-            context.services.logger.debug("postlist size: " + str(len(postlist)))
+            context.logger.debug("prelist size: " + str(len(prelist)))
+            context.logger.debug("easing_list size: " + str(len(easing_list)))
+            context.logger.debug("postlist size: " + str(len(postlist)))
 
         param_list = prelist + easing_list + postlist
 

invokeai/app/invocations/primitives.py

@@ -1,20 +1,28 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
-from typing import Optional, Tuple
+from typing import Optional
 
 import torch
-from pydantic import BaseModel, Field
 
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
+from invokeai.app.invocations.fields import (
+    ColorField,
+    ConditioningField,
+    DenoiseMaskField,
+    FieldDescriptions,
+    ImageField,
+    Input,
+    InputField,
+    LatentsField,
+    OutputField,
+    UIComponent,
+)
+from invokeai.app.services.images.images_common import ImageDTO
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
     invocation,
     invocation_output,
 )
@@ -221,18 +229,6 @@ class StringCollectionInvocation(BaseInvocation):
 # region Image
 
 
-class ImageField(BaseModel):
-    """An image primitive field"""
-
-    image_name: str = Field(description="The name of the image")
-
-
-class BoardField(BaseModel):
-    """A board primitive field"""
-
-    board_id: str = Field(description="The id of the board")
-
-
 @invocation_output("image_output")
 class ImageOutput(BaseInvocationOutput):
     """Base class for nodes that output a single image"""
@@ -241,6 +237,14 @@ class ImageOutput(BaseInvocationOutput):
     width: int = OutputField(description="The width of the image in pixels")
     height: int = OutputField(description="The height of the image in pixels")
 
+    @classmethod
+    def build(cls, image_dto: ImageDTO) -> "ImageOutput":
+        return cls(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
 
 @invocation_output("image_collection_output")
 class ImageCollectionOutput(BaseInvocationOutput):
@@ -251,16 +255,14 @@ class ImageCollectionOutput(BaseInvocationOutput):
     )
 
 
-@invocation("image", title="Image Primitive", tags=["primitives", "image"], category="primitives", version="1.0.0")
-class ImageInvocation(
-    BaseInvocation,
-):
+@invocation("image", title="Image Primitive", tags=["primitives", "image"], category="primitives", version="1.0.1")
+class ImageInvocation(BaseInvocation):
     """An image primitive value"""
 
     image: ImageField = InputField(description="The image to load")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         return ImageOutput(
             image=ImageField(image_name=self.image.image_name),
@@ -290,42 +292,40 @@ class ImageCollectionInvocation(BaseInvocation):
 # region DenoiseMask
 
 
-class DenoiseMaskField(BaseModel):
-    """An inpaint mask field"""
-
-    mask_name: str = Field(description="The name of the mask image")
-    masked_latents_name: Optional[str] = Field(default=None, description="The name of the masked image latents")
-
-
 @invocation_output("denoise_mask_output")
 class DenoiseMaskOutput(BaseInvocationOutput):
     """Base class for nodes that output a single image"""
 
     denoise_mask: DenoiseMaskField = OutputField(description="Mask for denoise model run")
 
+    @classmethod
+    def build(cls, mask_name: str, masked_latents_name: Optional[str] = None) -> "DenoiseMaskOutput":
+        return cls(
+            denoise_mask=DenoiseMaskField(mask_name=mask_name, masked_latents_name=masked_latents_name),
+        )
+
 
 # endregion
 
 # region Latents
 
 
-class LatentsField(BaseModel):
-    """A latents tensor primitive field"""
-
-    latents_name: str = Field(description="The name of the latents")
-    seed: Optional[int] = Field(default=None, description="Seed used to generate this latents")
-
-
 @invocation_output("latents_output")
 class LatentsOutput(BaseInvocationOutput):
     """Base class for nodes that output a single latents tensor"""
 
-    latents: LatentsField = OutputField(
-        description=FieldDescriptions.latents,
-    )
+    latents: LatentsField = OutputField(description=FieldDescriptions.latents)
     width: int = OutputField(description=FieldDescriptions.width)
     height: int = OutputField(description=FieldDescriptions.height)
 
+    @classmethod
+    def build(cls, latents_name: str, latents: torch.Tensor, seed: Optional[int] = None) -> "LatentsOutput":
+        return cls(
+            latents=LatentsField(latents_name=latents_name, seed=seed),
+            width=latents.size()[3] * LATENT_SCALE_FACTOR,
+            height=latents.size()[2] * LATENT_SCALE_FACTOR,
+        )
+
 
 @invocation_output("latents_collection_output")
 class LatentsCollectionOutput(BaseInvocationOutput):
@@ -337,7 +337,7 @@ class LatentsCollectionOutput(BaseInvocationOutput):
 
 
 @invocation(
-    "latents", title="Latents Primitive", tags=["primitives", "latents"], category="primitives", version="1.0.0"
+    "latents", title="Latents Primitive", tags=["primitives", "latents"], category="primitives", version="1.0.1"
 )
 class LatentsInvocation(BaseInvocation):
     """A latents tensor primitive value"""
@@ -345,9 +345,9 @@ class LatentsInvocation(BaseInvocation):
     latents: LatentsField = InputField(description="The latents tensor", input=Input.Connection)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
-        return build_latents_output(self.latents.latents_name, latents)
+        return LatentsOutput.build(self.latents.latents_name, latents)
 
 
 @invocation(
@@ -368,31 +368,11 @@ class LatentsCollectionInvocation(BaseInvocation):
         return LatentsCollectionOutput(collection=self.collection)
 
 
-def build_latents_output(latents_name: str, latents: torch.Tensor, seed: Optional[int] = None):
-    return LatentsOutput(
-        latents=LatentsField(latents_name=latents_name, seed=seed),
-        width=latents.size()[3] * 8,
-        height=latents.size()[2] * 8,
-    )
-
-
 # endregion
 
 # region Color
 
 
-class ColorField(BaseModel):
-    """A color primitive field"""
-
-    r: int = Field(ge=0, le=255, description="The red component")
-    g: int = Field(ge=0, le=255, description="The green component")
-    b: int = Field(ge=0, le=255, description="The blue component")
-    a: int = Field(ge=0, le=255, description="The alpha component")
-
-    def tuple(self) -> Tuple[int, int, int, int]:
-        return (self.r, self.g, self.b, self.a)
-
-
 @invocation_output("color_output")
 class ColorOutput(BaseInvocationOutput):
     """Base class for nodes that output a single color"""
@@ -424,18 +404,16 @@ class ColorInvocation(BaseInvocation):
 # region Conditioning
 
 
-class ConditioningField(BaseModel):
-    """A conditioning tensor primitive value"""
-
-    conditioning_name: str = Field(description="The name of conditioning tensor")
-
-
 @invocation_output("conditioning_output")
 class ConditioningOutput(BaseInvocationOutput):
     """Base class for nodes that output a single conditioning tensor"""
 
     conditioning: ConditioningField = OutputField(description=FieldDescriptions.cond)
 
+    @classmethod
+    def build(cls, conditioning_name: str) -> "ConditioningOutput":
+        return cls(conditioning=ConditioningField(conditioning_name=conditioning_name))
+
 
 @invocation_output("conditioning_collection_output")
 class ConditioningCollectionOutput(BaseInvocationOutput):

invokeai/app/invocations/prompt.py

@@ -6,8 +6,10 @@ from dynamicprompts.generators import CombinatorialPromptGenerator, RandomPrompt
 from pydantic import field_validator
 
 from invokeai.app.invocations.primitives import StringCollectionOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, UIComponent, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, UIComponent
 
 
 @invocation(

invokeai/app/invocations/sdxl.py

@@ -1,14 +1,10 @@
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIType
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 from ...backend.model_management import ModelType, SubModelType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIType,
     invocation,
     invocation_output,
 )
@@ -34,7 +30,7 @@ class SDXLRefinerModelLoaderOutput(BaseInvocationOutput):
     vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
 
 
-@invocation("sdxl_model_loader", title="SDXL Main Model", tags=["model", "sdxl"], category="model", version="1.0.0")
+@invocation("sdxl_model_loader", title="SDXL Main Model", tags=["model", "sdxl"], category="model", version="1.0.1")
 class SDXLModelLoaderInvocation(BaseInvocation):
     """Loads an sdxl base model, outputting its submodels."""
 
@@ -49,7 +45,7 @@ class SDXLModelLoaderInvocation(BaseInvocation):
         model_type = ModelType.Main
 
         # TODO: not found exceptions
-        if not context.services.model_manager.model_exists(
+        if not context.models.exists(
             model_name=model_name,
             base_model=base_model,
             model_type=model_type,
@@ -120,7 +116,7 @@ class SDXLModelLoaderInvocation(BaseInvocation):
     title="SDXL Refiner Model",
     tags=["model", "sdxl", "refiner"],
     category="model",
-    version="1.0.0",
+    version="1.0.1",
 )
 class SDXLRefinerModelLoaderInvocation(BaseInvocation):
     """Loads an sdxl refiner model, outputting its submodels."""
@@ -138,7 +134,7 @@ class SDXLRefinerModelLoaderInvocation(BaseInvocation):
         model_type = ModelType.Main
 
         # TODO: not found exceptions
-        if not context.services.model_manager.model_exists(
+        if not context.models.exists(
             model_name=model_name,
             base_model=base_model,
             model_type=model_type,

invokeai/app/invocations/strings.py

@@ -2,16 +2,15 @@
 
 import re
 
+from invokeai.app.services.shared.invocation_context import InvocationContext
+
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
     invocation,
     invocation_output,
 )
+from .fields import InputField, OutputField, UIComponent
 from .primitives import StringOutput
 
 

invokeai/app/invocations/t2i_adapter.py

@@ -5,17 +5,13 @@ from pydantic import BaseModel, ConfigDict, Field, field_validator, model_valida
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
 from invokeai.app.invocations.controlnet_image_processors import CONTROLNET_RESIZE_VALUES
-from invokeai.app.invocations.primitives import ImageField
+from invokeai.app.invocations.fields import FieldDescriptions, ImageField, Input, InputField, OutputField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.model_management.models.base import BaseModelType
 
 

invokeai/app/invocations/tiles.py

@@ -8,16 +8,12 @@ from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
     Classification,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    WithMetadata,
     invocation,
     invocation_output,
 )
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField, Input, InputField, OutputField, WithBoard, WithMetadata
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.tiles.tiles import (
     calc_tiles_even_split,
     calc_tiles_min_overlap,
@@ -236,7 +232,7 @@ BLEND_MODES = Literal["Linear", "Seam"]
     version="1.1.0",
     classification=Classification.Beta,
 )
-class MergeTilesToImageInvocation(BaseInvocation, WithMetadata):
+class MergeTilesToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Merge multiple tile images into a single image."""
 
     # Inputs
@@ -268,7 +264,7 @@ class MergeTilesToImageInvocation(BaseInvocation, WithMetadata):
         # existed in memory at an earlier point in the graph.
         tile_np_images: list[np.ndarray] = []
         for image in images:
-            pil_image = context.services.images.get_pil_image(image.image_name)
+            pil_image = context.images.get_pil(image.image_name)
             pil_image = pil_image.convert("RGB")
             tile_np_images.append(np.array(pil_image))
 
@@ -291,18 +287,5 @@ class MergeTilesToImageInvocation(BaseInvocation, WithMetadata):
         # Convert into a PIL image and save
         pil_image = Image.fromarray(np_image)
 
-        image_dto = context.services.images.create(
-            image=pil_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        image_dto = context.images.save(image=pil_image)
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/upscale.py

@@ -5,16 +5,18 @@ from typing import Literal
 import cv2
 import numpy as np
 import torch
-from basicsr.archs.rrdbnet_arch import RRDBNet
 from PIL import Image
 from pydantic import ConfigDict
 
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.image_util.basicsr.rrdbnet_arch import RRDBNet
 from invokeai.backend.image_util.realesrgan.realesrgan import RealESRGAN
 from invokeai.backend.util.devices import choose_torch_device
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, WithBoard, WithMetadata
 
 # TODO: Populate this from disk?
 # TODO: Use model manager to load?
@@ -29,8 +31,8 @@ if choose_torch_device() == torch.device("mps"):
     from torch import mps
 
 
-@invocation("esrgan", title="Upscale (RealESRGAN)", tags=["esrgan", "upscale"], category="esrgan", version="1.3.0")
-class ESRGANInvocation(BaseInvocation, WithMetadata):
+@invocation("esrgan", title="Upscale (RealESRGAN)", tags=["esrgan", "upscale"], category="esrgan", version="1.3.1")
+class ESRGANInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Upscales an image using RealESRGAN."""
 
     image: ImageField = InputField(description="The input image")
@@ -42,8 +44,8 @@ class ESRGANInvocation(BaseInvocation, WithMetadata):
     model_config = ConfigDict(protected_namespaces=())
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-        models_path = context.services.configuration.models_path
+        image = context.images.get_pil(self.image.image_name)
+        models_path = context.config.get().models_path
 
         rrdbnet_model = None
         netscale = None
@@ -87,7 +89,7 @@ class ESRGANInvocation(BaseInvocation, WithMetadata):
             netscale = 2
         else:
             msg = f"Invalid RealESRGAN model: {self.model_name}"
-            context.services.logger.error(msg)
+            context.logger.error(msg)
             raise ValueError(msg)
 
         esrgan_model_path = Path(f"core/upscaling/realesrgan/{self.model_name}")
@@ -110,19 +112,6 @@ class ESRGANInvocation(BaseInvocation, WithMetadata):
         if choose_torch_device() == torch.device("mps"):
             mps.empty_cache()
 
-        image_dto = context.services.images.create(
-            image=pil_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=pil_image)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/services/events/events_base.py

@@ -11,7 +11,7 @@ from invokeai.app.services.session_queue.session_queue_common import (
     SessionQueueStatus,
 )
 from invokeai.app.util.misc import get_timestamp
-from invokeai.backend.model_management.model_manager import ModelInfo
+from invokeai.backend.model_management.model_manager import LoadedModelInfo
 from invokeai.backend.model_management.models.base import BaseModelType, ModelType, SubModelType
 
 
@@ -55,7 +55,7 @@ class EventServiceBase:
         queue_item_id: int,
         queue_batch_id: str,
         graph_execution_state_id: str,
-        node: dict,
+        node_id: str,
         source_node_id: str,
         progress_image: Optional[ProgressImage],
         step: int,
@@ -70,7 +70,7 @@ class EventServiceBase:
                 "queue_item_id": queue_item_id,
                 "queue_batch_id": queue_batch_id,
                 "graph_execution_state_id": graph_execution_state_id,
-                "node_id": node.get("id"),
+                "node_id": node_id,
                 "source_node_id": source_node_id,
                 "progress_image": progress_image.model_dump() if progress_image is not None else None,
                 "step": step,
@@ -201,7 +201,7 @@ class EventServiceBase:
         base_model: BaseModelType,
         model_type: ModelType,
         submodel: SubModelType,
-        model_info: ModelInfo,
+        loaded_model_info: LoadedModelInfo,
     ) -> None:
         """Emitted when a model is correctly loaded (returns model info)"""
         self.__emit_queue_event(
@@ -215,9 +215,9 @@ class EventServiceBase:
                 "base_model": base_model,
                 "model_type": model_type,
                 "submodel": submodel,
-                "hash": model_info.hash,
-                "location": str(model_info.location),
-                "precision": str(model_info.precision),
+                "hash": loaded_model_info.hash,
+                "location": str(loaded_model_info.location),
+                "precision": str(loaded_model_info.precision),
             },
         )
 

invokeai/app/services/image_files/image_files_base.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from PIL.Image import Image as PILImageType
 
-from invokeai.app.invocations.baseinvocation import MetadataField
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
 
 

invokeai/app/services/image_files/image_files_disk.py

@@ -7,7 +7,7 @@ from PIL import Image, PngImagePlugin
 from PIL.Image import Image as PILImageType
 from send2trash import send2trash
 
-from invokeai.app.invocations.baseinvocation import MetadataField
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
 from invokeai.app.util.thumbnails import get_thumbnail_name, make_thumbnail

invokeai/app/services/image_records/image_records_base.py

@@ -2,7 +2,7 @@ from abc import ABC, abstractmethod
 from datetime import datetime
 from typing import Optional
 
-from invokeai.app.invocations.metadata import MetadataField
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
 
 from .image_records_common import ImageCategory, ImageRecord, ImageRecordChanges, ResourceOrigin

invokeai/app/services/image_records/image_records_sqlite.py

@@ -3,7 +3,7 @@ import threading
 from datetime import datetime
 from typing import Optional, Union, cast
 
-from invokeai.app.invocations.baseinvocation import MetadataField, MetadataFieldValidator
+from invokeai.app.invocations.fields import MetadataField, MetadataFieldValidator
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
 from invokeai.app.services.shared.sqlite.sqlite_database import SqliteDatabase
 

invokeai/app/services/images/images_base.py

@@ -3,7 +3,7 @@ from typing import Callable, Optional
 
 from PIL.Image import Image as PILImageType
 
-from invokeai.app.invocations.baseinvocation import MetadataField
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.image_records.image_records_common import (
     ImageCategory,
     ImageRecord,

invokeai/app/services/images/images_default.py

@@ -2,7 +2,7 @@ from typing import Optional
 
 from PIL.Image import Image as PILImageType
 
-from invokeai.app.invocations.baseinvocation import MetadataField
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
 from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
@@ -154,7 +154,7 @@ class ImageService(ImageServiceABC):
             self.__invoker.services.logger.error("Image record not found")
             raise
         except Exception as e:
-            self.__invoker.services.logger.error("Problem getting image DTO")
+            self.__invoker.services.logger.error("Problem getting image metadata")
             raise e
 
     def get_workflow(self, image_name: str) -> Optional[WorkflowWithoutID]:

invokeai/app/services/invocation_cache/invocation_cache_memory.py

@@ -37,7 +37,8 @@ class MemoryInvocationCache(InvocationCacheBase):
         if self._max_cache_size == 0:
             return
         self._invoker.services.images.on_deleted(self._delete_by_match)
-        self._invoker.services.latents.on_deleted(self._delete_by_match)
+        self._invoker.services.tensors.on_deleted(self._delete_by_match)
+        self._invoker.services.conditioning.on_deleted(self._delete_by_match)
 
     def get(self, key: Union[int, str]) -> Optional[BaseInvocationOutput]:
         with self._lock:

invokeai/app/services/invocation_processor/invocation_processor_default.py

@@ -5,11 +5,11 @@ from threading import BoundedSemaphore, Event, Thread
 from typing import Optional
 
 import invokeai.backend.util.logging as logger
-from invokeai.app.invocations.baseinvocation import InvocationContext
 from invokeai.app.services.invocation_queue.invocation_queue_common import InvocationQueueItem
 from invokeai.app.services.invocation_stats.invocation_stats_common import (
     GESStatsNotFoundError,
 )
+from invokeai.app.services.shared.invocation_context import InvocationContextData, build_invocation_context
 from invokeai.app.util.profiler import Profiler
 
 from ..invoker import Invoker
@@ -54,6 +54,17 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                 else None
             )
 
+            def stats_cleanup(graph_execution_state_id: str) -> None:
+                if profiler:
+                    profile_path = profiler.stop()
+                    stats_path = profile_path.with_suffix(".json")
+                    self.__invoker.services.performance_statistics.dump_stats(
+                        graph_execution_state_id=graph_execution_state_id, output_path=stats_path
+                    )
+                with suppress(GESStatsNotFoundError):
+                    self.__invoker.services.performance_statistics.log_stats(graph_execution_state_id)
+                    self.__invoker.services.performance_statistics.reset_stats(graph_execution_state_id)
+
             while not stop_event.is_set():
                 try:
                     queue_item = self.__invoker.services.queue.get()
@@ -120,16 +131,20 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                         # which handles a few things:
                         # - nodes that require a value, but get it only from a connection
                         # - referencing the invocation cache instead of executing the node
-                        outputs = invocation.invoke_internal(
-                            InvocationContext(
-                                services=self.__invoker.services,
-                                graph_execution_state_id=graph_execution_state.id,
-                                queue_item_id=queue_item.session_queue_item_id,
-                                queue_id=queue_item.session_queue_id,
-                                queue_batch_id=queue_item.session_queue_batch_id,
-                                workflow=queue_item.workflow,
-                            )
+                        context_data = InvocationContextData(
+                            invocation=invocation,
+                            session_id=graph_id,
+                            workflow=queue_item.workflow,
+                            source_node_id=source_node_id,
+                            queue_id=queue_item.session_queue_id,
+                            queue_item_id=queue_item.session_queue_item_id,
+                            batch_id=queue_item.session_queue_batch_id,
                         )
+                        context = build_invocation_context(
+                            services=self.__invoker.services,
+                            context_data=context_data,
+                        )
+                        outputs = invocation.invoke_internal(context=context, services=self.__invoker.services)
 
                         # Check queue to see if this is canceled, and skip if so
                         if self.__invoker.services.queue.is_canceled(graph_execution_state.id):
@@ -156,8 +171,7 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     pass
 
                 except CanceledException:
-                    with suppress(GESStatsNotFoundError):
-                        self.__invoker.services.performance_statistics.reset_stats(graph_execution_state.id)
+                    stats_cleanup(graph_execution_state.id)
                     pass
 
                 except Exception as e:
@@ -182,8 +196,6 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                         error_type=e.__class__.__name__,
                         error=error,
                     )
-                    with suppress(GESStatsNotFoundError):
-                        self.__invoker.services.performance_statistics.reset_stats(graph_execution_state.id)
                     pass
 
                 # Check queue to see if this is canceled, and skip if so
@@ -215,21 +227,13 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                             error=traceback.format_exc(),
                         )
                 elif is_complete:
-                    with suppress(GESStatsNotFoundError):
-                        self.__invoker.services.performance_statistics.log_stats(graph_execution_state.id)
-                        self.__invoker.services.events.emit_graph_execution_complete(
-                            queue_batch_id=queue_item.session_queue_batch_id,
-                            queue_item_id=queue_item.session_queue_item_id,
-                            queue_id=queue_item.session_queue_id,
-                            graph_execution_state_id=graph_execution_state.id,
-                        )
-                        if profiler:
-                            profile_path = profiler.stop()
-                            stats_path = profile_path.with_suffix(".json")
-                            self.__invoker.services.performance_statistics.dump_stats(
-                                graph_execution_state_id=graph_execution_state.id, output_path=stats_path
-                            )
-                        self.__invoker.services.performance_statistics.reset_stats(graph_execution_state.id)
+                    self.__invoker.services.events.emit_graph_execution_complete(
+                        queue_batch_id=queue_item.session_queue_batch_id,
+                        queue_item_id=queue_item.session_queue_item_id,
+                        queue_id=queue_item.session_queue_id,
+                        graph_execution_state_id=graph_execution_state.id,
+                    )
+                    stats_cleanup(graph_execution_state.id)
 
         except KeyboardInterrupt:
             pass  # Log something? KeyboardInterrupt is probably not going to be seen by the processor

invokeai/app/services/invocation_services.py

@@ -3,9 +3,15 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING
 
+from invokeai.app.services.object_serializer.object_serializer_base import ObjectSerializerBase
+
 if TYPE_CHECKING:
     from logging import Logger
 
+    import torch
+
+    from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningFieldData
+
     from .board_image_records.board_image_records_base import BoardImageRecordStorageBase
     from .board_images.board_images_base import BoardImagesServiceABC
     from .board_records.board_records_base import BoardRecordStorageBase
@@ -21,7 +27,6 @@ if TYPE_CHECKING:
     from .invocation_queue.invocation_queue_base import InvocationQueueABC
     from .invocation_stats.invocation_stats_base import InvocationStatsServiceBase
     from .item_storage.item_storage_base import ItemStorageABC
-    from .latents_storage.latents_storage_base import LatentsStorageBase
     from .model_install import ModelInstallServiceBase
     from .model_manager.model_manager_base import ModelManagerServiceBase
     from .model_records import ModelRecordServiceBase
@@ -36,33 +41,6 @@ if TYPE_CHECKING:
 class InvocationServices:
     """Services that can be used by invocations"""
 
-    # TODO: Just forward-declared everything due to circular dependencies. Fix structure.
-    board_images: "BoardImagesServiceABC"
-    board_image_record_storage: "BoardImageRecordStorageBase"
-    boards: "BoardServiceABC"
-    board_records: "BoardRecordStorageBase"
-    configuration: "InvokeAIAppConfig"
-    events: "EventServiceBase"
-    graph_execution_manager: "ItemStorageABC[GraphExecutionState]"
-    images: "ImageServiceABC"
-    image_records: "ImageRecordStorageBase"
-    image_files: "ImageFileStorageBase"
-    latents: "LatentsStorageBase"
-    logger: "Logger"
-    model_manager: "ModelManagerServiceBase"
-    model_records: "ModelRecordServiceBase"
-    download_queue: "DownloadQueueServiceBase"
-    model_install: "ModelInstallServiceBase"
-    processor: "InvocationProcessorABC"
-    performance_statistics: "InvocationStatsServiceBase"
-    queue: "InvocationQueueABC"
-    session_queue: "SessionQueueBase"
-    session_processor: "SessionProcessorBase"
-    invocation_cache: "InvocationCacheBase"
-    names: "NameServiceBase"
-    urls: "UrlServiceBase"
-    workflow_records: "WorkflowRecordsStorageBase"
-
     def __init__(
         self,
         board_images: "BoardImagesServiceABC",
@@ -75,7 +53,6 @@ class InvocationServices:
         images: "ImageServiceABC",
         image_files: "ImageFileStorageBase",
         image_records: "ImageRecordStorageBase",
-        latents: "LatentsStorageBase",
         logger: "Logger",
         model_manager: "ModelManagerServiceBase",
         model_records: "ModelRecordServiceBase",
@@ -90,6 +67,8 @@ class InvocationServices:
         names: "NameServiceBase",
         urls: "UrlServiceBase",
         workflow_records: "WorkflowRecordsStorageBase",
+        tensors: "ObjectSerializerBase[torch.Tensor]",
+        conditioning: "ObjectSerializerBase[ConditioningFieldData]",
     ):
         self.board_images = board_images
         self.board_image_records = board_image_records
@@ -101,7 +80,6 @@ class InvocationServices:
         self.images = images
         self.image_files = image_files
         self.image_records = image_records
-        self.latents = latents
         self.logger = logger
         self.model_manager = model_manager
         self.model_records = model_records
@@ -116,3 +94,5 @@ class InvocationServices:
         self.names = names
         self.urls = urls
         self.workflow_records = workflow_records
+        self.tensors = tensors
+        self.conditioning = conditioning

invokeai/app/services/invocation_stats/invocation_stats_default.py

@@ -106,9 +106,9 @@ class InvocationStatsService(InvocationStatsServiceBase):
             del self._stats[graph_execution_state_id]
             del self._cache_stats[graph_execution_state_id]
         except KeyError as e:
-            msg = f"Attempted to clear statistics for unknown graph {graph_execution_state_id}: {e}."
-            logger.error(msg)
-            raise GESStatsNotFoundError(msg) from e
+            raise GESStatsNotFoundError(
+                f"Attempted to clear statistics for unknown graph {graph_execution_state_id}: {e}."
+            ) from e
 
     def get_stats(self, graph_execution_state_id: str) -> InvocationStatsSummary:
         graph_stats_summary = self._get_graph_summary(graph_execution_state_id)
@@ -136,9 +136,9 @@ class InvocationStatsService(InvocationStatsServiceBase):
         try:
             cache_stats = self._cache_stats[graph_execution_state_id]
         except KeyError as e:
-            msg = f"Attempted to get model cache statistics for unknown graph {graph_execution_state_id}: {e}."
-            logger.error(msg)
-            raise GESStatsNotFoundError(msg) from e
+            raise GESStatsNotFoundError(
+                f"Attempted to get model cache statistics for unknown graph {graph_execution_state_id}: {e}."
+            ) from e
 
         return ModelCacheStatsSummary(
             cache_hits=cache_stats.hits,
@@ -154,9 +154,9 @@ class InvocationStatsService(InvocationStatsServiceBase):
         try:
             graph_stats = self._stats[graph_execution_state_id]
         except KeyError as e:
-            msg = f"Attempted to get graph statistics for unknown graph {graph_execution_state_id}: {e}."
-            logger.error(msg)
-            raise GESStatsNotFoundError(msg) from e
+            raise GESStatsNotFoundError(
+                f"Attempted to get graph statistics for unknown graph {graph_execution_state_id}: {e}."
+            ) from e
 
         return graph_stats.get_graph_stats_summary(graph_execution_state_id)
 
@@ -164,8 +164,8 @@ class InvocationStatsService(InvocationStatsServiceBase):
         try:
             graph_stats = self._stats[graph_execution_state_id]
         except KeyError as e:
-            msg = f"Attempted to get node statistics for unknown graph {graph_execution_state_id}: {e}."
-            logger.error(msg)
-            raise GESStatsNotFoundError(msg) from e
+            raise GESStatsNotFoundError(
+                f"Attempted to get node statistics for unknown graph {graph_execution_state_id}: {e}."
+            ) from e
 
         return graph_stats.get_node_stats_summaries()

invokeai/app/services/item_storage/item_storage_base.py

@@ -30,7 +30,7 @@ class ItemStorageABC(ABC, Generic[T]):
     @abstractmethod
     def set(self, item: T) -> None:
         """
-        Sets the item. The id will be extracted based on id_field.
+        Sets the item.
         :param item: the item to set
         """
         pass

invokeai/app/services/latents_storage/latents_storage_base.py

@@ -1,45 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-from abc import ABC, abstractmethod
-from typing import Callable
-
-import torch
-
-
-class LatentsStorageBase(ABC):
-    """Responsible for storing and retrieving latents."""
-
-    _on_changed_callbacks: list[Callable[[torch.Tensor], None]]
-    _on_deleted_callbacks: list[Callable[[str], None]]
-
-    def __init__(self) -> None:
-        self._on_changed_callbacks = []
-        self._on_deleted_callbacks = []
-
-    @abstractmethod
-    def get(self, name: str) -> torch.Tensor:
-        pass
-
-    @abstractmethod
-    def save(self, name: str, data: torch.Tensor) -> None:
-        pass
-
-    @abstractmethod
-    def delete(self, name: str) -> None:
-        pass
-
-    def on_changed(self, on_changed: Callable[[torch.Tensor], None]) -> None:
-        """Register a callback for when an item is changed"""
-        self._on_changed_callbacks.append(on_changed)
-
-    def on_deleted(self, on_deleted: Callable[[str], None]) -> None:
-        """Register a callback for when an item is deleted"""
-        self._on_deleted_callbacks.append(on_deleted)
-
-    def _on_changed(self, item: torch.Tensor) -> None:
-        for callback in self._on_changed_callbacks:
-            callback(item)
-
-    def _on_deleted(self, item_id: str) -> None:
-        for callback in self._on_deleted_callbacks:
-            callback(item_id)

invokeai/app/services/latents_storage/latents_storage_disk.py

@@ -1,58 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-from pathlib import Path
-from typing import Union
-
-import torch
-
-from invokeai.app.services.invoker import Invoker
-
-from .latents_storage_base import LatentsStorageBase
-
-
-class DiskLatentsStorage(LatentsStorageBase):
-    """Stores latents in a folder on disk without caching"""
-
-    __output_folder: Path
-
-    def __init__(self, output_folder: Union[str, Path]):
-        self.__output_folder = output_folder if isinstance(output_folder, Path) else Path(output_folder)
-        self.__output_folder.mkdir(parents=True, exist_ok=True)
-
-    def start(self, invoker: Invoker) -> None:
-        self._invoker = invoker
-        self._delete_all_latents()
-
-    def get(self, name: str) -> torch.Tensor:
-        latent_path = self.get_path(name)
-        return torch.load(latent_path)
-
-    def save(self, name: str, data: torch.Tensor) -> None:
-        self.__output_folder.mkdir(parents=True, exist_ok=True)
-        latent_path = self.get_path(name)
-        torch.save(data, latent_path)
-
-    def delete(self, name: str) -> None:
-        latent_path = self.get_path(name)
-        latent_path.unlink()
-
-    def get_path(self, name: str) -> Path:
-        return self.__output_folder / name
-
-    def _delete_all_latents(self) -> None:
-        """
-        Deletes all latents from disk.
-        Must be called after we have access to `self._invoker` (e.g. in `start()`).
-        """
-        deleted_latents_count = 0
-        freed_space = 0
-        for latents_file in Path(self.__output_folder).glob("*"):
-            if latents_file.is_file():
-                freed_space += latents_file.stat().st_size
-                deleted_latents_count += 1
-                latents_file.unlink()
-        if deleted_latents_count > 0:
-            freed_space_in_mb = round(freed_space / 1024 / 1024, 2)
-            self._invoker.services.logger.info(
-                f"Deleted {deleted_latents_count} latents files (freed {freed_space_in_mb}MB)"
-            )

invokeai/app/services/latents_storage/latents_storage_forward_cache.py

@@ -1,68 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-from queue import Queue
-from typing import Dict, Optional
-
-import torch
-
-from invokeai.app.services.invoker import Invoker
-
-from .latents_storage_base import LatentsStorageBase
-
-
-class ForwardCacheLatentsStorage(LatentsStorageBase):
-    """Caches the latest N latents in memory, writing-thorugh to and reading from underlying storage"""
-
-    __cache: Dict[str, torch.Tensor]
-    __cache_ids: Queue
-    __max_cache_size: int
-    __underlying_storage: LatentsStorageBase
-
-    def __init__(self, underlying_storage: LatentsStorageBase, max_cache_size: int = 20):
-        super().__init__()
-        self.__underlying_storage = underlying_storage
-        self.__cache = {}
-        self.__cache_ids = Queue()
-        self.__max_cache_size = max_cache_size
-
-    def start(self, invoker: Invoker) -> None:
-        self._invoker = invoker
-        start_op = getattr(self.__underlying_storage, "start", None)
-        if callable(start_op):
-            start_op(invoker)
-
-    def stop(self, invoker: Invoker) -> None:
-        self._invoker = invoker
-        stop_op = getattr(self.__underlying_storage, "stop", None)
-        if callable(stop_op):
-            stop_op(invoker)
-
-    def get(self, name: str) -> torch.Tensor:
-        cache_item = self.__get_cache(name)
-        if cache_item is not None:
-            return cache_item
-
-        latent = self.__underlying_storage.get(name)
-        self.__set_cache(name, latent)
-        return latent
-
-    def save(self, name: str, data: torch.Tensor) -> None:
-        self.__underlying_storage.save(name, data)
-        self.__set_cache(name, data)
-        self._on_changed(data)
-
-    def delete(self, name: str) -> None:
-        self.__underlying_storage.delete(name)
-        if name in self.__cache:
-            del self.__cache[name]
-        self._on_deleted(name)
-
-    def __get_cache(self, name: str) -> Optional[torch.Tensor]:
-        return None if name not in self.__cache else self.__cache[name]
-
-    def __set_cache(self, name: str, data: torch.Tensor):
-        if name not in self.__cache:
-            self.__cache[name] = data
-            self.__cache_ids.put(name)
-            if self.__cache_ids.qsize() > self.__max_cache_size:
-                self.__cache.pop(self.__cache_ids.get())

invokeai/app/services/model_manager/model_manager_base.py

@@ -5,25 +5,23 @@ from __future__ import annotations
 from abc import ABC, abstractmethod
 from logging import Logger
 from pathlib import Path
-from typing import TYPE_CHECKING, Callable, List, Literal, Optional, Tuple, Union
+from typing import Callable, List, Literal, Optional, Tuple, Union
 
 from pydantic import Field
 
 from invokeai.app.services.config.config_default import InvokeAIAppConfig
+from invokeai.app.services.shared.invocation_context import InvocationContextData
 from invokeai.backend.model_management import (
     AddModelResult,
     BaseModelType,
+    LoadedModelInfo,
     MergeInterpolationMethod,
-    ModelInfo,
     ModelType,
     SchedulerPredictionType,
     SubModelType,
 )
 from invokeai.backend.model_management.model_cache import CacheStats
 
-if TYPE_CHECKING:
-    from invokeai.app.invocations.baseinvocation import BaseInvocation, InvocationContext
-
 
 class ModelManagerServiceBase(ABC):
     """Responsible for managing models on disk and in memory"""
@@ -49,9 +47,8 @@ class ModelManagerServiceBase(ABC):
         base_model: BaseModelType,
         model_type: ModelType,
         submodel: Optional[SubModelType] = None,
-        node: Optional[BaseInvocation] = None,
-        context: Optional[InvocationContext] = None,
-    ) -> ModelInfo:
+        context_data: Optional[InvocationContextData] = None,
+    ) -> LoadedModelInfo:
         """Retrieve the indicated model with name and type.
         submodel can be used to get a part (such as the vae)
         of a diffusers pipeline."""

invokeai/app/services/model_manager/model_manager_default.py

@@ -11,11 +11,13 @@ from pydantic import Field
 
 from invokeai.app.services.config.config_default import InvokeAIAppConfig
 from invokeai.app.services.invocation_processor.invocation_processor_common import CanceledException
+from invokeai.app.services.invoker import Invoker
+from invokeai.app.services.shared.invocation_context import InvocationContextData
 from invokeai.backend.model_management import (
     AddModelResult,
     BaseModelType,
+    LoadedModelInfo,
     MergeInterpolationMethod,
-    ModelInfo,
     ModelManager,
     ModelMerger,
     ModelNotFoundException,
@@ -30,7 +32,7 @@ from invokeai.backend.util import choose_precision, choose_torch_device
 from .model_manager_base import ModelManagerServiceBase
 
 if TYPE_CHECKING:
-    from invokeai.app.invocations.baseinvocation import InvocationContext
+    pass
 
 
 # simple implementation
@@ -86,47 +88,50 @@ class ModelManagerService(ModelManagerServiceBase):
         )
         logger.info("Model manager service initialized")
 
+    def start(self, invoker: Invoker) -> None:
+        self._invoker: Optional[Invoker] = invoker
+
     def get_model(
         self,
         model_name: str,
         base_model: BaseModelType,
         model_type: ModelType,
         submodel: Optional[SubModelType] = None,
-        context: Optional[InvocationContext] = None,
-    ) -> ModelInfo:
+        context_data: Optional[InvocationContextData] = None,
+    ) -> LoadedModelInfo:
         """
         Retrieve the indicated model. submodel can be used to get a
         part (such as the vae) of a diffusers mode.
         """
 
         # we can emit model loading events if we are executing with access to the invocation context
-        if context:
+        if context_data is not None:
             self._emit_load_event(
-                context=context,
+                context_data=context_data,
                 model_name=model_name,
                 base_model=base_model,
                 model_type=model_type,
                 submodel=submodel,
             )
 
-        model_info = self.mgr.get_model(
+        loaded_model_info = self.mgr.get_model(
             model_name,
             base_model,
             model_type,
             submodel,
         )
 
-        if context:
+        if context_data is not None:
             self._emit_load_event(
-                context=context,
+                context_data=context_data,
                 model_name=model_name,
                 base_model=base_model,
                 model_type=model_type,
                 submodel=submodel,
-                model_info=model_info,
+                loaded_model_info=loaded_model_info,
             )
 
-        return model_info
+        return loaded_model_info
 
     def model_exists(
         self,
@@ -263,34 +268,37 @@ class ModelManagerService(ModelManagerServiceBase):
 
     def _emit_load_event(
         self,
-        context: InvocationContext,
+        context_data: InvocationContextData,
         model_name: str,
         base_model: BaseModelType,
         model_type: ModelType,
         submodel: Optional[SubModelType] = None,
-        model_info: Optional[ModelInfo] = None,
+        loaded_model_info: Optional[LoadedModelInfo] = None,
     ):
-        if context.services.queue.is_canceled(context.graph_execution_state_id):
+        if self._invoker is None:
+            return
+
+        if self._invoker.services.queue.is_canceled(context_data.session_id):
             raise CanceledException()
 
-        if model_info:
-            context.services.events.emit_model_load_completed(
-                queue_id=context.queue_id,
-                queue_item_id=context.queue_item_id,
-                queue_batch_id=context.queue_batch_id,
-                graph_execution_state_id=context.graph_execution_state_id,
+        if loaded_model_info:
+            self._invoker.services.events.emit_model_load_completed(
+                queue_id=context_data.queue_id,
+                queue_item_id=context_data.queue_item_id,
+                queue_batch_id=context_data.batch_id,
+                graph_execution_state_id=context_data.session_id,
                 model_name=model_name,
                 base_model=base_model,
                 model_type=model_type,
                 submodel=submodel,
-                model_info=model_info,
+                loaded_model_info=loaded_model_info,
             )
         else:
-            context.services.events.emit_model_load_started(
-                queue_id=context.queue_id,
-                queue_item_id=context.queue_item_id,
-                queue_batch_id=context.queue_batch_id,
-                graph_execution_state_id=context.graph_execution_state_id,
+            self._invoker.services.events.emit_model_load_started(
+                queue_id=context_data.queue_id,
+                queue_item_id=context_data.queue_item_id,
+                queue_batch_id=context_data.batch_id,
+                graph_execution_state_id=context_data.session_id,
                 model_name=model_name,
                 base_model=base_model,
                 model_type=model_type,

invokeai/app/services/object_serializer/object_serializer_base.py

@@ -0,0 +1,44 @@
+from abc import ABC, abstractmethod
+from typing import Callable, Generic, TypeVar
+
+T = TypeVar("T")
+
+
+class ObjectSerializerBase(ABC, Generic[T]):
+    """Saves and loads arbitrary python objects."""
+
+    def __init__(self) -> None:
+        self._on_deleted_callbacks: list[Callable[[str], None]] = []
+
+    @abstractmethod
+    def load(self, name: str) -> T:
+        """
+        Loads the object.
+        :param name: The name of the object to load.
+        :raises ObjectNotFoundError: if the object is not found
+        """
+        pass
+
+    @abstractmethod
+    def save(self, obj: T) -> str:
+        """
+        Saves the object, returning its name.
+        :param obj: The object to save.
+        """
+        pass
+
+    @abstractmethod
+    def delete(self, name: str) -> None:
+        """
+        Deletes the object, if it exists.
+        :param name: The name of the object to delete.
+        """
+        pass
+
+    def on_deleted(self, on_deleted: Callable[[str], None]) -> None:
+        """Register a callback for when an object is deleted"""
+        self._on_deleted_callbacks.append(on_deleted)
+
+    def _on_deleted(self, name: str) -> None:
+        for callback in self._on_deleted_callbacks:
+            callback(name)

invokeai/app/services/object_serializer/object_serializer_common.py

@@ -0,0 +1,5 @@
+class ObjectNotFoundError(KeyError):
+    """Raised when an object is not found while loading"""
+
+    def __init__(self, name: str) -> None:
+        super().__init__(f"Object with name {name} not found")

invokeai/app/services/object_serializer/object_serializer_disk.py

@@ -0,0 +1,85 @@
+import tempfile
+import typing
+from dataclasses import dataclass
+from pathlib import Path
+from typing import TYPE_CHECKING, Optional, TypeVar
+
+import torch
+
+from invokeai.app.services.object_serializer.object_serializer_base import ObjectSerializerBase
+from invokeai.app.services.object_serializer.object_serializer_common import ObjectNotFoundError
+from invokeai.app.util.misc import uuid_string
+
+if TYPE_CHECKING:
+    from invokeai.app.services.invoker import Invoker
+
+
+T = TypeVar("T")
+
+
+@dataclass
+class DeleteAllResult:
+    deleted_count: int
+    freed_space_bytes: float
+
+
+class ObjectSerializerDisk(ObjectSerializerBase[T]):
+    """Disk-backed storage for arbitrary python objects. Serialization is handled by `torch.save` and `torch.load`.
+
+    :param output_dir: The folder where the serialized objects will be stored
+    :param ephemeral: If True, objects will be stored in a temporary directory inside the given output_dir and cleaned up on exit
+    """
+
+    def __init__(self, output_dir: Path, ephemeral: bool = False):
+        super().__init__()
+        self._ephemeral = ephemeral
+        self._base_output_dir = output_dir
+        self._base_output_dir.mkdir(parents=True, exist_ok=True)
+        # Must specify `ignore_cleanup_errors` to avoid fatal errors during cleanup on Windows
+        self._tempdir = (
+            tempfile.TemporaryDirectory(dir=self._base_output_dir, ignore_cleanup_errors=True) if ephemeral else None
+        )
+        self._output_dir = Path(self._tempdir.name) if self._tempdir else self._base_output_dir
+        self.__obj_class_name: Optional[str] = None
+
+    def load(self, name: str) -> T:
+        file_path = self._get_path(name)
+        try:
+            return torch.load(file_path)  # pyright: ignore [reportUnknownMemberType]
+        except FileNotFoundError as e:
+            raise ObjectNotFoundError(name) from e
+
+    def save(self, obj: T) -> str:
+        name = self._new_name()
+        file_path = self._get_path(name)
+        torch.save(obj, file_path)  # pyright: ignore [reportUnknownMemberType]
+        return name
+
+    def delete(self, name: str) -> None:
+        file_path = self._get_path(name)
+        file_path.unlink()
+
+    @property
+    def _obj_class_name(self) -> str:
+        if not self.__obj_class_name:
+            # `__orig_class__` is not available in the constructor for some technical, undoubtedly very pythonic reason
+            self.__obj_class_name = typing.get_args(self.__orig_class__)[0].__name__  # pyright: ignore [reportUnknownMemberType, reportAttributeAccessIssue]
+        return self.__obj_class_name
+
+    def _get_path(self, name: str) -> Path:
+        return self._output_dir / name
+
+    def _new_name(self) -> str:
+        return f"{self._obj_class_name}_{uuid_string()}"
+
+    def _tempdir_cleanup(self) -> None:
+        """Calls `cleanup` on the temporary directory, if it exists."""
+        if self._tempdir:
+            self._tempdir.cleanup()
+
+    def __del__(self) -> None:
+        # In case the service is not properly stopped, clean up the temporary directory when the class instance is GC'd.
+        self._tempdir_cleanup()
+
+    def stop(self, invoker: "Invoker") -> None:
+        self._tempdir_cleanup()

invokeai/app/services/object_serializer/object_serializer_forward_cache.py

@@ -0,0 +1,65 @@
+from queue import Queue
+from typing import TYPE_CHECKING, Optional, TypeVar
+
+from invokeai.app.services.object_serializer.object_serializer_base import ObjectSerializerBase
+
+T = TypeVar("T")
+
+if TYPE_CHECKING:
+    from invokeai.app.services.invoker import Invoker
+
+
+class ObjectSerializerForwardCache(ObjectSerializerBase[T]):
+    """
+    Provides a LRU cache for an instance of `ObjectSerializerBase`.
+    Saving an object to the cache always writes through to the underlying storage.
+    """
+
+    def __init__(self, underlying_storage: ObjectSerializerBase[T], max_cache_size: int = 20):
+        super().__init__()
+        self._underlying_storage = underlying_storage
+        self._cache: dict[str, T] = {}
+        self._cache_ids = Queue[str]()
+        self._max_cache_size = max_cache_size
+
+    def start(self, invoker: "Invoker") -> None:
+        self._invoker = invoker
+        start_op = getattr(self._underlying_storage, "start", None)
+        if callable(start_op):
+            start_op(invoker)
+
+    def stop(self, invoker: "Invoker") -> None:
+        self._invoker = invoker
+        stop_op = getattr(self._underlying_storage, "stop", None)
+        if callable(stop_op):
+            stop_op(invoker)
+
+    def load(self, name: str) -> T:
+        cache_item = self._get_cache(name)
+        if cache_item is not None:
+            return cache_item
+
+        obj = self._underlying_storage.load(name)
+        self._set_cache(name, obj)
+        return obj
+
+    def save(self, obj: T) -> str:
+        name = self._underlying_storage.save(obj)
+        self._set_cache(name, obj)
+        return name
+
+    def delete(self, name: str) -> None:
+        self._underlying_storage.delete(name)
+        if name in self._cache:
+            del self._cache[name]
+        self._on_deleted(name)
+
+    def _get_cache(self, name: str) -> Optional[T]:
+        return None if name not in self._cache else self._cache[name]
+
+    def _set_cache(self, name: str, data: T):
+        if name not in self._cache:
+            self._cache[name] = data
+            self._cache_ids.put(name)
+            if self._cache_ids.qsize() > self._max_cache_size:
+                self._cache.pop(self._cache_ids.get())

invokeai/app/services/shared/graph.py

@@ -2,7 +2,7 @@
 
 import copy
 import itertools
-from typing import Annotated, Any, Optional, Union, get_args, get_origin, get_type_hints
+from typing import Annotated, Any, Optional, TypeVar, Union, get_args, get_origin, get_type_hints
 
 import networkx as nx
 from pydantic import BaseModel, ConfigDict, field_validator, model_validator
@@ -13,14 +13,11 @@ from invokeai.app.invocations import *  # noqa: F401 F403
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIType,
     invocation,
     invocation_output,
 )
+from invokeai.app.invocations.fields import Input, InputField, OutputField, UIType
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import uuid_string
 
 # in 3.10 this would be "from types import NoneType"
@@ -141,6 +138,16 @@ def are_connections_compatible(
     return are_connection_types_compatible(from_node_field, to_node_field)
 
 
+T = TypeVar("T")
+
+
+def copydeep(obj: T) -> T:
+    """Deep-copies an object. If it is a pydantic model, use the model's copy method."""
+    if isinstance(obj, BaseModel):
+        return obj.model_copy(deep=True)
+    return copy.deepcopy(obj)
+
+
 class NodeAlreadyInGraphError(ValueError):
     pass
 
@@ -530,7 +537,7 @@ class Graph(BaseModel):
         except NodeNotFoundError:
             return False
 
-    def get_node(self, node_path: str) -> InvocationsUnion:
+    def get_node(self, node_path: str) -> BaseInvocation:
         """Gets a node from the graph using a node path."""
         # Materialized graphs may have nodes at the top level
         graph, node_id = self._get_graph_and_node(node_path)
@@ -881,7 +888,7 @@ class GraphExecutionState(BaseModel):
         # If next is still none, there's no next node, return None
         return next_node
 
-    def complete(self, node_id: str, output: InvocationOutputsUnion):
+    def complete(self, node_id: str, output: BaseInvocationOutput) -> None:
         """Marks a node as complete"""
 
         if node_id not in self.execution_graph.nodes:
@@ -1118,17 +1125,22 @@ class GraphExecutionState(BaseModel):
 
     def _prepare_inputs(self, node: BaseInvocation):
         input_edges = [e for e in self.execution_graph.edges if e.destination.node_id == node.id]
+        # Inputs must be deep-copied, else if a node mutates the object, other nodes that get the same input
+        # will see the mutation.
         if isinstance(node, CollectInvocation):
             output_collection = [
-                getattr(self.results[edge.source.node_id], edge.source.field)
+                copydeep(getattr(self.results[edge.source.node_id], edge.source.field))
                 for edge in input_edges
                 if edge.destination.field == "item"
             ]
             node.collection = output_collection
         else:
             for edge in input_edges:
-                output_value = getattr(self.results[edge.source.node_id], edge.source.field)
-                setattr(node, edge.destination.field, output_value)
+                setattr(
+                    node,
+                    edge.destination.field,
+                    copydeep(getattr(self.results[edge.source.node_id], edge.source.field)),
+                )
 
     # TODO: Add API for modifying underlying graph that checks if the change will be valid given the current execution state
     def _is_edge_valid(self, edge: Edge) -> bool:

invokeai/app/services/shared/invocation_context.py

@@ -0,0 +1,409 @@
+from dataclasses import dataclass
+from typing import TYPE_CHECKING, Optional
+
+from PIL.Image import Image
+from torch import Tensor
+
+from invokeai.app.invocations.fields import MetadataField, WithBoard, WithMetadata
+from invokeai.app.services.boards.boards_common import BoardDTO
+from invokeai.app.services.config.config_default import InvokeAIAppConfig
+from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.services.images.images_common import ImageDTO
+from invokeai.app.services.invocation_services import InvocationServices
+from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
+from invokeai.app.util.step_callback import stable_diffusion_step_callback
+from invokeai.backend.model_management.model_manager import LoadedModelInfo
+from invokeai.backend.model_management.models.base import BaseModelType, ModelType, SubModelType
+from invokeai.backend.stable_diffusion.diffusers_pipeline import PipelineIntermediateState
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningFieldData
+
+if TYPE_CHECKING:
+    from invokeai.app.invocations.baseinvocation import BaseInvocation
+
+"""
+The InvocationContext provides access to various services and data about the current invocation.
+
+We do not provide the invocation services directly, as their methods are both dangerous and
+inconvenient to use.
+
+For example:
+- The `images` service allows nodes to delete or unsafely modify existing images.
+- The `configuration` service allows nodes to change the app's config at runtime.
+- The `events` service allows nodes to emit arbitrary events.
+
+Wrapping these services provides a simpler and safer interface for nodes to use.
+
+When a node executes, a fresh `InvocationContext` is built for it, ensuring nodes cannot interfere
+with each other.
+
+Many of the wrappers have the same signature as the methods they wrap. This allows us to write
+user-facing docstrings and not need to go and update the internal services to match.
+
+Note: The docstrings are in weird places, but that's where they must be to get IDEs to see them.
+"""
+
+
+@dataclass
+class InvocationContextData:
+    invocation: "BaseInvocation"
+    """The invocation that is being executed."""
+    session_id: str
+    """The session that is being executed."""
+    queue_id: str
+    """The queue in which the session is being executed."""
+    source_node_id: str
+    """The ID of the node from which the currently executing invocation was prepared."""
+    queue_item_id: int
+    """The ID of the queue item that is being executed."""
+    batch_id: str
+    """The ID of the batch that is being executed."""
+    workflow: Optional[WorkflowWithoutID] = None
+    """The workflow associated with this queue item, if any."""
+
+
+class InvocationContextInterface:
+    def __init__(self, services: InvocationServices, context_data: InvocationContextData) -> None:
+        self._services = services
+        self._context_data = context_data
+
+
+class BoardsInterface(InvocationContextInterface):
+    def create(self, board_name: str) -> BoardDTO:
+        """
+        Creates a board.
+
+        :param board_name: The name of the board to create.
+        """
+        return self._services.boards.create(board_name)
+
+    def get_dto(self, board_id: str) -> BoardDTO:
+        """
+        Gets a board DTO.
+
+        :param board_id: The ID of the board to get.
+        """
+        return self._services.boards.get_dto(board_id)
+
+    def get_all(self) -> list[BoardDTO]:
+        """
+        Gets all boards.
+        """
+        return self._services.boards.get_all()
+
+    def add_image_to_board(self, board_id: str, image_name: str) -> None:
+        """
+        Adds an image to a board.
+
+        :param board_id: The ID of the board to add the image to.
+        :param image_name: The name of the image to add to the board.
+        """
+        return self._services.board_images.add_image_to_board(board_id, image_name)
+
+    def get_all_image_names_for_board(self, board_id: str) -> list[str]:
+        """
+        Gets all image names for a board.
+
+        :param board_id: The ID of the board to get the image names for.
+        """
+        return self._services.board_images.get_all_board_image_names_for_board(board_id)
+
+
+class LoggerInterface(InvocationContextInterface):
+    def debug(self, message: str) -> None:
+        """
+        Logs a debug message.
+
+        :param message: The message to log.
+        """
+        self._services.logger.debug(message)
+
+    def info(self, message: str) -> None:
+        """
+        Logs an info message.
+
+        :param message: The message to log.
+        """
+        self._services.logger.info(message)
+
+    def warning(self, message: str) -> None:
+        """
+        Logs a warning message.
+
+        :param message: The message to log.
+        """
+        self._services.logger.warning(message)
+
+    def error(self, message: str) -> None:
+        """
+        Logs an error message.
+
+        :param message: The message to log.
+        """
+        self._services.logger.error(message)
+
+
+class ImagesInterface(InvocationContextInterface):
+    def save(
+        self,
+        image: Image,
+        board_id: Optional[str] = None,
+        image_category: ImageCategory = ImageCategory.GENERAL,
+        metadata: Optional[MetadataField] = None,
+    ) -> ImageDTO:
+        """
+        Saves an image, returning its DTO.
+
+        If the current queue item has a workflow or metadata, it is automatically saved with the image.
+
+        :param image: The image to save, as a PIL image.
+        :param board_id: The board ID to add the image to, if it should be added. It the invocation \
+            inherits from `WithBoard`, that board will be used automatically. **Use this only if \
+            you want to override or provide a board manually!**
+        :param image_category: The category of the image. Only the GENERAL category is added \
+            to the gallery.
+        :param metadata: The metadata to save with the image, if it should have any. If the \
+            invocation inherits from `WithMetadata`, that metadata will be used automatically. \
+            **Use this only if you want to override or provide metadata manually!**
+        """
+
+        # If `metadata` is provided directly, use that. Else, use the metadata provided by `WithMetadata`, falling back to None.
+        metadata_ = None
+        if metadata:
+            metadata_ = metadata
+        elif isinstance(self._context_data.invocation, WithMetadata):
+            metadata_ = self._context_data.invocation.metadata
+
+        # If `board_id` is provided directly, use that. Else, use the board provided by `WithBoard`, falling back to None.
+        board_id_ = None
+        if board_id:
+            board_id_ = board_id
+        elif isinstance(self._context_data.invocation, WithBoard) and self._context_data.invocation.board:
+            board_id_ = self._context_data.invocation.board.board_id
+
+        return self._services.images.create(
+            image=image,
+            is_intermediate=self._context_data.invocation.is_intermediate,
+            image_category=image_category,
+            board_id=board_id_,
+            metadata=metadata_,
+            image_origin=ResourceOrigin.INTERNAL,
+            workflow=self._context_data.workflow,
+            session_id=self._context_data.session_id,
+            node_id=self._context_data.invocation.id,
+        )
+
+    def get_pil(self, image_name: str) -> Image:
+        """
+        Gets an image as a PIL Image object.
+
+        :param image_name: The name of the image to get.
+        """
+        return self._services.images.get_pil_image(image_name)
+
+    def get_metadata(self, image_name: str) -> Optional[MetadataField]:
+        """
+        Gets an image's metadata, if it has any.
+
+        :param image_name: The name of the image to get the metadata for.
+        """
+        return self._services.images.get_metadata(image_name)
+
+    def get_dto(self, image_name: str) -> ImageDTO:
+        """
+        Gets an image as an ImageDTO object.
+
+        :param image_name: The name of the image to get.
+        """
+        return self._services.images.get_dto(image_name)
+
+
+class TensorsInterface(InvocationContextInterface):
+    def save(self, tensor: Tensor) -> str:
+        """
+        Saves a tensor, returning its name.
+
+        :param tensor: The tensor to save.
+        """
+
+        name = self._services.tensors.save(obj=tensor)
+        return name
+
+    def load(self, name: str) -> Tensor:
+        """
+        Loads a tensor by name.
+
+        :param name: The name of the tensor to load.
+        """
+        return self._services.tensors.load(name)
+
+
+class ConditioningInterface(InvocationContextInterface):
+    def save(self, conditioning_data: ConditioningFieldData) -> str:
+        """
+        Saves a conditioning data object, returning its name.
+
+        :param conditioning_context_data: The conditioning data to save.
+        """
+
+        name = self._services.conditioning.save(obj=conditioning_data)
+        return name
+
+    def load(self, name: str) -> ConditioningFieldData:
+        """
+        Loads conditioning data by name.
+
+        :param name: The name of the conditioning data to load.
+        """
+
+        return self._services.conditioning.load(name)
+
+
+class ModelsInterface(InvocationContextInterface):
+    def exists(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> bool:
+        """
+        Checks if a model exists.
+
+        :param model_name: The name of the model to check.
+        :param base_model: The base model of the model to check.
+        :param model_type: The type of the model to check.
+        """
+        return self._services.model_manager.model_exists(model_name, base_model, model_type)
+
+    def load(
+        self, model_name: str, base_model: BaseModelType, model_type: ModelType, submodel: Optional[SubModelType] = None
+    ) -> LoadedModelInfo:
+        """
+        Loads a model.
+
+        :param model_name: The name of the model to get.
+        :param base_model: The base model of the model to get.
+        :param model_type: The type of the model to get.
+        :param submodel: The submodel of the model to get.
+        :returns: An object representing the loaded model.
+        """
+
+        # The model manager emits events as it loads the model. It needs the context data to build
+        # the event payloads.
+
+        return self._services.model_manager.get_model(
+            model_name, base_model, model_type, submodel, context_data=self._context_data
+        )
+
+    def get_info(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> dict:
+        """
+        Gets a model's info, an dict-like object.
+
+        :param model_name: The name of the model to get.
+        :param base_model: The base model of the model to get.
+        :param model_type: The type of the model to get.
+        """
+        return self._services.model_manager.model_info(model_name, base_model, model_type)
+
+
+class ConfigInterface(InvocationContextInterface):
+    def get(self) -> InvokeAIAppConfig:
+        """Gets the app's config."""
+
+        return self._services.configuration.get_config()
+
+
+class UtilInterface(InvocationContextInterface):
+    def sd_step_callback(self, intermediate_state: PipelineIntermediateState, base_model: BaseModelType) -> None:
+        """
+        The step callback emits a progress event with the current step, the total number of
+        steps, a preview image, and some other internal metadata.
+
+        This should be called after each denoising step.
+
+        :param intermediate_state: The intermediate state of the diffusion pipeline.
+        :param base_model: The base model for the current denoising step.
+        """
+
+        # The step callback needs access to the events and the invocation queue services, but this
+        # represents a dangerous level of access.
+        #
+        # We wrap the step callback so that nodes do not have direct access to these services.
+
+        stable_diffusion_step_callback(
+            context_data=self._context_data,
+            intermediate_state=intermediate_state,
+            base_model=base_model,
+            invocation_queue=self._services.queue,
+            events=self._services.events,
+        )
+
+
+class InvocationContext:
+    """
+    The `InvocationContext` provides access to various services and data for the current invocation.
+    """
+
+    def __init__(
+        self,
+        images: ImagesInterface,
+        tensors: TensorsInterface,
+        conditioning: ConditioningInterface,
+        models: ModelsInterface,
+        logger: LoggerInterface,
+        config: ConfigInterface,
+        util: UtilInterface,
+        boards: BoardsInterface,
+        context_data: InvocationContextData,
+        services: InvocationServices,
+    ) -> None:
+        self.images = images
+        """Provides methods to save, get and update images and their metadata."""
+        self.tensors = tensors
+        """Provides methods to save and get tensors, including image, noise, masks, and masked images."""
+        self.conditioning = conditioning
+        """Provides methods to save and get conditioning data."""
+        self.models = models
+        """Provides methods to check if a model exists, get a model, and get a model's info."""
+        self.logger = logger
+        """Provides access to the app logger."""
+        self.config = config
+        """Provides access to the app's config."""
+        self.util = util
+        """Provides utility methods."""
+        self.boards = boards
+        """Provides methods to interact with boards."""
+        self._data = context_data
+        """Provides data about the current queue item and invocation. This is an internal API and may change without warning."""
+        self._services = services
+        """Provides access to the full application services. This is an internal API and may change without warning."""
+
+
+def build_invocation_context(
+    services: InvocationServices,
+    context_data: InvocationContextData,
+) -> InvocationContext:
+    """
+    Builds the invocation context for a specific invocation execution.
+
+    :param invocation_services: The invocation services to wrap.
+    :param invocation_context_data: The invocation context data.
+    """
+
+    logger = LoggerInterface(services=services, context_data=context_data)
+    images = ImagesInterface(services=services, context_data=context_data)
+    tensors = TensorsInterface(services=services, context_data=context_data)
+    models = ModelsInterface(services=services, context_data=context_data)
+    config = ConfigInterface(services=services, context_data=context_data)
+    util = UtilInterface(services=services, context_data=context_data)
+    conditioning = ConditioningInterface(services=services, context_data=context_data)
+    boards = BoardsInterface(services=services, context_data=context_data)
+
+    ctx = InvocationContext(
+        images=images,
+        logger=logger,
+        config=config,
+        tensors=tensors,
+        models=models,
+        context_data=context_data,
+        util=util,
+        conditioning=conditioning,
+        services=services,
+        boards=boards,
+    )
+
+    return ctx

invokeai/app/shared/fields.py

@@ -1,67 +0,0 @@
-class FieldDescriptions:
-    denoising_start = "When to start denoising, expressed a percentage of total steps"
-    denoising_end = "When to stop denoising, expressed a percentage of total steps"
-    cfg_scale = "Classifier-Free Guidance scale"
-    cfg_rescale_multiplier = "Rescale multiplier for CFG guidance, used for models trained with zero-terminal SNR"
-    scheduler = "Scheduler to use during inference"
-    positive_cond = "Positive conditioning tensor"
-    negative_cond = "Negative conditioning tensor"
-    noise = "Noise tensor"
-    clip = "CLIP (tokenizer, text encoder, LoRAs) and skipped layer count"
-    unet = "UNet (scheduler, LoRAs)"
-    vae = "VAE"
-    cond = "Conditioning tensor"
-    controlnet_model = "ControlNet model to load"
-    vae_model = "VAE model to load"
-    lora_model = "LoRA model to load"
-    main_model = "Main model (UNet, VAE, CLIP) to load"
-    sdxl_main_model = "SDXL Main model (UNet, VAE, CLIP1, CLIP2) to load"
-    sdxl_refiner_model = "SDXL Refiner Main Modde (UNet, VAE, CLIP2) to load"
-    onnx_main_model = "ONNX Main model (UNet, VAE, CLIP) to load"
-    lora_weight = "The weight at which the LoRA is applied to each model"
-    compel_prompt = "Prompt to be parsed by Compel to create a conditioning tensor"
-    raw_prompt = "Raw prompt text (no parsing)"
-    sdxl_aesthetic = "The aesthetic score to apply to the conditioning tensor"
-    skipped_layers = "Number of layers to skip in text encoder"
-    seed = "Seed for random number generation"
-    steps = "Number of steps to run"
-    width = "Width of output (px)"
-    height = "Height of output (px)"
-    control = "ControlNet(s) to apply"
-    ip_adapter = "IP-Adapter to apply"
-    t2i_adapter = "T2I-Adapter(s) to apply"
-    denoised_latents = "Denoised latents tensor"
-    latents = "Latents tensor"
-    strength = "Strength of denoising (proportional to steps)"
-    metadata = "Optional metadata to be saved with the image"
-    metadata_collection = "Collection of Metadata"
-    metadata_item_polymorphic = "A single metadata item or collection of metadata items"
-    metadata_item_label = "Label for this metadata item"
-    metadata_item_value = "The value for this metadata item (may be any type)"
-    workflow = "Optional workflow to be saved with the image"
-    interp_mode = "Interpolation mode"
-    torch_antialias = "Whether or not to apply antialiasing (bilinear or bicubic only)"
-    fp32 = "Whether or not to use full float32 precision"
-    precision = "Precision to use"
-    tiled = "Processing using overlapping tiles (reduce memory consumption)"
-    detect_res = "Pixel resolution for detection"
-    image_res = "Pixel resolution for output image"
-    safe_mode = "Whether or not to use safe mode"
-    scribble_mode = "Whether or not to use scribble mode"
-    scale_factor = "The factor by which to scale"
-    blend_alpha = (
-        "Blending factor. 0.0 = use input A only, 1.0 = use input B only, 0.5 = 50% mix of input A and input B."
-    )
-    num_1 = "The first number"
-    num_2 = "The second number"
-    mask = "The mask to use for the operation"
-    board = "The board to save the image to"
-    image = "The image to process"
-    tile_size = "Tile size"
-    inclusive_low = "The inclusive low value"
-    exclusive_high = "The exclusive high value"
-    decimal_places = "The number of decimal places to round to"
-    freeu_s1 = 'Scaling factor for stage 1 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
-    freeu_s2 = 'Scaling factor for stage 2 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
-    freeu_b1 = "Scaling factor for stage 1 to amplify the contributions of backbone features."
-    freeu_b2 = "Scaling factor for stage 2 to amplify the contributions of backbone features."

invokeai/app/shared/models.py

@@ -1,6 +1,6 @@
 from pydantic import BaseModel, Field
 
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.fields import FieldDescriptions
 
 
 class FreeUConfig(BaseModel):

invokeai/app/util/step_callback.py

@@ -1,3 +1,5 @@
+from typing import TYPE_CHECKING
+
 import torch
 from PIL import Image
 
@@ -6,7 +8,11 @@ from invokeai.app.services.invocation_processor.invocation_processor_common impo
 from ...backend.model_management.models import BaseModelType
 from ...backend.stable_diffusion import PipelineIntermediateState
 from ...backend.util.util import image_to_dataURL
-from ..invocations.baseinvocation import InvocationContext
+
+if TYPE_CHECKING:
+    from invokeai.app.services.events.events_base import EventServiceBase
+    from invokeai.app.services.invocation_queue.invocation_queue_base import InvocationQueueABC
+    from invokeai.app.services.shared.invocation_context import InvocationContextData
 
 
 def sample_to_lowres_estimated_image(samples, latent_rgb_factors, smooth_matrix=None):
@@ -25,13 +31,13 @@ def sample_to_lowres_estimated_image(samples, latent_rgb_factors, smooth_matrix=
 
 
 def stable_diffusion_step_callback(
-    context: InvocationContext,
+    context_data: "InvocationContextData",
     intermediate_state: PipelineIntermediateState,
-    node: dict,
-    source_node_id: str,
     base_model: BaseModelType,
-):
-    if context.services.queue.is_canceled(context.graph_execution_state_id):
+    invocation_queue: "InvocationQueueABC",
+    events: "EventServiceBase",
+) -> None:
+    if invocation_queue.is_canceled(context_data.session_id):
         raise CanceledException
 
     # Some schedulers report not only the noisy latents at the current timestep,
@@ -108,13 +114,13 @@ def stable_diffusion_step_callback(
 
     dataURL = image_to_dataURL(image, image_format="JPEG")
 
-    context.services.events.emit_generator_progress(
-        queue_id=context.queue_id,
-        queue_item_id=context.queue_item_id,
-        queue_batch_id=context.queue_batch_id,
-        graph_execution_state_id=context.graph_execution_state_id,
-        node=node,
-        source_node_id=source_node_id,
+    events.emit_generator_progress(
+        queue_id=context_data.queue_id,
+        queue_item_id=context_data.queue_item_id,
+        queue_batch_id=context_data.batch_id,
+        graph_execution_state_id=context_data.session_id,
+        node_id=context_data.invocation.id,
+        source_node_id=context_data.source_node_id,
         progress_image=ProgressImage(width=width, height=height, dataURL=dataURL),
         step=intermediate_state.step,
         order=intermediate_state.order,

invokeai/backend/__init__.py

@@ -1,5 +1,12 @@
 """
 Initialization file for invokeai.backend
 """
-from .model_management import BaseModelType, ModelCache, ModelInfo, ModelManager, ModelType, SubModelType  # noqa: F401
+from .model_management import (  # noqa: F401
+    BaseModelType,
+    LoadedModelInfo,
+    ModelCache,
+    ModelManager,
+    ModelType,
+    SubModelType,
+)
 from .model_management.models import SilenceWarnings  # noqa: F401

invokeai/backend/image_util/basicsr/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2018-2022 BasicSR Authors
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

invokeai/backend/image_util/basicsr/__init__.py

@@ -0,0 +1,18 @@
+"""
+Adapted from https://github.com/XPixelGroup/BasicSR
+License: Apache-2.0
+
+As of Feb 2024, `basicsr` appears to be unmaintained. It imports a function from `torchvision` that is removed in
+`torchvision` 0.17. Here is the deprecation warning:
+
+    UserWarning: The torchvision.transforms.functional_tensor module is deprecated in 0.15 and will be **removed in
+    0.17**. Please don't rely on it. You probably just need to use APIs in torchvision.transforms.functional or in
+    torchvision.transforms.v2.functional.
+
+As a result, a dependency on `basicsr` means we cannot keep our `torchvision` dependency up to date.
+
+Because we only rely on a single class `RRDBNet` from `basicsr`, we've copied the relevant code here and removed the
+dependency on `basicsr`.
+
+The code is almost unchanged, only a few type annotations have been added. The license is also copied.
+"""

invokeai/backend/image_util/basicsr/arch_util.py

@@ -0,0 +1,75 @@
+from typing import Type
+
+import torch
+from torch import nn as nn
+from torch.nn import init as init
+from torch.nn.modules.batchnorm import _BatchNorm
+
+
+@torch.no_grad()
+def default_init_weights(
+    module_list: list[nn.Module] | nn.Module, scale: float = 1, bias_fill: float = 0, **kwargs
+) -> None:
+    """Initialize network weights.
+
+    Args:
+        module_list (list[nn.Module] | nn.Module): Modules to be initialized.
+        scale (float): Scale initialized weights, especially for residual
+            blocks. Default: 1.
+        bias_fill (float): The value to fill bias. Default: 0
+        kwargs (dict): Other arguments for initialization function.
+    """
+    if not isinstance(module_list, list):
+        module_list = [module_list]
+    for module in module_list:
+        for m in module.modules():
+            if isinstance(m, nn.Conv2d):
+                init.kaiming_normal_(m.weight, **kwargs)
+                m.weight.data *= scale
+                if m.bias is not None:
+                    m.bias.data.fill_(bias_fill)
+            elif isinstance(m, nn.Linear):
+                init.kaiming_normal_(m.weight, **kwargs)
+                m.weight.data *= scale
+                if m.bias is not None:
+                    m.bias.data.fill_(bias_fill)
+            elif isinstance(m, _BatchNorm):
+                init.constant_(m.weight, 1)
+                if m.bias is not None:
+                    m.bias.data.fill_(bias_fill)
+
+
+def make_layer(basic_block: Type[nn.Module], num_basic_block: int, **kwarg) -> nn.Sequential:
+    """Make layers by stacking the same blocks.
+
+    Args:
+        basic_block (Type[nn.Module]): nn.Module class for basic block.
+        num_basic_block (int): number of blocks.
+
+    Returns:
+        nn.Sequential: Stacked blocks in nn.Sequential.
+    """
+    layers = []
+    for _ in range(num_basic_block):
+        layers.append(basic_block(**kwarg))
+    return nn.Sequential(*layers)
+
+
+# TODO: may write a cpp file
+def pixel_unshuffle(x: torch.Tensor, scale: int) -> torch.Tensor:
+    """Pixel unshuffle.
+
+    Args:
+        x (Tensor): Input feature with shape (b, c, hh, hw).
+        scale (int): Downsample ratio.
+
+    Returns:
+        Tensor: the pixel unshuffled feature.
+    """
+    b, c, hh, hw = x.size()
+    out_channel = c * (scale**2)
+    assert hh % scale == 0 and hw % scale == 0
+    h = hh // scale
+    w = hw // scale
+    x_view = x.view(b, c, h, scale, w, scale)
+    return x_view.permute(0, 1, 3, 5, 2, 4).reshape(b, out_channel, h, w)

invokeai/backend/image_util/basicsr/rrdbnet_arch.py

@@ -0,0 +1,125 @@
+import torch
+from torch import nn as nn
+from torch.nn import functional as F
+
+from .arch_util import default_init_weights, make_layer, pixel_unshuffle
+
+
+class ResidualDenseBlock(nn.Module):
+    """Residual Dense Block.
+
+    Used in RRDB block in ESRGAN.
+
+    Args:
+        num_feat (int): Channel number of intermediate features.
+        num_grow_ch (int): Channels for each growth.
+    """
+
+    def __init__(self, num_feat: int = 64, num_grow_ch: int = 32) -> None:
+        super(ResidualDenseBlock, self).__init__()
+        self.conv1 = nn.Conv2d(num_feat, num_grow_ch, 3, 1, 1)
+        self.conv2 = nn.Conv2d(num_feat + num_grow_ch, num_grow_ch, 3, 1, 1)
+        self.conv3 = nn.Conv2d(num_feat + 2 * num_grow_ch, num_grow_ch, 3, 1, 1)
+        self.conv4 = nn.Conv2d(num_feat + 3 * num_grow_ch, num_grow_ch, 3, 1, 1)
+        self.conv5 = nn.Conv2d(num_feat + 4 * num_grow_ch, num_feat, 3, 1, 1)
+
+        self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
+
+        # initialization
+        default_init_weights([self.conv1, self.conv2, self.conv3, self.conv4, self.conv5], 0.1)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        x1 = self.lrelu(self.conv1(x))
+        x2 = self.lrelu(self.conv2(torch.cat((x, x1), 1)))
+        x3 = self.lrelu(self.conv3(torch.cat((x, x1, x2), 1)))
+        x4 = self.lrelu(self.conv4(torch.cat((x, x1, x2, x3), 1)))
+        x5 = self.conv5(torch.cat((x, x1, x2, x3, x4), 1))
+        # Empirically, we use 0.2 to scale the residual for better performance
+        return x5 * 0.2 + x
+
+
+class RRDB(nn.Module):
+    """Residual in Residual Dense Block.
+
+    Used in RRDB-Net in ESRGAN.
+
+    Args:
+        num_feat (int): Channel number of intermediate features.
+        num_grow_ch (int): Channels for each growth.
+    """
+
+    def __init__(self, num_feat: int, num_grow_ch: int = 32) -> None:
+        super(RRDB, self).__init__()
+        self.rdb1 = ResidualDenseBlock(num_feat, num_grow_ch)
+        self.rdb2 = ResidualDenseBlock(num_feat, num_grow_ch)
+        self.rdb3 = ResidualDenseBlock(num_feat, num_grow_ch)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        out = self.rdb1(x)
+        out = self.rdb2(out)
+        out = self.rdb3(out)
+        # Empirically, we use 0.2 to scale the residual for better performance
+        return out * 0.2 + x
+
+
+class RRDBNet(nn.Module):
+    """Networks consisting of Residual in Residual Dense Block, which is used
+    in ESRGAN.
+
+    ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks.
+
+    We extend ESRGAN for scale x2 and scale x1.
+    Note: This is one option for scale 1, scale 2 in RRDBNet.
+    We first employ the pixel-unshuffle (an inverse operation of pixelshuffle to reduce the spatial size
+    and enlarge the channel size before feeding inputs into the main ESRGAN architecture.
+
+    Args:
+        num_in_ch (int): Channel number of inputs.
+        num_out_ch (int): Channel number of outputs.
+        num_feat (int): Channel number of intermediate features.
+            Default: 64
+        num_block (int): Block number in the trunk network. Defaults: 23
+        num_grow_ch (int): Channels for each growth. Default: 32.
+    """
+
+    def __init__(
+        self,
+        num_in_ch: int,
+        num_out_ch: int,
+        scale: int = 4,
+        num_feat: int = 64,
+        num_block: int = 23,
+        num_grow_ch: int = 32,
+    ) -> None:
+        super(RRDBNet, self).__init__()
+        self.scale = scale
+        if scale == 2:
+            num_in_ch = num_in_ch * 4
+        elif scale == 1:
+            num_in_ch = num_in_ch * 16
+        self.conv_first = nn.Conv2d(num_in_ch, num_feat, 3, 1, 1)
+        self.body = make_layer(RRDB, num_block, num_feat=num_feat, num_grow_ch=num_grow_ch)
+        self.conv_body = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
+        # upsample
+        self.conv_up1 = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
+        self.conv_up2 = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
+        self.conv_hr = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
+        self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
+
+        self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        if self.scale == 2:
+            feat = pixel_unshuffle(x, scale=2)
+        elif self.scale == 1:
+            feat = pixel_unshuffle(x, scale=4)
+        else:
+            feat = x
+        feat = self.conv_first(feat)
+        body_feat = self.conv_body(self.body(feat))
+        feat = feat + body_feat
+        # upsample
+        feat = self.lrelu(self.conv_up1(F.interpolate(feat, scale_factor=2, mode="nearest")))
+        feat = self.lrelu(self.conv_up2(F.interpolate(feat, scale_factor=2, mode="nearest")))
+        out = self.conv_last(self.lrelu(self.conv_hr(feat)))
+        return out

invokeai/backend/image_util/dw_openpose/__init__.py

@@ -0,0 +1,81 @@
+import numpy as np
+import torch
+from controlnet_aux.util import resize_image
+from PIL import Image
+
+from invokeai.backend.image_util.dw_openpose.utils import draw_bodypose, draw_facepose, draw_handpose
+from invokeai.backend.image_util.dw_openpose.wholebody import Wholebody
+
+
+def draw_pose(pose, H, W, draw_face=True, draw_body=True, draw_hands=True, resolution=512):
+    bodies = pose["bodies"]
+    faces = pose["faces"]
+    hands = pose["hands"]
+    candidate = bodies["candidate"]
+    subset = bodies["subset"]
+    canvas = np.zeros(shape=(H, W, 3), dtype=np.uint8)
+
+    if draw_body:
+        canvas = draw_bodypose(canvas, candidate, subset)
+
+    if draw_hands:
+        canvas = draw_handpose(canvas, hands)
+
+    if draw_face:
+        canvas = draw_facepose(canvas, faces)
+
+    dwpose_image = resize_image(
+        canvas,
+        resolution,
+    )
+    dwpose_image = Image.fromarray(dwpose_image)
+
+    return dwpose_image
+
+
+class DWOpenposeDetector:
+    """
+    Code from the original implementation of the DW Openpose Detector.
+    Credits: https://github.com/IDEA-Research/DWPose
+    """
+
+    def __init__(self) -> None:
+        self.pose_estimation = Wholebody()
+
+    def __call__(
+        self, image: Image.Image, draw_face=False, draw_body=True, draw_hands=False, resolution=512
+    ) -> Image.Image:
+        np_image = np.array(image)
+        H, W, C = np_image.shape
+
+        with torch.no_grad():
+            candidate, subset = self.pose_estimation(np_image)
+            nums, keys, locs = candidate.shape
+            candidate[..., 0] /= float(W)
+            candidate[..., 1] /= float(H)
+            body = candidate[:, :18].copy()
+            body = body.reshape(nums * 18, locs)
+            score = subset[:, :18]
+            for i in range(len(score)):
+                for j in range(len(score[i])):
+                    if score[i][j] > 0.3:
+                        score[i][j] = int(18 * i + j)
+                    else:
+                        score[i][j] = -1
+
+            un_visible = subset < 0.3
+            candidate[un_visible] = -1
+
+            # foot = candidate[:, 18:24]
+
+            faces = candidate[:, 24:92]
+
+            hands = candidate[:, 92:113]
+            hands = np.vstack([hands, candidate[:, 113:]])
+
+            bodies = {"candidate": body, "subset": score}
+            pose = {"bodies": bodies, "hands": hands, "faces": faces}
+
+            return draw_pose(
+                pose, H, W, draw_face=draw_face, draw_hands=draw_hands, draw_body=draw_body, resolution=resolution
+            )

invokeai/backend/image_util/dw_openpose/onnxdet.py

@@ -0,0 +1,128 @@
+# Code from the original DWPose Implementation: https://github.com/IDEA-Research/DWPose
+
+import cv2
+import numpy as np
+
+
+def nms(boxes, scores, nms_thr):
+    """Single class NMS implemented in Numpy."""
+    x1 = boxes[:, 0]
+    y1 = boxes[:, 1]
+    x2 = boxes[:, 2]
+    y2 = boxes[:, 3]
+
+    areas = (x2 - x1 + 1) * (y2 - y1 + 1)
+    order = scores.argsort()[::-1]
+
+    keep = []
+    while order.size > 0:
+        i = order[0]
+        keep.append(i)
+        xx1 = np.maximum(x1[i], x1[order[1:]])
+        yy1 = np.maximum(y1[i], y1[order[1:]])
+        xx2 = np.minimum(x2[i], x2[order[1:]])
+        yy2 = np.minimum(y2[i], y2[order[1:]])
+
+        w = np.maximum(0.0, xx2 - xx1 + 1)
+        h = np.maximum(0.0, yy2 - yy1 + 1)
+        inter = w * h
+        ovr = inter / (areas[i] + areas[order[1:]] - inter)
+
+        inds = np.where(ovr <= nms_thr)[0]
+        order = order[inds + 1]
+
+    return keep
+
+
+def multiclass_nms(boxes, scores, nms_thr, score_thr):
+    """Multiclass NMS implemented in Numpy. Class-aware version."""
+    final_dets = []
+    num_classes = scores.shape[1]
+    for cls_ind in range(num_classes):
+        cls_scores = scores[:, cls_ind]
+        valid_score_mask = cls_scores > score_thr
+        if valid_score_mask.sum() == 0:
+            continue
+        else:
+            valid_scores = cls_scores[valid_score_mask]
+            valid_boxes = boxes[valid_score_mask]
+            keep = nms(valid_boxes, valid_scores, nms_thr)
+            if len(keep) > 0:
+                cls_inds = np.ones((len(keep), 1)) * cls_ind
+                dets = np.concatenate([valid_boxes[keep], valid_scores[keep, None], cls_inds], 1)
+                final_dets.append(dets)
+    if len(final_dets) == 0:
+        return None
+    return np.concatenate(final_dets, 0)
+
+
+def demo_postprocess(outputs, img_size, p6=False):
+    grids = []
+    expanded_strides = []
+    strides = [8, 16, 32] if not p6 else [8, 16, 32, 64]
+
+    hsizes = [img_size[0] // stride for stride in strides]
+    wsizes = [img_size[1] // stride for stride in strides]
+
+    for hsize, wsize, stride in zip(hsizes, wsizes, strides, strict=False):
+        xv, yv = np.meshgrid(np.arange(wsize), np.arange(hsize))
+        grid = np.stack((xv, yv), 2).reshape(1, -1, 2)
+        grids.append(grid)
+        shape = grid.shape[:2]
+        expanded_strides.append(np.full((*shape, 1), stride))
+
+    grids = np.concatenate(grids, 1)
+    expanded_strides = np.concatenate(expanded_strides, 1)
+    outputs[..., :2] = (outputs[..., :2] + grids) * expanded_strides
+    outputs[..., 2:4] = np.exp(outputs[..., 2:4]) * expanded_strides
+
+    return outputs
+
+
+def preprocess(img, input_size, swap=(2, 0, 1)):
+    if len(img.shape) == 3:
+        padded_img = np.ones((input_size[0], input_size[1], 3), dtype=np.uint8) * 114
+    else:
+        padded_img = np.ones(input_size, dtype=np.uint8) * 114
+
+    r = min(input_size[0] / img.shape[0], input_size[1] / img.shape[1])
+    resized_img = cv2.resize(
+        img,
+        (int(img.shape[1] * r), int(img.shape[0] * r)),
+        interpolation=cv2.INTER_LINEAR,
+    ).astype(np.uint8)
+    padded_img[: int(img.shape[0] * r), : int(img.shape[1] * r)] = resized_img
+
+    padded_img = padded_img.transpose(swap)
+    padded_img = np.ascontiguousarray(padded_img, dtype=np.float32)
+    return padded_img, r
+
+
+def inference_detector(session, oriImg):
+    input_shape = (640, 640)
+    img, ratio = preprocess(oriImg, input_shape)
+
+    ort_inputs = {session.get_inputs()[0].name: img[None, :, :, :]}
+    output = session.run(None, ort_inputs)
+    predictions = demo_postprocess(output[0], input_shape)[0]
+
+    boxes = predictions[:, :4]
+    scores = predictions[:, 4:5] * predictions[:, 5:]
+
+    boxes_xyxy = np.ones_like(boxes)
+    boxes_xyxy[:, 0] = boxes[:, 0] - boxes[:, 2] / 2.0
+    boxes_xyxy[:, 1] = boxes[:, 1] - boxes[:, 3] / 2.0
+    boxes_xyxy[:, 2] = boxes[:, 0] + boxes[:, 2] / 2.0
+    boxes_xyxy[:, 3] = boxes[:, 1] + boxes[:, 3] / 2.0
+    boxes_xyxy /= ratio
+    dets = multiclass_nms(boxes_xyxy, scores, nms_thr=0.45, score_thr=0.1)
+    if dets is not None:
+        final_boxes, final_scores, final_cls_inds = dets[:, :4], dets[:, 4], dets[:, 5]
+        isscore = final_scores > 0.3
+        iscat = final_cls_inds == 0
+        isbbox = [i and j for (i, j) in zip(isscore, iscat, strict=False)]
+        final_boxes = final_boxes[isbbox]
+    else:
+        final_boxes = np.array([])
+
+    return final_boxes

invokeai/backend/image_util/dw_openpose/onnxpose.py

@@ -0,0 +1,361 @@
+# Code from the original DWPose Implementation: https://github.com/IDEA-Research/DWPose
+
+from typing import List, Tuple
+
+import cv2
+import numpy as np
+import onnxruntime as ort
+
+
+def preprocess(
+    img: np.ndarray, out_bbox, input_size: Tuple[int, int] = (192, 256)
+) -> Tuple[np.ndarray, np.ndarray, np.ndarray]:
+    """Do preprocessing for RTMPose model inference.
+
+    Args:
+        img (np.ndarray): Input image in shape.
+        input_size (tuple): Input image size in shape (w, h).
+
+    Returns:
+        tuple:
+        - resized_img (np.ndarray): Preprocessed image.
+        - center (np.ndarray): Center of image.
+        - scale (np.ndarray): Scale of image.
+    """
+    # get shape of image
+    img_shape = img.shape[:2]
+    out_img, out_center, out_scale = [], [], []
+    if len(out_bbox) == 0:
+        out_bbox = [[0, 0, img_shape[1], img_shape[0]]]
+    for i in range(len(out_bbox)):
+        x0 = out_bbox[i][0]
+        y0 = out_bbox[i][1]
+        x1 = out_bbox[i][2]
+        y1 = out_bbox[i][3]
+        bbox = np.array([x0, y0, x1, y1])
+
+        # get center and scale
+        center, scale = bbox_xyxy2cs(bbox, padding=1.25)
+
+        # do affine transformation
+        resized_img, scale = top_down_affine(input_size, scale, center, img)
+
+        # normalize image
+        mean = np.array([123.675, 116.28, 103.53])
+        std = np.array([58.395, 57.12, 57.375])
+        resized_img = (resized_img - mean) / std
+
+        out_img.append(resized_img)
+        out_center.append(center)
+        out_scale.append(scale)
+
+    return out_img, out_center, out_scale
+
+
+def inference(sess: ort.InferenceSession, img: np.ndarray) -> np.ndarray:
+    """Inference RTMPose model.
+
+    Args:
+        sess (ort.InferenceSession): ONNXRuntime session.
+        img (np.ndarray): Input image in shape.
+
+    Returns:
+        outputs (np.ndarray): Output of RTMPose model.
+    """
+    all_out = []
+    # build input
+    for i in range(len(img)):
+        input = [img[i].transpose(2, 0, 1)]
+
+        # build output
+        sess_input = {sess.get_inputs()[0].name: input}
+        sess_output = []
+        for out in sess.get_outputs():
+            sess_output.append(out.name)
+
+        # run model
+        outputs = sess.run(sess_output, sess_input)
+        all_out.append(outputs)
+
+    return all_out
+
+
+def postprocess(
+    outputs: List[np.ndarray],
+    model_input_size: Tuple[int, int],
+    center: Tuple[int, int],
+    scale: Tuple[int, int],
+    simcc_split_ratio: float = 2.0,
+) -> Tuple[np.ndarray, np.ndarray]:
+    """Postprocess for RTMPose model output.
+
+    Args:
+        outputs (np.ndarray): Output of RTMPose model.
+        model_input_size (tuple): RTMPose model Input image size.
+        center (tuple): Center of bbox in shape (x, y).
+        scale (tuple): Scale of bbox in shape (w, h).
+        simcc_split_ratio (float): Split ratio of simcc.
+
+    Returns:
+        tuple:
+        - keypoints (np.ndarray): Rescaled keypoints.
+        - scores (np.ndarray): Model predict scores.
+    """
+    all_key = []
+    all_score = []
+    for i in range(len(outputs)):
+        # use simcc to decode
+        simcc_x, simcc_y = outputs[i]
+        keypoints, scores = decode(simcc_x, simcc_y, simcc_split_ratio)
+
+        # rescale keypoints
+        keypoints = keypoints / model_input_size * scale[i] + center[i] - scale[i] / 2
+        all_key.append(keypoints[0])
+        all_score.append(scores[0])
+
+    return np.array(all_key), np.array(all_score)
+
+
+def bbox_xyxy2cs(bbox: np.ndarray, padding: float = 1.0) -> Tuple[np.ndarray, np.ndarray]:
+    """Transform the bbox format from (x,y,w,h) into (center, scale)
+
+    Args:
+        bbox (ndarray): Bounding box(es) in shape (4,) or (n, 4), formatted
+            as (left, top, right, bottom)
+        padding (float): BBox padding factor that will be multilied to scale.
+            Default: 1.0
+
+    Returns:
+        tuple: A tuple containing center and scale.
+        - np.ndarray[float32]: Center (x, y) of the bbox in shape (2,) or
+            (n, 2)
+        - np.ndarray[float32]: Scale (w, h) of the bbox in shape (2,) or
+            (n, 2)
+    """
+    # convert single bbox from (4, ) to (1, 4)
+    dim = bbox.ndim
+    if dim == 1:
+        bbox = bbox[None, :]
+
+    # get bbox center and scale
+    x1, y1, x2, y2 = np.hsplit(bbox, [1, 2, 3])
+    center = np.hstack([x1 + x2, y1 + y2]) * 0.5
+    scale = np.hstack([x2 - x1, y2 - y1]) * padding
+
+    if dim == 1:
+        center = center[0]
+        scale = scale[0]
+
+    return center, scale
+
+
+def _fix_aspect_ratio(bbox_scale: np.ndarray, aspect_ratio: float) -> np.ndarray:
+    """Extend the scale to match the given aspect ratio.
+
+    Args:
+        scale (np.ndarray): The image scale (w, h) in shape (2, )
+        aspect_ratio (float): The ratio of ``w/h``
+
+    Returns:
+        np.ndarray: The reshaped image scale in (2, )
+    """
+    w, h = np.hsplit(bbox_scale, [1])
+    bbox_scale = np.where(w > h * aspect_ratio, np.hstack([w, w / aspect_ratio]), np.hstack([h * aspect_ratio, h]))
+    return bbox_scale
+
+
+def _rotate_point(pt: np.ndarray, angle_rad: float) -> np.ndarray:
+    """Rotate a point by an angle.
+
+    Args:
+        pt (np.ndarray): 2D point coordinates (x, y) in shape (2, )
+        angle_rad (float): rotation angle in radian
+
+    Returns:
+        np.ndarray: Rotated point in shape (2, )
+    """
+    sn, cs = np.sin(angle_rad), np.cos(angle_rad)
+    rot_mat = np.array([[cs, -sn], [sn, cs]])
+    return rot_mat @ pt
+
+
+def _get_3rd_point(a: np.ndarray, b: np.ndarray) -> np.ndarray:
+    """To calculate the affine matrix, three pairs of points are required. This
+    function is used to get the 3rd point, given 2D points a & b.
+
+    The 3rd point is defined by rotating vector `a - b` by 90 degrees
+    anticlockwise, using b as the rotation center.
+
+    Args:
+        a (np.ndarray): The 1st point (x,y) in shape (2, )
+        b (np.ndarray): The 2nd point (x,y) in shape (2, )
+
+    Returns:
+        np.ndarray: The 3rd point.
+    """
+    direction = a - b
+    c = b + np.r_[-direction[1], direction[0]]
+    return c
+
+
+def get_warp_matrix(
+    center: np.ndarray,
+    scale: np.ndarray,
+    rot: float,
+    output_size: Tuple[int, int],
+    shift: Tuple[float, float] = (0.0, 0.0),
+    inv: bool = False,
+) -> np.ndarray:
+    """Calculate the affine transformation matrix that can warp the bbox area
+    in the input image to the output size.
+
+    Args:
+        center (np.ndarray[2, ]): Center of the bounding box (x, y).
+        scale (np.ndarray[2, ]): Scale of the bounding box
+            wrt [width, height].
+        rot (float): Rotation angle (degree).
+        output_size (np.ndarray[2, ] | list(2,)): Size of the
+            destination heatmaps.
+        shift (0-100%): Shift translation ratio wrt the width/height.
+            Default (0., 0.).
+        inv (bool): Option to inverse the affine transform direction.
+            (inv=False: src->dst or inv=True: dst->src)
+
+    Returns:
+        np.ndarray: A 2x3 transformation matrix
+    """
+    shift = np.array(shift)
+    src_w = scale[0]
+    dst_w = output_size[0]
+    dst_h = output_size[1]
+
+    # compute transformation matrix
+    rot_rad = np.deg2rad(rot)
+    src_dir = _rotate_point(np.array([0.0, src_w * -0.5]), rot_rad)
+    dst_dir = np.array([0.0, dst_w * -0.5])
+
+    # get four corners of the src rectangle in the original image
+    src = np.zeros((3, 2), dtype=np.float32)
+    src[0, :] = center + scale * shift
+    src[1, :] = center + src_dir + scale * shift
+    src[2, :] = _get_3rd_point(src[0, :], src[1, :])
+
+    # get four corners of the dst rectangle in the input image
+    dst = np.zeros((3, 2), dtype=np.float32)
+    dst[0, :] = [dst_w * 0.5, dst_h * 0.5]
+    dst[1, :] = np.array([dst_w * 0.5, dst_h * 0.5]) + dst_dir
+    dst[2, :] = _get_3rd_point(dst[0, :], dst[1, :])
+
+    if inv:
+        warp_mat = cv2.getAffineTransform(np.float32(dst), np.float32(src))
+    else:
+        warp_mat = cv2.getAffineTransform(np.float32(src), np.float32(dst))
+
+    return warp_mat
+
+
+def top_down_affine(
+    input_size: dict, bbox_scale: dict, bbox_center: dict, img: np.ndarray
+) -> Tuple[np.ndarray, np.ndarray]:
+    """Get the bbox image as the model input by affine transform.
+
+    Args:
+        input_size (dict): The input size of the model.
+        bbox_scale (dict): The bbox scale of the img.
+        bbox_center (dict): The bbox center of the img.
+        img (np.ndarray): The original image.
+
+    Returns:
+        tuple: A tuple containing center and scale.
+        - np.ndarray[float32]: img after affine transform.
+        - np.ndarray[float32]: bbox scale after affine transform.
+    """
+    w, h = input_size
+    warp_size = (int(w), int(h))
+
+    # reshape bbox to fixed aspect ratio
+    bbox_scale = _fix_aspect_ratio(bbox_scale, aspect_ratio=w / h)
+
+    # get the affine matrix
+    center = bbox_center
+    scale = bbox_scale
+    rot = 0
+    warp_mat = get_warp_matrix(center, scale, rot, output_size=(w, h))
+
+    # do affine transform
+    img = cv2.warpAffine(img, warp_mat, warp_size, flags=cv2.INTER_LINEAR)
+
+    return img, bbox_scale
+
+
+def get_simcc_maximum(simcc_x: np.ndarray, simcc_y: np.ndarray) -> Tuple[np.ndarray, np.ndarray]:
+    """Get maximum response location and value from simcc representations.
+
+    Note:
+        instance number: N
+        num_keypoints: K
+        heatmap height: H
+        heatmap width: W
+
+    Args:
+        simcc_x (np.ndarray): x-axis SimCC in shape (K, Wx) or (N, K, Wx)
+        simcc_y (np.ndarray): y-axis SimCC in shape (K, Wy) or (N, K, Wy)
+
+    Returns:
+        tuple:
+        - locs (np.ndarray): locations of maximum heatmap responses in shape
+            (K, 2) or (N, K, 2)
+        - vals (np.ndarray): values of maximum heatmap responses in shape
+            (K,) or (N, K)
+    """
+    N, K, Wx = simcc_x.shape
+    simcc_x = simcc_x.reshape(N * K, -1)
+    simcc_y = simcc_y.reshape(N * K, -1)
+
+    # get maximum value locations
+    x_locs = np.argmax(simcc_x, axis=1)
+    y_locs = np.argmax(simcc_y, axis=1)
+    locs = np.stack((x_locs, y_locs), axis=-1).astype(np.float32)
+    max_val_x = np.amax(simcc_x, axis=1)
+    max_val_y = np.amax(simcc_y, axis=1)
+
+    # get maximum value across x and y axis
+    mask = max_val_x > max_val_y
+    max_val_x[mask] = max_val_y[mask]
+    vals = max_val_x
+    locs[vals <= 0.0] = -1
+
+    # reshape
+    locs = locs.reshape(N, K, 2)
+    vals = vals.reshape(N, K)
+
+    return locs, vals
+
+
+def decode(simcc_x: np.ndarray, simcc_y: np.ndarray, simcc_split_ratio) -> Tuple[np.ndarray, np.ndarray]:
+    """Modulate simcc distribution with Gaussian.
+
+    Args:
+        simcc_x (np.ndarray[K, Wx]): model predicted simcc in x.
+        simcc_y (np.ndarray[K, Wy]): model predicted simcc in y.
+        simcc_split_ratio (int): The split ratio of simcc.
+
+    Returns:
+        tuple: A tuple containing center and scale.
+        - np.ndarray[float32]: keypoints in shape (K, 2) or (n, K, 2)
+        - np.ndarray[float32]: scores in shape (K,) or (n, K)
+    """
+    keypoints, scores = get_simcc_maximum(simcc_x, simcc_y)
+    keypoints /= simcc_split_ratio
+
+    return keypoints, scores
+
+
+def inference_pose(session, out_bbox, oriImg):
+    h, w = session.get_inputs()[0].shape[2:]
+    model_input_size = (w, h)
+    resized_img, center, scale = preprocess(oriImg, out_bbox, model_input_size)
+    outputs = inference(session, resized_img)
+    keypoints, scores = postprocess(outputs, model_input_size, center, scale)
+
+    return keypoints, scores

invokeai/backend/image_util/dw_openpose/utils.py

@@ -0,0 +1,155 @@
+# Code from the original DWPose Implementation: https://github.com/IDEA-Research/DWPose
+
+import math
+
+import cv2
+import matplotlib
+import numpy as np
+
+eps = 0.01
+
+
+def draw_bodypose(canvas, candidate, subset):
+    H, W, C = canvas.shape
+    candidate = np.array(candidate)
+    subset = np.array(subset)
+
+    stickwidth = 4
+
+    limbSeq = [
+        [2, 3],
+        [2, 6],
+        [3, 4],
+        [4, 5],
+        [6, 7],
+        [7, 8],
+        [2, 9],
+        [9, 10],
+        [10, 11],
+        [2, 12],
+        [12, 13],
+        [13, 14],
+        [2, 1],
+        [1, 15],
+        [15, 17],
+        [1, 16],
+        [16, 18],
+        [3, 17],
+        [6, 18],
+    ]
+
+    colors = [
+        [255, 0, 0],
+        [255, 85, 0],
+        [255, 170, 0],
+        [255, 255, 0],
+        [170, 255, 0],
+        [85, 255, 0],
+        [0, 255, 0],
+        [0, 255, 85],
+        [0, 255, 170],
+        [0, 255, 255],
+        [0, 170, 255],
+        [0, 85, 255],
+        [0, 0, 255],
+        [85, 0, 255],
+        [170, 0, 255],
+        [255, 0, 255],
+        [255, 0, 170],
+        [255, 0, 85],
+    ]
+
+    for i in range(17):
+        for n in range(len(subset)):
+            index = subset[n][np.array(limbSeq[i]) - 1]
+            if -1 in index:
+                continue
+            Y = candidate[index.astype(int), 0] * float(W)
+            X = candidate[index.astype(int), 1] * float(H)
+            mX = np.mean(X)
+            mY = np.mean(Y)
+            length = ((X[0] - X[1]) ** 2 + (Y[0] - Y[1]) ** 2) ** 0.5
+            angle = math.degrees(math.atan2(X[0] - X[1], Y[0] - Y[1]))
+            polygon = cv2.ellipse2Poly((int(mY), int(mX)), (int(length / 2), stickwidth), int(angle), 0, 360, 1)
+            cv2.fillConvexPoly(canvas, polygon, colors[i])
+
+    canvas = (canvas * 0.6).astype(np.uint8)
+
+    for i in range(18):
+        for n in range(len(subset)):
+            index = int(subset[n][i])
+            if index == -1:
+                continue
+            x, y = candidate[index][0:2]
+            x = int(x * W)
+            y = int(y * H)
+            cv2.circle(canvas, (int(x), int(y)), 4, colors[i], thickness=-1)
+
+    return canvas
+
+
+def draw_handpose(canvas, all_hand_peaks):
+    H, W, C = canvas.shape
+
+    edges = [
+        [0, 1],
+        [1, 2],
+        [2, 3],
+        [3, 4],
+        [0, 5],
+        [5, 6],
+        [6, 7],
+        [7, 8],
+        [0, 9],
+        [9, 10],
+        [10, 11],
+        [11, 12],
+        [0, 13],
+        [13, 14],
+        [14, 15],
+        [15, 16],
+        [0, 17],
+        [17, 18],
+        [18, 19],
+        [19, 20],
+    ]
+
+    for peaks in all_hand_peaks:
+        peaks = np.array(peaks)
+
+        for ie, e in enumerate(edges):
+            x1, y1 = peaks[e[0]]
+            x2, y2 = peaks[e[1]]
+            x1 = int(x1 * W)
+            y1 = int(y1 * H)
+            x2 = int(x2 * W)
+            y2 = int(y2 * H)
+            if x1 > eps and y1 > eps and x2 > eps and y2 > eps:
+                cv2.line(
+                    canvas,
+                    (x1, y1),
+                    (x2, y2),
+                    matplotlib.colors.hsv_to_rgb([ie / float(len(edges)), 1.0, 1.0]) * 255,
+                    thickness=2,
+                )
+
+        for _, keyponit in enumerate(peaks):
+            x, y = keyponit
+            x = int(x * W)
+            y = int(y * H)
+            if x > eps and y > eps:
+                cv2.circle(canvas, (x, y), 4, (0, 0, 255), thickness=-1)
+    return canvas
+
+
+def draw_facepose(canvas, all_lmks):
+    H, W, C = canvas.shape
+    for lmks in all_lmks:
+        lmks = np.array(lmks)
+        for lmk in lmks:
+            x, y = lmk
+            x = int(x * W)
+            y = int(y * H)
+            if x > eps and y > eps:
+                cv2.circle(canvas, (x, y), 3, (255, 255, 255), thickness=-1)
+    return canvas

invokeai/backend/image_util/dw_openpose/wholebody.py

@@ -0,0 +1,67 @@
+# Code from the original DWPose Implementation: https://github.com/IDEA-Research/DWPose
+# Modified pathing to suit Invoke
+
+import pathlib
+
+import numpy as np
+import onnxruntime as ort
+
+from invokeai.app.services.config.config_default import InvokeAIAppConfig
+from invokeai.backend.util.devices import choose_torch_device
+from invokeai.backend.util.util import download_with_progress_bar
+
+from .onnxdet import inference_detector
+from .onnxpose import inference_pose
+
+DWPOSE_MODELS = {
+    "yolox_l.onnx": {
+        "local": "any/annotators/dwpose/yolox_l.onnx",
+        "url": "https://huggingface.co/yzd-v/DWPose/resolve/main/yolox_l.onnx?download=true",
+    },
+    "dw-ll_ucoco_384.onnx": {
+        "local": "any/annotators/dwpose/dw-ll_ucoco_384.onnx",
+        "url": "https://huggingface.co/yzd-v/DWPose/resolve/main/dw-ll_ucoco_384.onnx?download=true",
+    },
+}
+
+config = InvokeAIAppConfig.get_config()
+
+
+class Wholebody:
+    def __init__(self):
+        device = choose_torch_device()
+
+        providers = ["CUDAExecutionProvider"] if device == "cuda" else ["CPUExecutionProvider"]
+
+        DET_MODEL_PATH = pathlib.Path(config.models_path / DWPOSE_MODELS["yolox_l.onnx"]["local"])
+        if not DET_MODEL_PATH.exists():
+            download_with_progress_bar(DWPOSE_MODELS["yolox_l.onnx"]["url"], DET_MODEL_PATH)
+
+        POSE_MODEL_PATH = pathlib.Path(config.models_path / DWPOSE_MODELS["dw-ll_ucoco_384.onnx"]["local"])
+        if not POSE_MODEL_PATH.exists():
+            download_with_progress_bar(DWPOSE_MODELS["dw-ll_ucoco_384.onnx"]["url"], POSE_MODEL_PATH)
+
+        onnx_det = DET_MODEL_PATH
+        onnx_pose = POSE_MODEL_PATH
+
+        self.session_det = ort.InferenceSession(path_or_bytes=onnx_det, providers=providers)
+        self.session_pose = ort.InferenceSession(path_or_bytes=onnx_pose, providers=providers)
+
+    def __call__(self, oriImg):
+        det_result = inference_detector(self.session_det, oriImg)
+        keypoints, scores = inference_pose(self.session_pose, det_result, oriImg)
+
+        keypoints_info = np.concatenate((keypoints, scores[..., None]), axis=-1)
+        # compute neck joint
+        neck = np.mean(keypoints_info[:, [5, 6]], axis=1)
+        # neck score when visualizing pred
+        neck[:, 2:4] = np.logical_and(keypoints_info[:, 5, 2:4] > 0.3, keypoints_info[:, 6, 2:4] > 0.3).astype(int)
+        new_keypoints_info = np.insert(keypoints_info, 17, neck, axis=1)
+        mmpose_idx = [17, 6, 8, 10, 7, 9, 12, 14, 16, 13, 15, 2, 1, 4, 3]
+        openpose_idx = [1, 2, 3, 4, 6, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17]
+        new_keypoints_info[:, openpose_idx] = new_keypoints_info[:, mmpose_idx]
+        keypoints_info = new_keypoints_info
+
+        keypoints, scores = keypoints_info[..., :2], keypoints_info[..., 2]
+
+        return keypoints, scores

invokeai/backend/image_util/realesrgan/realesrgan.py

@@ -7,10 +7,10 @@ import cv2
 import numpy as np
 import numpy.typing as npt
 import torch
-from basicsr.archs.rrdbnet_arch import RRDBNet
 from cv2.typing import MatLike
 from tqdm import tqdm
 
+from invokeai.backend.image_util.basicsr.rrdbnet_arch import RRDBNet
 from invokeai.backend.util.devices import choose_torch_device
 
 """

invokeai/backend/model_management/__init__.py

@@ -3,7 +3,7 @@
 Initialization file for invokeai.backend.model_management
 """
 # This import must be first
-from .model_manager import AddModelResult, ModelInfo, ModelManager, SchedulerPredictionType
+from .model_manager import AddModelResult, LoadedModelInfo, ModelManager, SchedulerPredictionType
 from .lora import ModelPatcher, ONNXModelPatcher
 from .model_cache import ModelCache
 

invokeai/backend/model_management/model_manager.py

@@ -271,7 +271,7 @@ CONFIG_FILE_VERSION = "3.0.0"
 
 
 @dataclass
-class ModelInfo:
+class LoadedModelInfo:
     context: ModelLocker
     name: str
     base_model: BaseModelType
@@ -450,7 +450,7 @@ class ModelManager(object):
         base_model: BaseModelType,
         model_type: ModelType,
         submodel_type: Optional[SubModelType] = None,
-    ) -> ModelInfo:
+    ) -> LoadedModelInfo:
         """Given a model named identified in models.yaml, return
         an ModelInfo object describing it.
         :param model_name: symbolic name of the model in models.yaml
@@ -508,7 +508,7 @@ class ModelManager(object):
 
         model_hash = "<NO_HASH>"  # TODO:
 
-        return ModelInfo(
+        return LoadedModelInfo(
             context=model_context,
             name=model_name,
             base_model=base_model,

invokeai/backend/model_management/seamless.py

@@ -1,10 +1,11 @@
 from __future__ import annotations
 
 from contextlib import contextmanager
-from typing import List, Union
+from typing import Callable, List, Union
 
 import torch.nn as nn
-from diffusers.models import AutoencoderKL, UNet2DConditionModel
+from diffusers.models.autoencoders.autoencoder_kl import AutoencoderKL
+from diffusers.models.unets.unet_2d_condition import UNet2DConditionModel
 
 
 def _conv_forward_asymmetric(self, input, weight, bias):
@@ -26,70 +27,51 @@ def _conv_forward_asymmetric(self, input, weight, bias):
 
 @contextmanager
 def set_seamless(model: Union[UNet2DConditionModel, AutoencoderKL], seamless_axes: List[str]):
+    # Callable: (input: Tensor, weight: Tensor, bias: Optional[Tensor]) -> Tensor
+    to_restore: list[tuple[nn.Conv2d | nn.ConvTranspose2d, Callable]] = []
     try:
-        to_restore = []
-
+        # Hard coded to skip down block layers, allowing for seamless tiling at the expense of prompt adherence
+        skipped_layers = 1
         for m_name, m in model.named_modules():
-            if isinstance(model, UNet2DConditionModel):
-                if ".attentions." in m_name:
+            if not isinstance(m, (nn.Conv2d, nn.ConvTranspose2d)):
+                continue
+
+            if isinstance(model, UNet2DConditionModel) and m_name.startswith("down_blocks.") and ".resnets." in m_name:
+                # down_blocks.1.resnets.1.conv1
+                _, block_num, _, resnet_num, submodule_name = m_name.split(".")
+                block_num = int(block_num)
+                resnet_num = int(resnet_num)
+
+                if block_num >= len(model.down_blocks) - skipped_layers:
                     continue
 
-                if ".resnets." in m_name:
-                    if ".conv2" in m_name:
-                        continue
-                    if ".conv_shortcut" in m_name:
-                        continue
-
-            """
-            if isinstance(model, UNet2DConditionModel):
-                if False and ".upsamplers." in m_name:
+                # Skip the second resnet (could be configurable)
+                if resnet_num > 0:
                     continue
 
-                if False and ".downsamplers." in m_name:
+                # Skip Conv2d layers (could be configurable)
+                if submodule_name == "conv2":
                     continue
 
-                if True and ".resnets." in m_name:
-                    if True and ".conv1" in m_name:
-                        if False and "down_blocks" in m_name:
-                            continue
-                        if False and "mid_block" in m_name:
-                            continue
-                        if False and "up_blocks" in m_name:
-                            continue
+            m.asymmetric_padding_mode = {}
+            m.asymmetric_padding = {}
+            m.asymmetric_padding_mode["x"] = "circular" if ("x" in seamless_axes) else "constant"
+            m.asymmetric_padding["x"] = (
+                m._reversed_padding_repeated_twice[0],
+                m._reversed_padding_repeated_twice[1],
+                0,
+                0,
+            )
+            m.asymmetric_padding_mode["y"] = "circular" if ("y" in seamless_axes) else "constant"
+            m.asymmetric_padding["y"] = (
+                0,
+                0,
+                m._reversed_padding_repeated_twice[2],
+                m._reversed_padding_repeated_twice[3],
+            )
 
-                    if True and ".conv2" in m_name:
-                        continue
-
-                    if True and ".conv_shortcut" in m_name:
-                        continue
-
-                if True and ".attentions." in m_name:
-                    continue
-
-                if False and m_name in ["conv_in", "conv_out"]:
-                    continue
-            """
-
-            if isinstance(m, (nn.Conv2d, nn.ConvTranspose2d)):
-                m.asymmetric_padding_mode = {}
-                m.asymmetric_padding = {}
-                m.asymmetric_padding_mode["x"] = "circular" if ("x" in seamless_axes) else "constant"
-                m.asymmetric_padding["x"] = (
-                    m._reversed_padding_repeated_twice[0],
-                    m._reversed_padding_repeated_twice[1],
-                    0,
-                    0,
-                )
-                m.asymmetric_padding_mode["y"] = "circular" if ("y" in seamless_axes) else "constant"
-                m.asymmetric_padding["y"] = (
-                    0,
-                    0,
-                    m._reversed_padding_repeated_twice[2],
-                    m._reversed_padding_repeated_twice[3],
-                )
-
-                to_restore.append((m, m._conv_forward))
-                m._conv_forward = _conv_forward_asymmetric.__get__(m, nn.Conv2d)
+            to_restore.append((m, m._conv_forward))
+            m._conv_forward = _conv_forward_asymmetric.__get__(m, nn.Conv2d)
 
         yield
 

invokeai/backend/stable_diffusion/diffusion/conditioning_data.py

@@ -32,6 +32,11 @@ class BasicConditioningInfo:
         return self
 
 
+@dataclass
+class ConditioningFieldData:
+    conditionings: List[BasicConditioningInfo]
+
+
 @dataclass
 class SDXLConditioningInfo(BasicConditioningInfo):
     pooled_embeds: torch.Tensor

invokeai/backend/tiles/tiles.py

@@ -3,7 +3,7 @@ from typing import Union
 
 import numpy as np
 
-from invokeai.app.invocations.latent import LATENT_SCALE_FACTOR
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
 from invokeai.backend.tiles.utils import TBLR, Tile, paste, seam_blend
 
 

invokeai/backend/util/test_utils.py

@@ -7,7 +7,7 @@ import torch
 
 from invokeai.app.services.config.config_default import InvokeAIAppConfig
 from invokeai.backend.install.model_install_backend import ModelInstall
-from invokeai.backend.model_management.model_manager import ModelInfo
+from invokeai.backend.model_management.model_manager import LoadedModelInfo
 from invokeai.backend.model_management.models.base import BaseModelType, ModelNotFoundException, ModelType, SubModelType
 
 
@@ -34,8 +34,8 @@ def install_and_load_model(
     base_model: BaseModelType,
     model_type: ModelType,
     submodel_type: Optional[SubModelType] = None,
-) -> ModelInfo:
-    """Install a model if it is not already installed, then get the ModelInfo for that model.
+) -> LoadedModelInfo:
+    """Install a model if it is not already installed, then get the LoadedModelInfo for that model.
 
     This is intended as a utility function for tests.
 
@@ -49,9 +49,9 @@ def install_and_load_model(
         submodel_type (Optional[SubModelType]): The submodel type, forwarded to ModelManager.get_model(...).
 
     Returns:
-        ModelInfo
+        LoadedModelInfo
     """
-    # If the requested model is already installed, return its ModelInfo.
+    # If the requested model is already installed, return its LoadedModelInfo.
     with contextlib.suppress(ModelNotFoundException):
         return model_installer.mgr.get_model(model_name, base_model, model_type, submodel_type)
 

invokeai/frontend/web/package.json

@@ -52,6 +52,7 @@
     "@chakra-ui/react-use-size": "^2.1.0",
     "@dagrejs/graphlib": "^2.1.13",
     "@dnd-kit/core": "^6.1.0",
+    "@dnd-kit/sortable": "^8.0.0",
     "@dnd-kit/utilities": "^3.2.2",
     "@fontsource-variable/inter": "^5.0.16",
     "@invoke-ai/ui-library": "^0.0.18",

invokeai/frontend/web/pnpm-lock.yaml

@@ -22,6 +22,9 @@ dependencies:
   '@dnd-kit/core':
     specifier: ^6.1.0
     version: 6.1.0(react-dom@18.2.0)(react@18.2.0)
+  '@dnd-kit/sortable':
+    specifier: ^8.0.0
+    version: 8.0.0(@dnd-kit/core@6.1.0)(react@18.2.0)
   '@dnd-kit/utilities':
     specifier: ^3.2.2
     version: 3.2.2(react@18.2.0)
@@ -2884,6 +2887,18 @@ packages:
       tslib: 2.6.2
     dev: false
 
+  /@dnd-kit/sortable@8.0.0(@dnd-kit/core@6.1.0)(react@18.2.0):
+    resolution: {integrity: sha512-U3jk5ebVXe1Lr7c2wU7SBZjcWdQP+j7peHJfCspnA81enlu88Mgd7CC8Q+pub9ubP7eKVETzJW+IBAhsqbSu/g==}
+    peerDependencies:
+      '@dnd-kit/core': ^6.1.0
+      react: '>=16.8.0'
+    dependencies:
+      '@dnd-kit/core': 6.1.0(react-dom@18.2.0)(react@18.2.0)
+      '@dnd-kit/utilities': 3.2.2(react@18.2.0)
+      react: 18.2.0
+      tslib: 2.6.2
+    dev: false
+
   /@dnd-kit/utilities@3.2.2(react@18.2.0):
     resolution: {integrity: sha512-+MKAJEOfaBe5SmV6t34p80MMKhjvUz0vRrvVJbPT0WElzaOJ/1xs+D+KDv+tD/NE5ujfrChEcshd4fLn0wpiqg==}
     peerDependencies:

invokeai/frontend/web/public/locales/de.json

@@ -56,7 +56,7 @@
         "nodeEditor": "Knoten Editor",
         "statusMergingModels": "Modelle zusammenführen",
         "ipAdapter": "IP Adapter",
-        "controlAdapter": "Control Adapter",
+        "controlAdapter": "Control-Adapter",
         "auto": "Automatisch",
         "controlNet": "ControlNet",
         "imageFailedToLoad": "Kann Bild nicht laden",
@@ -69,18 +69,18 @@
         "random": "Zufall",
         "batch": "Stapel-Manager",
         "advanced": "Erweitert",
-        "unifiedCanvas": "Einheitliche Leinwand",
+        "unifiedCanvas": "Leinwand",
         "openInNewTab": "In einem neuem Tab öffnen",
         "statusProcessing": "wird bearbeitet",
         "linear": "Linear",
         "imagePrompt": "Bild Prompt",
         "checkpoint": "Checkpoint",
-        "inpaint": "inpaint",
+        "inpaint": "Inpaint",
         "simple": "Einfach",
         "template": "Vorlage",
         "outputs": "Ausgabe",
         "data": "Daten",
-        "safetensors": "Safetensors",
+        "safetensors": "Safe-Tensors",
         "outpaint": "Ausmalen",
         "details": "Details",
         "format": "Format",
@@ -115,7 +115,8 @@
         "orderBy": "Ordnen nach",
         "saveAs": "Speicher als",
         "updated": "Aktualisiert",
-        "copy": "Kopieren"
+        "copy": "Kopieren",
+        "aboutHeading": "Nutzen Sie Ihre kreative Energie"
     },
     "gallery": {
         "generations": "Erzeugungen",
@@ -126,7 +127,7 @@
         "galleryImageResetSize": "Größe zurücksetzen",
         "gallerySettings": "Galerie-Einstellungen",
         "maintainAspectRatio": "Seitenverhältnis beibehalten",
-        "autoSwitchNewImages": "Automatisch zu neuen Bildern wechseln",
+        "autoSwitchNewImages": "Auto-Wechsel zu neuen Bildern",
         "singleColumnLayout": "Einspaltiges Layout",
         "allImagesLoaded": "Alle Bilder geladen",
         "loadMore": "Mehr laden",
@@ -146,26 +147,30 @@
         "deleteImagePermanent": "Gelöschte Bilder können nicht wiederhergestellt werden.",
         "autoAssignBoardOnClick": "Board per Klick automatisch zuweisen",
         "noImageSelected": "Kein Bild ausgewählt",
-        "problemDeletingImagesDesc": "Eins oder mehr Bilder könnten nicht gelöscht werden",
+        "problemDeletingImagesDesc": "Ein oder mehrere Bilder konnten nicht gelöscht werden",
         "starImage": "Bild markieren",
         "assets": "Ressourcen",
         "unstarImage": "Markierung Entfernen",
         "image": "Bild",
-        "deleteSelection": "Lösche markierte"
+        "deleteSelection": "Lösche markierte",
+        "dropToUpload": "$t(gallery.drop) zum hochladen",
+        "dropOrUpload": "$t(gallery.drop) oder hochladen",
+        "drop": "Ablegen",
+        "problemDeletingImages": "Problem beim Löschen der Bilder"
     },
     "hotkeys": {
         "keyboardShortcuts": "Tastenkürzel",
         "appHotkeys": "App-Tastenkombinationen",
-        "generalHotkeys": "Allgemeine Tastenkürzel",
-        "galleryHotkeys": "Galerie Tastenkürzel",
-        "unifiedCanvasHotkeys": "Unified Canvas Tastenkürzel",
+        "generalHotkeys": "Allgemein",
+        "galleryHotkeys": "Galerie",
+        "unifiedCanvasHotkeys": "Leinwand",
         "invoke": {
             "desc": "Ein Bild erzeugen",
             "title": "Invoke"
         },
         "cancel": {
             "title": "Abbrechen",
-            "desc": "Bilderzeugung abbrechen"
+            "desc": "Aktuelle Bilderzeugung abbrechen"
         },
         "focusPrompt": {
             "title": "Fokussiere Prompt",
@@ -221,7 +226,7 @@
         },
         "sendToImageToImage": {
             "title": "An Bild zu Bild senden",
-            "desc": "Aktuelles Bild an Bild zu Bild senden"
+            "desc": "Aktuelles Bild an Bild-zu-Bild senden"
         },
         "deleteImage": {
             "title": "Bild löschen",
@@ -253,7 +258,7 @@
         },
         "selectEraser": {
             "title": "Radiergummi auswählen",
-            "desc": "Wählt den Radiergummi für die Leinwand aus"
+            "desc": "Wählt den Radiergummi aus"
         },
         "decreaseBrushSize": {
             "title": "Pinselgröße verkleinern",
@@ -325,7 +330,7 @@
         },
         "downloadImage": {
             "title": "Bild herunterladen",
-            "desc": "Aktuelle Leinwand herunterladen"
+            "desc": "Aktuelles Bild herunterladen"
         },
         "undoStroke": {
             "title": "Pinselstrich rückgängig machen",
@@ -351,42 +356,55 @@
             "title": "Staging-Bild akzeptieren",
             "desc": "Akzeptieren Sie das aktuelle Bild des Staging-Bereichs"
         },
-        "nodesHotkeys": "Knoten Tastenkürzel",
+        "nodesHotkeys": "Knoten",
         "addNodes": {
             "title": "Knotenpunkt hinzufügen",
             "desc": "Öffnet das Menü zum Hinzufügen von Knoten"
         },
         "cancelAndClear": {
-            "title": "Abbruch und leeren"
+            "title": "Abbruch und leeren",
+            "desc": "Aktuelle Berechnung abbrechen und alle wartenden löschen"
         },
         "noHotkeysFound": "Kein Hotkey gefunden",
         "searchHotkeys": "Hotkeys durchsuchen",
-        "clearSearch": "Suche leeren"
+        "clearSearch": "Suche leeren",
+        "resetOptionsAndGallery": {
+            "desc": "Optionen und Galerie-Panels zurücksetzen",
+            "title": "Optionen und Galerie zurücksetzen"
+        },
+        "remixImage": {
+            "desc": "Alle Parameter außer Seed vom aktuellen Bild verwenden",
+            "title": "Remix des Bilds erstellen"
+        },
+        "toggleOptionsAndGallery": {
+            "title": "Optionen und Galerie umschalten",
+            "desc": "Optionen und Galerie-Panels öffnen und schließen"
+        }
     },
     "modelManager": {
         "modelAdded": "Model hinzugefügt",
         "modelUpdated": "Model aktualisiert",
         "modelEntryDeleted": "Modelleintrag gelöscht",
         "cannotUseSpaces": "Leerzeichen können nicht verwendet werden",
-        "addNew": "Neue hinzufügen",
-        "addNewModel": "Neues Model hinzufügen",
+        "addNew": "Neu hinzufügen",
+        "addNewModel": "Neues Modell hinzufügen",
         "addManually": "Manuell hinzufügen",
         "nameValidationMsg": "Geben Sie einen Namen für Ihr Model ein",
         "description": "Beschreibung",
         "descriptionValidationMsg": "Fügen Sie eine Beschreibung für Ihr Model hinzu",
         "config": "Konfiguration",
-        "configValidationMsg": "Pfad zur Konfigurationsdatei Ihres Models.",
+        "configValidationMsg": "Pfad zur Konfigurationsdatei Ihres Modells.",
         "modelLocation": "Ort des Models",
         "modelLocationValidationMsg": "Pfad zum Speicherort Ihres Models",
         "vaeLocation": "VAE Ort",
         "vaeLocationValidationMsg": "Pfad zum Speicherort Ihres VAE.",
         "width": "Breite",
-        "widthValidationMsg": "Standardbreite Ihres Models.",
+        "widthValidationMsg": "Standardbreite Ihres Modells.",
         "height": "Höhe",
         "heightValidationMsg": "Standardbhöhe Ihres Models.",
-        "addModel": "Model hinzufügen",
+        "addModel": "Modell hinzufügen",
         "updateModel": "Model aktualisieren",
-        "availableModels": "Verfügbare Models",
+        "availableModels": "Verfügbare Modelle",
         "search": "Suche",
         "load": "Laden",
         "active": "Aktiv",
@@ -483,7 +501,7 @@
         "quickAdd": "Schnell hinzufügen",
         "simpleModelDesc": "Geben Sie einen Pfad zu einem lokalen Diffusers-Modell, einem lokalen Checkpoint-/Safetensors-Modell, einer HuggingFace-Repo-ID oder einer Checkpoint-/Diffusers-Modell-URL an.",
         "modelDeleted": "Modell gelöscht",
-        "inpainting": "v1 Inpainting",
+        "inpainting": "V1-Inpainting",
         "modelUpdateFailed": "Modellaktualisierung fehlgeschlagen",
         "useCustomConfig": "Benutzerdefinierte Konfiguration verwenden",
         "settings": "Einstellungen",
@@ -500,12 +518,14 @@
         "interpolationType": "Interpolationstyp",
         "oliveModels": "Olives",
         "variant": "Variante",
-        "loraModels": "LoRAs",
+        "loraModels": "\"LoRAs\"",
         "modelDeleteFailed": "Modell konnte nicht gelöscht werden",
         "mergedModelName": "Zusammengeführter Modellname",
         "checkpointOrSafetensors": "$t(common.checkpoint) / $t(common.safetensors)",
         "formMessageDiffusersModelLocation": "Diffusers Modell Speicherort",
-        "noModelSelected": "Kein Modell ausgewählt"
+        "noModelSelected": "Kein Modell ausgewählt",
+        "conversionNotSupported": "Umwandlung nicht unterstützt",
+        "configFile": "Konfigurationsdatei"
     },
     "parameters": {
         "images": "Bilder",
@@ -544,8 +564,8 @@
         "img2imgStrength": "Bild-zu-Bild-Stärke",
         "toggleLoopback": "Loopback umschalten",
         "sendTo": "Senden an",
-        "sendToImg2Img": "Senden an Bild zu Bild",
-        "sendToUnifiedCanvas": "Senden an Unified Canvas",
+        "sendToImg2Img": "Senden an Bild-zu-Bild",
+        "sendToUnifiedCanvas": "Senden an Leinwand",
         "copyImageToLink": "Bild-Link kopieren",
         "downloadImage": "Bild herunterladen",
         "openInViewer": "Im Viewer öffnen",
@@ -583,7 +603,10 @@
         "resetWebUIDesc2": "Wenn die Bilder nicht in der Galerie angezeigt werden oder etwas anderes nicht funktioniert, versuchen Sie bitte, die Einstellungen zurückzusetzen, bevor Sie einen Fehler auf GitHub melden.",
         "resetComplete": "Die Web-Oberfläche wurde zurückgesetzt.",
         "models": "Modelle",
-        "useSlidersForAll": "Schieberegler für alle Optionen verwenden"
+        "useSlidersForAll": "Schieberegler für alle Optionen verwenden",
+        "showAdvancedOptions": "Erweiterte Optionen anzeigen",
+        "alternateCanvasLayout": "Alternatives Leinwand-Layout",
+        "clearIntermediatesDesc1": "Das Löschen der Zwischenprodukte setzt Leinwand und ControlNet zurück."
     },
     "toast": {
         "tempFoldersEmptied": "Temp-Ordner geleert",
@@ -597,7 +620,7 @@
         "imageSavedToGallery": "Bild in die Galerie gespeichert",
         "canvasMerged": "Leinwand zusammengeführt",
         "sentToImageToImage": "Gesendet an Bild zu Bild",
-        "sentToUnifiedCanvas": "Gesendet an Unified Canvas",
+        "sentToUnifiedCanvas": "Gesendet an Leinwand",
         "parametersSet": "Parameter festlegen",
         "parametersNotSet": "Parameter nicht festgelegt",
         "parametersNotSetDesc": "Keine Metadaten für dieses Bild gefunden.",
@@ -614,7 +637,21 @@
         "metadataLoadFailed": "Metadaten konnten nicht geladen werden",
         "initialImageSet": "Ausgangsbild festgelegt",
         "initialImageNotSet": "Ausgangsbild nicht festgelegt",
-        "initialImageNotSetDesc": "Ausgangsbild konnte nicht geladen werden"
+        "initialImageNotSetDesc": "Ausgangsbild konnte nicht geladen werden",
+        "setCanvasInitialImage": "Ausgangsbild setzen",
+        "problemMergingCanvas": "Problem bei Verschmelzung der Leinwand",
+        "canvasCopiedClipboard": "Leinwand in Zwischenablage kopiert",
+        "canvasSentControlnetAssets": "Leinwand an ControlNet & Sammlung geschickt",
+        "problemDownloadingCanvasDesc": "Kann Basis-Layer nicht exportieren",
+        "canvasDownloaded": "Leinwand heruntergeladen",
+        "problemSavingCanvasDesc": "Kann Basis-Layer nicht exportieren",
+        "canvasSavedGallery": "Leinwand in Galerie gespeichert",
+        "problemMergingCanvasDesc": "Kann Basis-Layer nicht exportieren",
+        "problemSavingCanvas": "Problem beim Speichern der Leinwand",
+        "problemCopyingCanvas": "Problem beim Kopieren der Leinwand",
+        "problemCopyingCanvasDesc": "Kann Basis-Layer nicht exportieren",
+        "problemDownloadingCanvas": "Problem beim Herunterladen der Leinwand",
+        "setAsCanvasInitialImage": "Als Ausgangsbild gesetzt"
     },
     "tooltip": {
         "feature": {
@@ -626,8 +663,8 @@
             "upscale": "Verwenden Sie ESRGAN, um das Bild unmittelbar nach der Erzeugung zu vergrößern.",
             "faceCorrection": "Gesichtskorrektur mit GFPGAN oder Codeformer: Der Algorithmus erkennt Gesichter im Bild und korrigiert alle Fehler. Ein hoher Wert verändert das Bild stärker, was zu attraktiveren Gesichtern führt. Codeformer mit einer höheren Genauigkeit bewahrt das Originalbild auf Kosten einer stärkeren Gesichtskorrektur.",
             "imageToImage": "Bild zu Bild lädt ein beliebiges Bild als Ausgangsbild, aus dem dann zusammen mit dem Prompt ein neues Bild erzeugt wird. Je höher der Wert ist, desto stärker wird das Ergebnisbild verändert. Werte von 0,0 bis 1,0 sind möglich, der empfohlene Bereich ist .25-.75",
-            "boundingBox": "Der Begrenzungsrahmen ist derselbe wie die Einstellungen für Breite und Höhe bei Text zu Bild oder Bild zu Bild. Es wird nur der Bereich innerhalb des Rahmens verarbeitet.",
-            "seamCorrection": "Steuert die Behandlung von sichtbaren Übergängen, die zwischen den erzeugten Bildern auf der Leinwand auftreten.",
+            "boundingBox": "Der Begrenzungsrahmen ist derselbe wie die Einstellungen für Breite und Höhe bei Text-zu-Bild oder Bild-zu-Bild. Es wird nur der Bereich innerhalb des Rahmens verarbeitet.",
+            "seamCorrection": "Behandlung von sichtbaren Übergängen, die zwischen den erzeugten Bildern auftreten.",
             "infillAndScaling": "Verwalten Sie Infill-Methoden (für maskierte oder gelöschte Bereiche der Leinwand) und Skalierung (nützlich für kleine Begrenzungsrahmengrößen)."
         }
     },
@@ -638,17 +675,17 @@
         "maskingOptions": "Maskierungsoptionen",
         "enableMask": "Maske aktivieren",
         "preserveMaskedArea": "Maskierten Bereich bewahren",
-        "clearMask": "Maske löschen",
+        "clearMask": "Maske löschen (Shift+C)",
         "brush": "Pinsel",
         "eraser": "Radierer",
         "fillBoundingBox": "Begrenzungsrahmen füllen",
         "eraseBoundingBox": "Begrenzungsrahmen löschen",
-        "colorPicker": "Farbpipette",
+        "colorPicker": "Pipette",
         "brushOptions": "Pinseloptionen",
         "brushSize": "Größe",
         "move": "Bewegen",
         "resetView": "Ansicht zurücksetzen",
-        "mergeVisible": "Sichtbare Zusammenführen",
+        "mergeVisible": "Sichtbare zusammenführen",
         "saveToGallery": "In Galerie speichern",
         "copyToClipboard": "In Zwischenablage kopieren",
         "downloadAsImage": "Als Bild herunterladen",
@@ -656,21 +693,21 @@
         "redo": "Wiederherstellen",
         "clearCanvas": "Leinwand löschen",
         "canvasSettings": "Leinwand-Einstellungen",
-        "showIntermediates": "Zwischenprodukte anzeigen",
+        "showIntermediates": "Zwischenbilder anzeigen",
         "showGrid": "Gitternetz anzeigen",
         "snapToGrid": "Am Gitternetz einrasten",
         "darkenOutsideSelection": "Außerhalb der Auswahl verdunkeln",
         "autoSaveToGallery": "Automatisch in Galerie speichern",
         "saveBoxRegionOnly": "Nur Auswahlbox speichern",
-        "limitStrokesToBox": "Striche auf Box beschränken",
-        "showCanvasDebugInfo": "Zusätzliche Informationen zur Leinwand anzeigen",
+        "limitStrokesToBox": "Striche auf Auswahl beschränken",
+        "showCanvasDebugInfo": "Zusätzliche Informationen anzeigen",
         "clearCanvasHistory": "Leinwand-Verlauf löschen",
         "clearHistory": "Verlauf löschen",
-        "clearCanvasHistoryMessage": "Wenn Sie den Verlauf der Leinwand löschen, bleibt die aktuelle Leinwand intakt, aber der Verlauf der Rückgängig- und Wiederherstellung wird unwiderruflich gelöscht.",
-        "clearCanvasHistoryConfirm": "Sind Sie sicher, dass Sie den Verlauf der Leinwand löschen möchten?",
+        "clearCanvasHistoryMessage": "Wenn Sie den Verlauf löschen, bleibt die aktuelle Leinwand intakt, aber der Verlauf der Rückgängig- und Wiederherstellung wird unwiderruflich gelöscht.",
+        "clearCanvasHistoryConfirm": "Sind Sie sicher, dass Sie den Verlauf löschen möchten?",
         "emptyTempImageFolder": "Temp-Image Ordner leeren",
         "emptyFolder": "Leerer Ordner",
-        "emptyTempImagesFolderMessage": "Wenn Sie den Ordner für temporäre Bilder leeren, wird auch der Unified Canvas vollständig zurückgesetzt. Dies umfasst den gesamten Verlauf der Rückgängig-/Wiederherstellungsvorgänge, die Bilder im Bereitstellungsbereich und die Leinwand-Basisebene.",
+        "emptyTempImagesFolderMessage": "Wenn Sie den Ordner für temporäre Bilder leeren, wird die Leinwand zurückgesetzt. Dies umfasst den gesamten Verlauf der Rückgängig-/Wiederherstellungsvorgänge, die Bilder im Bereitstellungsbereich und die Leinwand-Basisebene.",
         "emptyTempImagesFolderConfirm": "Sind Sie sicher, dass Sie den temporären Ordner leeren wollen?",
         "activeLayer": "Aktive Ebene",
         "canvasScale": "Leinwand Maßstab",
@@ -687,14 +724,14 @@
         "discardAll": "Alles verwerfen",
         "betaClear": "Löschen",
         "betaDarkenOutside": "Außen abdunkeln",
-        "betaLimitToBox": "Begrenzung auf das Feld",
+        "betaLimitToBox": "Auf Auswahl begrenzen",
         "betaPreserveMasked": "Maskiertes bewahren",
         "antialiasing": "Kantenglättung",
         "showResultsOn": "Zeige Ergebnisse (An)",
         "showResultsOff": "Zeige Ergebnisse (Aus)"
     },
     "accessibility": {
-        "modelSelect": "Model Auswahl",
+        "modelSelect": "Modell-Auswahl",
         "uploadImage": "Bild hochladen",
         "previousImage": "Voriges Bild",
         "useThisParameter": "Benutze diesen Parameter",
@@ -706,11 +743,11 @@
         "modifyConfig": "Optionen einstellen",
         "toggleAutoscroll": "Auroscroll ein/ausschalten",
         "toggleLogViewer": "Log Betrachter ein/ausschalten",
-        "showOptionsPanel": "Zeige Optionen",
+        "showOptionsPanel": "Seitenpanel anzeigen",
         "reset": "Zurücksetzten",
         "nextImage": "Nächstes Bild",
         "zoomOut": "Verkleinern",
-        "rotateCounterClockwise": "Gegen den Uhrzeigersinn verdrehen",
+        "rotateCounterClockwise": "Gegen den Uhrzeigersinn drehen",
         "showGalleryPanel": "Galeriefenster anzeigen",
         "exitViewer": "Betrachten beenden",
         "menu": "Menü",
@@ -725,14 +762,14 @@
         "autoAddBoard": "Automatisches Hinzufügen zum Ordner",
         "topMessage": "Dieser Ordner enthält Bilder die in den folgenden Funktionen verwendet werden:",
         "move": "Bewegen",
-        "menuItemAutoAdd": "Automatisches Hinzufügen zu diesem Ordner",
+        "menuItemAutoAdd": "Auto-Hinzufügen zu diesem Ordner",
         "myBoard": "Meine Ordner",
         "searchBoard": "Ordner durchsuchen...",
         "noMatching": "Keine passenden Ordner",
         "selectBoard": "Ordner aussuchen",
         "cancel": "Abbrechen",
         "addBoard": "Ordner hinzufügen",
-        "uncategorized": "Nicht kategorisiert",
+        "uncategorized": "Ohne Kategorie",
         "downloadBoard": "Ordner runterladen",
         "changeBoard": "Ordner wechseln",
         "loading": "Laden...",
@@ -742,15 +779,15 @@
         "deleteBoard": "Löschen Ordner",
         "deleteBoardAndImages": "Löschen Ordner und Bilder",
         "deletedBoardsCannotbeRestored": "Gelöschte Ordner könnte nicht wiederhergestellt werden",
-        "movingImagesToBoard_one": "Verschiebe {{count}} Bild zu Ordner",
-        "movingImagesToBoard_other": "Verschiebe {{count}} Bilder in Ordner"
+        "movingImagesToBoard_one": "Verschiebe {{count}} Bild zu Ordner:",
+        "movingImagesToBoard_other": "Verschiebe {{count}} Bilder in Ordner:"
     },
     "controlnet": {
         "showAdvanced": "Zeige Erweitert",
         "contentShuffleDescription": "Mischt den Inhalt von einem Bild",
         "addT2IAdapter": "$t(common.t2iAdapter) hinzufügen",
-        "importImageFromCanvas": "Importieren Bild von Zeichenfläche",
-        "lineartDescription": "Konvertiere Bild zu Lineart",
+        "importImageFromCanvas": "Bild von Zeichenfläche importieren",
+        "lineartDescription": "Konvertiere Bild in Strichzeichnung",
         "importMaskFromCanvas": "Importiere Maske von Zeichenfläche",
         "hed": "HED",
         "hideAdvanced": "Verstecke Erweitert",
@@ -764,7 +801,7 @@
         "depthMidasDescription": "Tiefenmap erstellen mit Midas",
         "controlnet": "$t(controlnet.controlAdapter_one) #{{number}} ($t(common.controlNet))",
         "t2iEnabledControlNetDisabled": "$t(common.t2iAdapter) ist aktiv, $t(common.controlNet) ist deaktiviert",
-        "weight": "Breite",
+        "weight": "Einfluss",
         "selectModel": "Wähle ein Modell",
         "depthMidas": "Tiefe (Midas)",
         "w": "W",
@@ -786,17 +823,17 @@
         "toggleControlNet": "Schalten ControlNet um",
         "delete": "Löschen",
         "controlAdapter_one": "Control Adapter",
-        "controlAdapter_other": "Control Adapters",
-        "colorMapTileSize": "Tile Größe",
+        "controlAdapter_other": "Control Adapter",
+        "colorMapTileSize": "Kachelgröße",
         "depthZoeDescription": "Tiefenmap erstellen mit Zoe",
-        "setControlImageDimensions": "Setze Control Bild Auflösung auf Breite/Höhe",
+        "setControlImageDimensions": "Setze Control-Bild Auflösung auf Breite/Höhe",
         "handAndFace": "Hand und Gesicht",
         "enableIPAdapter": "Aktiviere IP Adapter",
         "resize": "Größe ändern",
         "resetControlImage": "Zurücksetzen vom Referenz Bild",
         "balanced": "Ausgewogen",
         "prompt": "Prompt",
-        "resizeMode": "Größenänderungsmodus",
+        "resizeMode": "Größe",
         "processor": "Prozessor",
         "saveControlImage": "Speichere Referenz Bild",
         "safe": "Speichern",
@@ -805,35 +842,33 @@
         "pidi": "PIDI",
         "normalBae": "Normales BAE",
         "mlsdDescription": "Minimalistischer Liniensegmentdetektor",
-        "openPoseDescription": "Schätzung der menschlichen Pose mit Openpose",
         "control": "Kontrolle",
-        "coarse": "Coarse",
+        "coarse": "Grob",
         "crop": "Zuschneiden",
         "pidiDescription": "PIDI-Bildverarbeitung",
         "mediapipeFace": "Mediapipe Gesichter",
         "mlsd": "M-LSD",
         "controlMode": "Steuermodus",
-        "cannyDescription": "Canny Ecken Erkennung",
-        "lineart": "Lineart",
+        "cannyDescription": "Canny Umrisserkennung",
+        "lineart": "Linienzeichnung",
         "lineartAnimeDescription": "Lineart-Verarbeitung im Anime-Stil",
         "minConfidence": "Minimales Vertrauen",
         "megaControl": "Mega-Kontrolle",
-        "autoConfigure": "Prozessor automatisch konfigurieren",
+        "autoConfigure": "Prozessor Auto-konfig",
         "normalBaeDescription": "Normale BAE-Verarbeitung",
         "noneDescription": "Es wurde keine Verarbeitung angewendet",
-        "openPose": "Openpose",
-        "lineartAnime": "Lineart Anime",
+        "lineartAnime": "Lineart Anime / \"Strichzeichnung Anime\"",
         "mediapipeFaceDescription": "Gesichtserkennung mit Mediapipe",
-        "canny": "Canny",
+        "canny": "\"Canny\"",
         "hedDescription": "Ganzheitlich verschachtelte Kantenerkennung",
         "scribble": "Scribble",
-        "maxFaces": "Maximal Anzahl Gesichter",
+        "maxFaces": "Maximale Anzahl Gesichter",
         "resizeSimple": "Größe ändern (einfach)",
         "large": "Groß",
         "modelSize": "Modell Größe",
         "small": "Klein",
         "base": "Basis",
-        "depthAnything": "Depth Anything",
+        "depthAnything": "Depth Anything / \"Tiefe irgendwas\"",
         "depthAnythingDescription": "Erstellung einer Tiefenkarte mit der Depth Anything-Technik"
     },
     "queue": {
@@ -876,7 +911,7 @@
         "enqueueing": "Stapel in der Warteschlange",
         "queueMaxExceeded": "Maximum von {{max_queue_size}} Elementen erreicht, würde {{skip}} Elemente überspringen",
         "cancelBatchFailed": "Problem beim Abbruch vom Stapel",
-        "clearQueueAlertDialog2": "bist du sicher die Warteschlange zu leeren?",
+        "clearQueueAlertDialog2": "Warteschlange wirklich leeren?",
         "pruneSucceeded": "{{item_count}} abgeschlossene Elemente aus der Warteschlange entfernt",
         "pauseSucceeded": "Prozessor angehalten",
         "cancelFailed": "Problem beim Stornieren des Auftrags",
@@ -890,78 +925,189 @@
         "resumeSucceeded": "Prozessor wieder aufgenommen",
         "resumeTooltip": "Prozessor wieder aufnehmen",
         "time": "Zeit",
-        "batchQueuedDesc_one": "{{count}} Eintrage ans {{direction}} der Wartschlange hinzugefügt",
-        "batchQueuedDesc_other": "{{count}} Einträge ans {{direction}} der Wartschlange hinzugefügt"
+        "batchQueuedDesc_one": "{{count}} Eintrag ans {{direction}} der Wartschlange hinzugefügt",
+        "batchQueuedDesc_other": "{{count}} Einträge ans {{direction}} der Wartschlange hinzugefügt",
+        "openQueue": "Warteschlange öffnen",
+        "batchFailedToQueue": "Fehler beim Einreihen in die Stapelverarbeitung",
+        "batchFieldValues": "Stapelverarbeitungswerte",
+        "batchQueued": "Stapelverarbeitung eingereiht",
+        "graphQueued": "Graph eingereiht",
+        "graphFailedToQueue": "Fehler beim Einreihen des Graphen"
     },
     "metadata": {
         "negativePrompt": "Negativ Beschreibung",
-        "metadata": "Meta-Data",
-        "strength": "Bild zu Bild stärke",
+        "metadata": "Meta-Daten",
+        "strength": "Bild zu Bild Stärke",
         "imageDetails": "Bild Details",
         "model": "Modell",
         "noImageDetails": "Keine Bild Details gefunden",
         "cfgScale": "CFG-Skala",
-        "fit": "Bild zu Bild passen",
+        "fit": "Bild zu Bild anpassen",
         "height": "Höhe",
-        "noMetaData": "Keine Meta-Data gefunden",
+        "noMetaData": "Keine Meta-Daten gefunden",
         "width": "Breite",
         "createdBy": "Erstellt von",
         "steps": "Schritte",
         "seamless": "Nahtlos",
         "positivePrompt": "Positiver Prompt",
         "generationMode": "Generierungsmodus",
-        "Threshold": "Noise Schwelle",
-        "seed": "Samen",
-        "perlin": "Perlin Noise",
+        "Threshold": "Rauschen-Schwelle",
+        "seed": "Seed",
+        "perlin": "Perlin-Rauschen",
         "hiresFix": "Optimierung für hohe Auflösungen",
         "initImage": "Erstes Bild",
-        "variations": "Samengewichtspaare",
+        "variations": "Seed-Gewichtungs-Paare",
         "vae": "VAE",
-        "workflow": "Arbeitsablauf",
-        "scheduler": "Scheduler",
+        "workflow": "Workflow",
+        "scheduler": "Planer",
         "noRecallParameters": "Es wurden keine Parameter zum Abrufen gefunden",
-        "recallParameters": "Recall Parameters"
+        "recallParameters": "Parameter wiederherstellen"
     },
     "popovers": {
         "noiseUseCPU": {
-            "heading": "Nutze Prozessor rauschen"
+            "heading": "Nutze Prozessor rauschen",
+            "paragraphs": [
+                "Entscheidet, ob auf der CPU oder GPU Rauschen erzeugt wird.",
+                "Mit aktiviertem CPU-Rauschen wird ein bestimmter Seedwert das gleiche Bild auf jeder Maschine erzeugen.",
+                "CPU-Rauschen einzuschalten beeinflusst nicht die Systemleistung."
+            ]
         },
         "paramModel": {
-            "heading": "Modell"
+            "heading": "Modell",
+            "paragraphs": [
+                "Modell für die Entrauschungsschritte.",
+                "Verschiedene Modelle werden in der Regel so trainiert, dass sie sich auf die Erzeugung bestimmter Ästhetik und/oder Inhalte spezialisiert."
+            ]
         },
         "paramIterations": {
-            "heading": "Iterationen"
+            "heading": "Iterationen",
+            "paragraphs": [
+                "Die Anzahl der Bilder, die erzeugt werden sollen.",
+                "Wenn \"Dynamische Prompts\" aktiviert ist, wird jeder einzelne Prompt so oft generiert."
+            ]
         },
         "paramCFGScale": {
-            "heading": "CFG-Skala"
+            "heading": "CFG-Skala",
+            "paragraphs": [
+                "Bestimmt, wie viel Ihr Prompt den Erzeugungsprozess beeinflusst."
+            ]
         },
         "paramSteps": {
-            "heading": "Schritte"
+            "heading": "Schritte",
+            "paragraphs": [
+                "Anzahl der Schritte, die bei jeder Generierung durchgeführt werden.",
+                "Höhere Schrittzahlen werden in der Regel bessere Bilder ergeben, aber mehr Zeit benötigen."
+            ]
         },
         "lora": {
-            "heading": "LoRA Gewichte"
+            "heading": "LoRA Gewichte",
+            "paragraphs": [
+                "Höhere LoRA-Wichtungen führen zu größeren Auswirkungen auf das endgültige Bild."
+            ]
         },
         "infillMethod": {
-            "heading": "Füllmethode"
+            "heading": "Füllmethode",
+            "paragraphs": [
+                "Infill-Methode für den ausgewählten Bereich."
+            ]
         },
         "paramVAE": {
-            "heading": "VAE"
+            "heading": "VAE",
+            "paragraphs": [
+                "Verwendetes Modell, um den KI-Ausgang in das endgültige Bild zu übersetzen."
+            ]
+        },
+        "paramRatio": {
+            "heading": "Seitenverhältnis",
+            "paragraphs": [
+                "Das Seitenverhältnis des erzeugten Bildes.",
+                "Für SD1.5-Modelle wird eine Bildgröße von 512x512 Pixel empfohlen, für SDXL-Modelle sind es 1024x1024 Pixel."
+            ]
+        },
+        "paramDenoisingStrength": {
+            "paragraphs": [
+                "Wie viel Rauschen dem Eingabebild hinzugefügt wird.",
+                "0 wird zu einem identischen Bild führen, während 1 zu einem völlig neuen Bild führt."
+            ],
+            "heading": "Stärke der Entrauschung"
+        },
+        "paramVAEPrecision": {
+            "heading": "VAE-Präzision",
+            "paragraphs": [
+                "Die bei der VAE-Kodierung und Dekodierung verwendete Präzision. FP16/Halbpräzision ist effizienter, aber auf Kosten kleiner Bildvariationen."
+            ]
+        },
+        "paramCFGRescaleMultiplier": {
+            "heading": "CFG Rescale Multiplikator",
+            "paragraphs": [
+                "Rescale-Multiplikator für die CFG-Lenkung, der für Modelle verwendet wird, die mit dem zero-terminal SNR (ztsnr) trainiert wurden. Empfohlener Wert: 0,7."
+            ]
+        },
+        "scaleBeforeProcessing": {
+            "paragraphs": [
+                "Skaliert den ausgewählten Bereich auf die Größe, die für das Modell am besten geeignet ist."
+            ],
+            "heading": "Skalieren vor der Verarbeitung"
+        },
+        "paramSeed": {
+            "paragraphs": [
+                "Kontrolliert das für die Erzeugung verwendete Startrauschen.",
+                "Deaktivieren Sie “Random Seed”, um identische Ergebnisse mit den gleichen Generierungseinstellungen zu erzeugen."
+            ],
+            "heading": "Seed"
+        },
+        "dynamicPromptsMaxPrompts": {
+            "paragraphs": [
+                "Beschränkt die Anzahl der Prompts, die von \"Dynamic Prompts\" generiert werden können."
+            ],
+            "heading": "Maximale Prompts"
+        },
+        "dynamicPromptsSeedBehaviour": {
+            "paragraphs": [
+                "Bestimmt, wie der Seed-Wert beim Erzeugen von Prompts verwendet wird.",
+                "Verwenden Sie dies, um schnelle Variationen eines einzigen Seeds zu erkunden.",
+                "Wenn Sie z. B. 5 Prompts haben, wird jedes Bild den selben Seed-Wert verwenden.",
+                "\"Per Bild\" wird einen einzigartigen Seed-Wert für jedes Bild verwenden. Dies bietet mehr Variationen."
+            ],
+            "heading": "Seed-Verhalten"
+        },
+        "dynamicPrompts": {
+            "paragraphs": [
+                "\"Dynamische Prompts\" übersetzt einen Prompt in mehrere.",
+                "Die Ausgangs-Syntax ist \"ein {roter|grüner|blauer} ball\". Das generiert 3 Prompts: \"ein roter ball\", \"ein grüner ball\" und \"ein blauer ball\".",
+                "Sie können die Syntax so oft verwenden, wie Sie in einem einzigen Prompt möchten, aber stellen Sie sicher, dass die Anzahl der Prompts zur Einstellung von \"Max Prompts\" passt."
+            ],
+            "heading": "Dynamische Prompts"
+        },
+        "controlNetWeight": {
+            "paragraphs": [
+                "Wie stark wird das ControlNet das generierte Bild beeinflussen wird."
+            ],
+            "heading": "Einfluss"
         }
     },
     "ui": {
         "lockRatio": "Verhältnis sperren",
         "hideProgressImages": "Verstecke Prozess Bild",
-        "showProgressImages": "Zeige Prozess Bild"
+        "showProgressImages": "Zeige Prozess Bild",
+        "swapSizes": "Tausche Größen"
     },
     "invocationCache": {
         "disable": "Deaktivieren",
-        "misses": "Cache Nötig",
+        "misses": "Cache nicht genutzt",
         "hits": "Cache Treffer",
         "enable": "Aktivieren",
         "clear": "Leeren",
         "maxCacheSize": "Maximale Cache Größe",
         "cacheSize": "Cache Größe",
-        "useCache": "Benutze Cache"
+        "useCache": "Benutze Cache",
+        "enableFailed": "Problem beim Aktivieren des Zwischenspeichers",
+        "disableFailed": "Problem bei Deaktivierung des Cache",
+        "enableSucceeded": "Zwischenspeicher aktiviert",
+        "disableSucceeded": "Invocation-Cache deaktiviert",
+        "clearSucceeded": "Zwischenspeicher gelöscht",
+        "invocationCache": "Zwischenspeicher",
+        "clearFailed": "Problem beim Löschen des Zwischenspeichers"
     },
     "embedding": {
         "noMatchingEmbedding": "Keine passenden Embeddings",
@@ -1000,10 +1146,151 @@
         "colorCodeEdges": "Farbkodierte Kanten",
         "addNodeToolTip": "Knoten hinzufügen (Umschalt+A, Leertaste)",
         "boardField": "Ordner",
-        "boardFieldDescription": "Ein Galerie Ordner"
+        "boardFieldDescription": "Ein Galerie Ordner",
+        "collectionFieldType": "{{name}} Sammlung",
+        "controlCollectionDescription": "Kontrollinformationen zwischen Knotenpunkten weitergegeben.",
+        "connectionWouldCreateCycle": "Verbindung würde einen Kreislauf/cycle schaffen",
+        "ipAdapterDescription": "Ein Adapter für die Bildabfrage (IP-Adapter) / Bildprompt-Adapter.",
+        "controlField": "Kontrolle",
+        "inputFields": "Eingabefelder",
+        "imageField": "Bild",
+        "inputMayOnlyHaveOneConnection": "Eingang darf nur eine Verbindung haben",
+        "integerCollectionDescription": "Eine Sammlung ganzer Zahlen.",
+        "integerDescription": "\"Integer\" sind ganze Zahlen ohne Dezimalpunkt.",
+        "conditioningPolymorphic": "Konditionierung polymorphisch",
+        "conditioningPolymorphicDescription": "Die Konditionierung kann zwischen den Knoten weitergegeben werden.",
+        "invalidOutputSchema": "Ungültiges Ausgabeschema",
+        "ipAdapterModel": "IP-Adapter Modell",
+        "conditioningFieldDescription": "Die Konditionierung kann zwischen den Knotenpunkten weitergegeben werden.",
+        "ipAdapterCollectionDescription": "Eine Sammlung von IP-Adaptern.",
+        "collectionDescription": "Zu erledigen",
+        "imageFieldDescription": "Bilder können zwischen Knoten weitergegeben werden.",
+        "imagePolymorphic": "Bild Polymorphie",
+        "imagePolymorphicDescription": "Eine Bildersammlung.",
+        "inputField": "Eingabefeld",
+        "hideLegendNodes": "Feldtyp-Legende ausblenden",
+        "collectionItemDescription": "Zu erledigen",
+        "inputNode": "Eingangsknoten",
+        "integer": "Ganze Zahl",
+        "integerCollection": "Ganzzahlige Sammlung",
+        "addLinearView": "Zur linearen Ansicht hinzufügen",
+        "currentImageDescription": "Zeigt das aktuelle Bild im Node-Editor an",
+        "ipAdapter": "IP-Adapter",
+        "hideMinimapnodes": "Miniatur-Kartenansicht ausblenden",
+        "imageCollection": "Bildersammlung",
+        "imageCollectionDescription": "Eine Sammlung von Bildern.",
+        "denoiseMaskField": "Entrauschen-Maske",
+        "ipAdapterCollection": "IP-Adapter Sammlung",
+        "newWorkflowDesc2": "Ihr aktueller Arbeitsablauf hat ungespeicherte Änderungen.",
+        "problemSettingTitle": "Problem beim Einstellen des Titels",
+        "noConnectionData": "Keine Verbindungsdaten",
+        "outputField": "Ausgabefeld",
+        "outputFieldInInput": "Ausgabefeld im Eingang",
+        "problemReadingWorkflow": "Problem beim Lesen des Arbeitsablaufs vom Bild",
+        "reloadNodeTemplates": "Knoten-Vorlagen neu laden",
+        "newWorkflow": "Neuer Arbeitsablauf / Workflow",
+        "newWorkflowDesc": "Einen neuen Arbeitsablauf erstellen?",
+        "noFieldsLinearview": "Keine Felder zur linearen Ansicht hinzugefügt",
+        "clearWorkflow": "Workflow löschen",
+        "clearWorkflowDesc": "Diesen Arbeitsablauf löschen und neu starten?",
+        "noConnectionInProgress": "Es besteht keine Verbindung",
+        "notes": "Anmerkungen",
+        "nodeVersion": "Knoten Version",
+        "noOutputSchemaName": "Kein Name des Ausgabeschemas im ref-Objekt gefunden",
+        "node": "Knoten",
+        "nodeSearch": "Knoten suchen",
+        "removeLinearView": "Entfernen aus Linear View",
+        "nodeOutputs": "Knoten-Ausgänge",
+        "nodeTemplate": "Knoten-Vorlage",
+        "nodeType": "Knotentyp",
+        "noFieldType": "Kein Feldtyp",
+        "oNNXModelField": "ONNX-Modell",
+        "noMatchingNodes": "Keine passenden Knoten",
+        "noNodeSelected": "Kein Knoten gewählt",
+        "noImageFoundState": "Kein Anfangsbild im Status gefunden",
+        "nodeOpacity": "Knoten-Deckkraft",
+        "noOutputRecorded": "Keine Ausgänge aufgezeichnet",
+        "outputSchemaNotFound": "Ausgabeschema nicht gefunden",
+        "oNNXModelFieldDescription": "ONNX-Modellfeld.",
+        "outputNode": "Ausgabeknoten",
+        "pickOne": "Eins auswählen",
+        "problemReadingMetadata": "Problem beim Lesen von Metadaten aus dem Bild",
+        "notesDescription": "Anmerkungen zum Arbeitsablauf hinzufügen",
+        "outputFields": "Ausgabefelder",
+        "sDXLRefinerModelField": "Refiner-Modell",
+        "sDXLMainModelFieldDescription": "SDXL Modellfeld.",
+        "clearWorkflowDesc2": "Ihr aktueller Arbeitsablauf hat ungespeicherte Änderungen.",
+        "skipped": "Übersprungen",
+        "schedulerDescription": "Zu erledigen",
+        "scheduler": "Planer",
+        "showGraphNodes": "Graph Overlay anzeigen",
+        "showMinimapnodes": "MiniMap anzeigen",
+        "sDXLMainModelField": "SDXL Modell",
+        "skippedReservedInput": "Reserviertes Eingabefeld übersprungen",
+        "sDXLRefinerModelFieldDescription": "Zu erledigen",
+        "showLegendNodes": "Feldtyp-Legende anzeigen",
+        "skippedReservedOutput": "Reserviertes Ausgangsfeld übersprungen",
+        "skippingInputNoTemplate": "Überspringe Eingabefeld ohne Vorlage",
+        "executionStateCompleted": "Erledigt",
+        "denoiseMaskFieldDescription": "Denoise Maske kann zwischen Knoten weitergegeben werden",
+        "downloadWorkflow": "Workflow JSON herunterladen",
+        "executionStateInProgress": "In Bearbeitung",
+        "snapToGridHelp": "Knoten am Gitternetz einrasten bei Bewegung",
+        "controlCollection": "Control-Sammlung",
+        "controlFieldDescription": "Control-Informationen zwischen Knotenpunkten weitergegeben.",
+        "latentsField": "Latents",
+        "mainModelFieldDescription": "Zu erledigen",
+        "missingTemplate": "Ungültiger Knoten: Knoten {{node}} vom Typ {{type}} fehlt Vorlage (nicht installiert?)",
+        "skippingUnknownInputType": "Überspringe unbekannten Eingabe-Feldtyp",
+        "stringCollectionDescription": "Eine Sammlung von Zeichenfolgen.",
+        "string": "Zeichenfolge",
+        "stringCollection": "Sammlung von Zeichenfolgen",
+        "stringDescription": "Zeichenfolgen (Strings) sind Text.",
+        "fieldTypesMustMatch": "Feldtypen müssen übereinstimmen",
+        "fitViewportNodes": "An Ansichtsgröße anpassen",
+        "missingCanvaInitMaskImages": "Fehlende Startbilder und Masken auf der Leinwand",
+        "missingCanvaInitImage": "Fehlendes Startbild auf der Leinwand",
+        "ipAdapterModelDescription": "IP-Adapter-Modellfeld",
+        "latentsPolymorphicDescription": "Zwischen Nodes können Latents weitergegeben werden.",
+        "loadingNodes": "Lade Nodes...",
+        "latentsCollectionDescription": "Zwischen Knoten können Latents weitergegeben werden.",
+        "mismatchedVersion": "Ungültiger Knoten: Knoten {{node}} vom Typ {{type}} hat keine passende Version (Update versuchen?)",
+        "colorCollectionDescription": "Zu erledigen",
+        "ipAdapterPolymorphicDescription": "Eine Sammlung von IP-Adaptern.",
+        "fullyContainNodesHelp": "Nodes müssen vollständig innerhalb der Auswahlbox sein, um ausgewählt werden zu können",
+        "latentsFieldDescription": "Zwischen Nodes können Latents weitergegeben werden.",
+        "noWorkflow": "Kein Workflow",
+        "hideGraphNodes": "Graph Overlay verbergen",
+        "sourceNode": "Quellknoten",
+        "executionStateError": "Fehler",
+        "latentsCollection": "Latents Sammlung",
+        "maybeIncompatible": "Möglicherweise inkompatibel mit installierten",
+        "nodePack": "Knoten-Pack",
+        "skippingUnknownOutputType": "Überspringe unbekannten Ausgabe-Feldtyp",
+        "loadWorkflow": "Lade Workflow",
+        "snapToGrid": "Am Gitternetz einrasten",
+        "skippingReservedFieldType": "Überspringe reservierten Feldtyp",
+        "loRAModelField": "LoRA",
+        "loRAModelFieldDescription": "Zu erledigen",
+        "mainModelField": "Modell",
+        "doesNotExist": "existiert nicht",
+        "vaeField": "VAE",
+        "unknownOutput": "Unbekannte Ausgabe: {{name}}",
+        "updateNode": "Knoten updaten",
+        "edge": "Rand / Kante",
+        "sourceNodeDoesNotExist": "Ungültiger Rand: Quell- / Ausgabe-Knoten {{node}} existiert nicht",
+        "updateAllNodes": "Update Knoten",
+        "allNodesUpdated": "Alle Knoten aktualisiert",
+        "unknownTemplate": "Unbekannte Vorlage",
+        "floatDescription": "Floats sind Zahlen mit einem Dezimalpunkt.",
+        "updateApp": "Update App",
+        "vaeFieldDescription": "VAE Submodell.",
+        "unknownInput": "Unbekannte Eingabe: {{name}}",
+        "unknownNodeType": "Unbekannter Knotentyp",
+        "float": "Kommazahlen"
     },
     "hrf": {
-        "enableHrf": "Aktivieren Sie die Korrektur für hohe Auflösungen",
+        "enableHrf": "Korrektur für hohe Auflösungen",
         "upscaleMethod": "Vergrößerungsmethoden",
         "enableHrfTooltip": "Generieren Sie mit einer niedrigeren Anfangsauflösung, skalieren Sie auf die Basisauflösung hoch und führen Sie dann Image-to-Image aus.",
         "metadata": {
@@ -1026,7 +1313,14 @@
         "noLoRAsInstalled": "Keine LoRAs installiert",
         "selectLoRA": "Wählen ein LoRA aus",
         "esrganModel": "ESRGAN Modell",
-        "addLora": "LoRA hinzufügen"
+        "addLora": "LoRA hinzufügen",
+        "defaultVAE": "Standard VAE",
+        "noLoRAsLoaded": "Keine LoRAs geladen",
+        "lora": "LoRA",
+        "allLoRAsAdded": "Alle LoRAs hinzugefügt",
+        "incompatibleBaseModel": "Inkompatibles Basismodell",
+        "noMainModelSelected": "Kein Hauptmodell ausgewählt",
+        "loraAlreadyAdded": "LoRA bereits hinzugefügt"
     },
     "accordions": {
         "generation": {
@@ -1050,5 +1344,40 @@
             "infillTab": "Füllung",
             "title": "Compositing"
         }
+    },
+    "workflows": {
+        "workflows": "Arbeitsabläufe",
+        "noSystemWorkflows": "Keine System-Arbeitsabläufe",
+        "workflowName": "Arbeitsablauf-Name",
+        "workflowIsOpen": "Arbeitsablauf ist geöffnet",
+        "saveWorkflowAs": "Arbeitsablauf speichern als",
+        "searchWorkflows": "Suche Arbeitsabläufe",
+        "newWorkflowCreated": "Neuer Arbeitsablauf erstellt",
+        "problemSavingWorkflow": "Problem beim Speichern des Arbeitsablaufs",
+        "noRecentWorkflows": "Keine kürzlichen Arbeitsabläufe",
+        "problemLoading": "Problem beim Laden von Arbeitsabläufen",
+        "downloadWorkflow": "Speichern als",
+        "savingWorkflow": "Speichere Arbeitsablauf...",
+        "saveWorkflow": "Arbeitsablauf speichern",
+        "noWorkflows": "Keine Arbeitsabläufe",
+        "workflowLibrary": "Bibliothek",
+        "defaultWorkflows": "Standard-Arbeitsabläufe",
+        "unnamedWorkflow": "Unbenannter Arbeitsablauf",
+        "noDescription": "Keine Beschreibung",
+        "clearWorkflowSearchFilter": "Suchfilter zurücksetzen",
+        "workflowEditorMenu": "Arbeitsablauf-Editor Menü",
+        "deleteWorkflow": "Arbeitsablauf löschen",
+        "userWorkflows": "Meine Arbeitsabläufe",
+        "workflowSaved": "Arbeitsablauf gespeichert",
+        "uploadWorkflow": "Aus Datei laden",
+        "projectWorkflows": "Projekt-Arbeitsabläufe",
+        "openWorkflow": "Arbeitsablauf öffnen",
+        "noUserWorkflows": "Keine Benutzer-Arbeitsabläufe",
+        "saveWorkflowToProject": "Arbeitsablauf in Projekt speichern",
+        "workflowCleared": "Arbeitsablauf gelöscht",
+        "loading": "Lade Arbeitsabläufe"
+    },
+    "app": {
+        "storeNotInitialized": "App-Store ist nicht initialisiert"
     }
 }

invokeai/frontend/web/public/locales/en.json

@@ -175,6 +175,7 @@
         "statusUpscaling": "Upscaling",
         "statusUpscalingESRGAN": "Upscaling (ESRGAN)",
         "template": "Template",
+        "toResolve": "To resolve",
         "training": "Training",
         "trainingDesc1": "A dedicated workflow for training your own embeddings and checkpoints using Textual Inversion and Dreambooth from the web interface.",
         "trainingDesc2": "InvokeAI already supports training custom embeddourings using Textual Inversion using the main script.",
@@ -235,6 +236,9 @@
         "fill": "Fill",
         "h": "H",
         "handAndFace": "Hand and Face",
+        "face": "Face",
+        "body": "Body",
+        "hands": "Hands",
         "hed": "HED",
         "hedDescription": "Holistically-Nested Edge Detection",
         "hideAdvanced": "Hide Advanced",
@@ -261,8 +265,8 @@
         "noneDescription": "No processing applied",
         "normalBae": "Normal BAE",
         "normalBaeDescription": "Normal BAE processing",
-        "openPose": "Openpose",
-        "openPoseDescription": "Human pose estimation using Openpose",
+        "dwOpenpose": "DW Openpose",
+        "dwOpenposeDescription": "Human pose estimation using DW Openpose",
         "pidi": "PIDI",
         "pidiDescription": "PIDI image processing",
         "processor": "Processor",
@@ -897,6 +901,7 @@
         "doesNotExist": "does not exist",
         "downloadWorkflow": "Download Workflow JSON",
         "edge": "Edge",
+        "editMode": "Edit in Workflow Editor",
         "enum": "Enum",
         "enumDescription": "Enums are values that may be one of a number of options.",
         "executionStateCompleted": "Completed",
@@ -992,8 +997,10 @@
         "problemReadingMetadata": "Problem reading metadata from image",
         "problemReadingWorkflow": "Problem reading workflow from image",
         "problemSettingTitle": "Problem Setting Title",
+        "resetToDefaultValue": "Reset to default value",
         "reloadNodeTemplates": "Reload Node Templates",
         "removeLinearView": "Remove from Linear View",
+        "reorderLinearView": "Reorder Linear View",
         "newWorkflow": "New Workflow",
         "newWorkflowDesc": "Create a new workflow?",
         "newWorkflowDesc2": "Your current workflow has unsaved changes.",
@@ -1064,6 +1071,7 @@
         "vaeModelFieldDescription": "TODO",
         "validateConnections": "Validate Connections and Graph",
         "validateConnectionsHelp": "Prevent invalid connections from being made, and invalid graphs from being invoked",
+        "viewMode": "Use in Linear View",
         "unableToGetWorkflowVersion": "Unable to get workflow schema version",
         "unrecognizedWorkflowVersion": "Unrecognized workflow schema version {{version}}",
         "version": "Version",

invokeai/frontend/web/public/locales/it.json

@@ -795,7 +795,8 @@
         "workflowDeleted": "Flusso di lavoro eliminato",
         "problemRetrievingWorkflow": "Problema nel recupero del flusso di lavoro",
         "resetInitialImage": "Reimposta l'immagine iniziale",
-        "uploadInitialImage": "Carica l'immagine iniziale"
+        "uploadInitialImage": "Carica l'immagine iniziale",
+        "problemDownloadingImage": "Impossibile scaricare l'immagine"
     },
     "tooltip": {
         "feature": {
@@ -1134,7 +1135,10 @@
         "newWorkflow": "Nuovo flusso di lavoro",
         "newWorkflowDesc": "Creare un nuovo flusso di lavoro?",
         "newWorkflowDesc2": "Il flusso di lavoro attuale presenta modifiche non salvate.",
-        "unsupportedAnyOfLength": "unione di troppi elementi ({{count}})"
+        "unsupportedAnyOfLength": "unione di troppi elementi ({{count}})",
+        "clearWorkflowDesc": "Cancellare questo flusso di lavoro e avviarne uno nuovo?",
+        "clearWorkflow": "Cancella il flusso di lavoro",
+        "clearWorkflowDesc2": "Il tuo flusso di lavoro attuale presenta modifiche non salvate."
     },
     "boards": {
         "autoAddBoard": "Aggiungi automaticamente bacheca",
@@ -1191,7 +1195,6 @@
         "f": "F",
         "h": "A",
         "prompt": "Prompt",
-        "openPoseDescription": "Stima della posa umana utilizzando Openpose",
         "resizeMode": "Ridimensionamento",
         "weight": "Peso",
         "selectModel": "Seleziona un modello",
@@ -1672,7 +1675,9 @@
         "downloadWorkflow": "Salva su file",
         "uploadWorkflow": "Carica da file",
         "projectWorkflows": "Flussi di lavoro del progetto",
-        "noWorkflows": "Nessun flusso di lavoro"
+        "noWorkflows": "Nessun flusso di lavoro",
+        "workflowCleared": "Flusso di lavoro cancellato",
+        "saveWorkflowToProject": "Salva flusso di lavoro nel progetto"
     },
     "app": {
         "storeNotInitialized": "Il negozio non è inizializzato"

invokeai/frontend/web/public/locales/ja.json

@@ -555,7 +555,6 @@
         "balanced": "バランス",
         "prompt": "プロンプト",
         "depthMidasDescription": "Midasを使用して深度マップを生成",
-        "openPoseDescription": "Openposeを使用してポーズを推定",
         "control": "コントロール",
         "resizeMode": "リサイズモード",
         "weight": "重み",

invokeai/frontend/web/public/locales/ko.json

@@ -333,7 +333,6 @@
         "h": "H",
         "prompt": "프롬프트",
         "depthMidasDescription": "Midas를 사용하여 Depth map 생성하기",
-        "openPoseDescription": "Openpose를 이용한 사람 포즈 추정",
         "control": "Control",
         "resizeMode": "크기 조정 모드",
         "t2iEnabledControlNetDisabled": "$t(common.t2iAdapter) 사용 가능,$t(common.controlNet) 사용 불가능",
@@ -370,7 +369,6 @@
         "normalBaeDescription": "Normal BAE 처리",
         "noneDescription": "처리되지 않음",
         "saveControlImage": "Control Image 저장",
-        "openPose": "Openpose",
         "toggleControlNet": "해당 ControlNet으로 전환",
         "delete": "삭제",
         "controlAdapter_other": "Control Adapter(s)",

invokeai/frontend/web/public/locales/nl.json

@@ -1033,7 +1033,6 @@
         "prompt": "Prompt",
         "depthMidasDescription": "Genereer diepteblad via Midas",
         "controlnet": "$t(controlnet.controlAdapter_one) #{{number}} ($t(common.controlNet))",
-        "openPoseDescription": "Menselijke pose-benadering via Openpose",
         "control": "Controle",
         "resizeMode": "Modus schaling",
         "t2iEnabledControlNetDisabled": "$t(common.t2iAdapter) ingeschakeld, $t(common.controlNet)s uitgeschakeld",
@@ -1072,7 +1071,6 @@
         "normalBaeDescription": "Normale BAE-verwerking",
         "noneDescription": "Geen verwerking toegepast",
         "saveControlImage": "Bewaar controle-afbeelding",
-        "openPose": "Openpose",
         "toggleControlNet": "Zet deze ControlNet aan/uit",
         "delete": "Verwijder",
         "controlAdapter_one": "Control-adapter",

invokeai/frontend/web/public/locales/ru.json

@@ -1155,7 +1155,6 @@
         "resetControlImage": "Сбросить контрольное изображение",
         "prompt": "Запрос",
         "controlnet": "$t(controlnet.controlAdapter_one) №{{number}} $t(common.controlNet)",
-        "openPoseDescription": "Оценка позы человека с помощью Openpose",
         "resizeMode": "Режим изменения размера",
         "t2iEnabledControlNetDisabled": "$t(common.t2iAdapter) включен, $t(common.controlNet)s отключен",
         "weight": "Вес",

invokeai/frontend/web/public/locales/tr.json

@@ -259,7 +259,6 @@
         "mediapipeFace": "Mediapipe Yüz",
         "megaControl": "Aşırı Yönetim",
         "mlsd": "M-LSD",
-        "openPoseDescription": "Openpose kullanarak poz belirleme",
         "setControlImageDimensions": "Yönetim Görseli Boyutlarını En/Boydan Al",
         "pidi": "PIDI",
         "scribble": "çiziktirme",
@@ -273,7 +272,6 @@
         "mlsdDescription": "Minimalist Line Segment Detector (Kolay Çizgi Parçası Algılama)",
         "normalBae": "Normal BAE",
         "normalBaeDescription": "Normal BAE işleme",
-        "openPose": "Openpose",
         "resetControlImage": "Yönetim Görselini Kaldır",
         "enableIPAdapter": "IP Aracını Etkinleştir",
         "lineart": "Çizim",