[nodes] Add cancelation to the API

.coveragerc

@@ -0,0 +1,6 @@
+[run]
+omit='.env/*'
+source='.'
+
+[report]
+show_missing = true

.github/CODEOWNERS

@@ -1,16 +1,16 @@
 # continuous integration
-/.github/workflows/ @mauwii @lstein @blessedcoolant
+/.github/workflows/ @mauwii @lstein
 
 # documentation
-/docs/ @lstein @mauwii @tildebyte @blessedcoolant
-/mkdocs.yml @lstein @mauwii @blessedcoolant
+/docs/ @lstein @mauwii @tildebyte
+/mkdocs.yml @lstein @mauwii
 
 # nodes
 /invokeai/app/ @Kyle0654 @blessedcoolant
 
 # installation and configuration
 /pyproject.toml @mauwii @lstein @blessedcoolant
-/docker/ @mauwii @lstein @blessedcoolant
+/docker/ @mauwii @lstein
 /scripts/ @ebr @lstein
 /installer/ @lstein @ebr
 /invokeai/assets @lstein @ebr

.github/stale.yaml

@@ -1,19 +0,0 @@
-# Number of days of inactivity before an issue becomes stale
-daysUntilStale: 28
-# Number of days of inactivity before a stale issue is closed
-daysUntilClose: 14
-# Issues with these labels will never be considered stale
-exemptLabels:
-  - pinned
-  - security
-# Label to use when marking an issue as stale
-staleLabel: stale
-# Comment to post when marking an issue as stale. Set to `false` to disable
-markComment: >
-  This issue has been automatically marked as stale because it has not had
-  recent activity. It will be closed if no further activity occurs. Please
-  update the ticket if this is still a problem on the latest release.
-# Comment to post when closing a stale issue. Set to `false` to disable
-closeComment: >
-  Due to inactivity, this issue has been automatically closed. If this is
-  still a problem on the latest release, please recreate the issue.

.github/workflows/build-container.yml

@@ -16,10 +16,6 @@ on:
       - 'v*.*.*'
   workflow_dispatch:
 
-permissions:
-  contents: write
-  packages: write
-
 jobs:
   docker:
     if: github.event.pull_request.draft == false

.github/workflows/mkdocs-material.yml

@@ -5,9 +5,6 @@ on:
       - 'main'
       - 'development'
 
-permissions:
-    contents: write
-
 jobs:
   mkdocs-material:
     if: github.event.pull_request.draft == false

.github/workflows/test-invoke-pip-skip.yml

@@ -6,6 +6,7 @@ on:
       - '!pyproject.toml'
       - '!invokeai/**'
       - 'invokeai/frontend/web/**'
+      - '!invokeai/frontend/web/dist/**'
   merge_group:
   workflow_dispatch:
 

.github/workflows/test-invoke-pip.yml

@@ -7,11 +7,13 @@ on:
       - 'pyproject.toml'
       - 'invokeai/**'
       - '!invokeai/frontend/web/**'
+      - 'invokeai/frontend/web/dist/**'
   pull_request:
     paths:
       - 'pyproject.toml'
       - 'invokeai/**'
       - '!invokeai/frontend/web/**'
+      - 'invokeai/frontend/web/dist/**'
     types:
       - 'ready_for_review'
       - 'opened'

.gitignore

@@ -63,7 +63,6 @@ pip-delete-this-directory.txt
 htmlcov/
 .tox/
 .nox/
-.coveragerc
 .coverage
 .coverage.*
 .cache
@@ -74,7 +73,6 @@ cov.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
-.pytest.ini
 cover/
 junit/
 

.pytest.ini

@@ -0,0 +1,5 @@
+[pytest]
+DJANGO_SETTINGS_MODULE = webtas.settings
+; python_files = tests.py test_*.py *_tests.py
+
+addopts = --cov=. --cov-config=.coveragerc --cov-report xml:cov.xml

README.md

@@ -139,13 +139,13 @@ not supported.
     _For Windows/Linux with an NVIDIA GPU:_
 
     ```terminal
-    pip install "InvokeAI[xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
+    pip install InvokeAI[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
     ```
 
     _For Linux with an AMD GPU:_
 
     ```sh
-    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.2
     ```
 
     _For Macintoshes, either Intel or M1/M2:_

coverage/.gitignore

@@ -1,4 +0,0 @@
-# Ignore everything in this directory
-*
-# Except this file
-!.gitignore

docs/contributing/INVOCATIONS.md

@@ -1,18 +1,10 @@
 # Invocations
 
-Invocations represent a single operation, its inputs, and its outputs. These
-operations and their outputs can be chained together to generate and modify
-images.
+Invocations represent a single operation, its inputs, and its outputs. These operations and their outputs can be chained together to generate and modify images.
 
 ## Creating a new invocation
 
-To create a new invocation, either find the appropriate module file in
-`/ldm/invoke/app/invocations` to add your invocation to, or create a new one in
-that folder. All invocations in that folder will be discovered and made
-available to the CLI and API automatically. Invocations make use of
-[typing](https://docs.python.org/3/library/typing.html) and
-[pydantic](https://pydantic-docs.helpmanual.io/) for validation and integration
-into the CLI and API.
+To create a new invocation, either find the appropriate module file in `/ldm/invoke/app/invocations` to add your invocation to, or create a new one in that folder. All invocations in that folder will be discovered and made available to the CLI and API automatically. Invocations make use of [typing](https://docs.python.org/3/library/typing.html) and [pydantic](https://pydantic-docs.helpmanual.io/) for validation and integration into the CLI and API.
 
 An invocation looks like this:
 
@@ -49,54 +41,34 @@ class UpscaleInvocation(BaseInvocation):
 Each portion is important to implement correctly.
 
 ### Class definition and type
-
 ```py
 class UpscaleInvocation(BaseInvocation):
     """Upscales an image."""
     type: Literal['upscale'] = 'upscale'
 ```
-
-All invocations must derive from `BaseInvocation`. They should have a docstring
-that declares what they do in a single, short line. They should also have a
-`type` with a type hint that's `Literal["command_name"]`, where `command_name`
-is what the user will type on the CLI or use in the API to create this
-invocation. The `command_name` must be unique. The `type` must be assigned to
-the value of the literal in the type hint.
+All invocations must derive from `BaseInvocation`. They should have a docstring that declares what they do in a single, short line. They should also have a `type` with a type hint that's `Literal["command_name"]`, where `command_name` is what the user will type on the CLI or use in the API to create this invocation. The `command_name` must be unique. The `type` must be assigned to the value of the literal in the type hint.
 
 ### Inputs
-
 ```py
     # Inputs
     image: Union[ImageField,None] = Field(description="The input image")
     strength: float               = Field(default=0.75, gt=0, le=1, description="The strength")
     level: Literal[2,4]           = Field(default=2, description="The upscale level")
 ```
+Inputs consist of three parts: a name, a type hint, and a `Field` with default, description, and validation information. For example:
+| Part | Value | Description |
+| ---- | ----- | ----------- |
+| Name | `strength` | This field is referred to as `strength` |
+| Type Hint | `float` | This field must be of type `float` |
+| Field | `Field(default=0.75, gt=0, le=1, description="The strength")` | The default value is `0.75`, the value must be in the range (0,1], and help text will show "The strength" for this field. |
 
-Inputs consist of three parts: a name, a type hint, and a `Field` with default,
-description, and validation information. For example:
+Notice that `image` has type `Union[ImageField,None]`. The `Union` allows this field to be parsed with `None` as a value, which enables linking to previous invocations. All fields should either provide a default value or allow `None` as a value, so that they can be overwritten with a linked output from another invocation.
 
-| Part      | Value                                                         | Description                                                                                                               |
-| --------- | ------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------- |
-| Name      | `strength`                                                    | This field is referred to as `strength`                                                                                   |
-| Type Hint | `float`                                                       | This field must be of type `float`                                                                                        |
-| Field     | `Field(default=0.75, gt=0, le=1, description="The strength")` | The default value is `0.75`, the value must be in the range (0,1], and help text will show "The strength" for this field. |
+The special type `ImageField` is also used here. All images are passed as `ImageField`, which protects them from pydantic validation errors (since images only ever come from links).
 
-Notice that `image` has type `Union[ImageField,None]`. The `Union` allows this
-field to be parsed with `None` as a value, which enables linking to previous
-invocations. All fields should either provide a default value or allow `None` as
-a value, so that they can be overwritten with a linked output from another
-invocation.
-
-The special type `ImageField` is also used here. All images are passed as
-`ImageField`, which protects them from pydantic validation errors (since images
-only ever come from links).
-
-Finally, note that for all linking, the `type` of the linked fields must match.
-If the `name` also matches, then the field can be **automatically linked** to a
-previous invocation by name and matching.
+Finally, note that for all linking, the `type` of the linked fields must match. If the `name` also matches, then the field can be **automatically linked** to a previous invocation by name and matching.
 
 ### Invoke Function
-
 ```py
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get(self.image.image_type, self.image.image_name)
@@ -116,22 +88,13 @@ previous invocation by name and matching.
             image = ImageField(image_type = image_type, image_name = image_name)
         )
 ```
+The `invoke` function is the last portion of an invocation. It is provided an `InvocationContext` which contains services to perform work as well as a `session_id` for use as needed. It should return a class with output values that derives from `BaseInvocationOutput`.
 
-The `invoke` function is the last portion of an invocation. It is provided an
-`InvocationContext` which contains services to perform work as well as a
-`session_id` for use as needed. It should return a class with output values that
-derives from `BaseInvocationOutput`.
+Before being called, the invocation will have all of its fields set from defaults, inputs, and finally links (overriding in that order).
 
-Before being called, the invocation will have all of its fields set from
-defaults, inputs, and finally links (overriding in that order).
-
-Assume that this invocation may be running simultaneously with other
-invocations, may be running on another machine, or in other interesting
-scenarios. If you need functionality, please provide it as a service in the
-`InvocationServices` class, and make sure it can be overridden.
+Assume that this invocation may be running simultaneously with other invocations, may be running on another machine, or in other interesting scenarios. If you need functionality, please provide it as a service in the `InvocationServices` class, and make sure it can be overridden.
 
 ### Outputs
-
 ```py
 class ImageOutput(BaseInvocationOutput):
     """Base class for invocations that output an image"""
@@ -139,64 +102,4 @@ class ImageOutput(BaseInvocationOutput):
 
     image: ImageField = Field(default=None, description="The output image")
 ```
-
-Output classes look like an invocation class without the invoke method. Prefer
-to use an existing output class if available, and prefer to name inputs the same
-as outputs when possible, to promote automatic invocation linking.
-
-## Schema Generation
-
-Invocation, output and related classes are used to generate an OpenAPI schema.
-
-### Required Properties
-
-The schema generation treat all properties with default values as optional. This
-makes sense internally, but when when using these classes via the generated
-schema, we end up with e.g. the `ImageOutput` class having its `image` property
-marked as optional.
-
-We know that this property will always be present, so the additional logic
-needed to always check if the property exists adds a lot of extraneous cruft.
-
-To fix this, we can leverage `pydantic`'s
-[schema customisation](https://docs.pydantic.dev/usage/schema/#schema-customization)
-to mark properties that we know will always be present as required.
-
-Here's that `ImageOutput` class, without the needed schema customisation:
-
-```python
-class ImageOutput(BaseInvocationOutput):
-    """Base class for invocations that output an image"""
-
-    type: Literal["image"] = "image"
-    image:      ImageField = Field(default=None, description="The output image")
-```
-
-The generated OpenAPI schema, and all clients/types generated from it, will have
-the `type` and `image` properties marked as optional, even though we know they
-will always have a value by the time we can interact with them via the API.
-
-Here's the same class, but with the schema customisation added:
-
-```python
-class ImageOutput(BaseInvocationOutput):
-    """Base class for invocations that output an image"""
-
-    type: Literal["image"] = "image"
-    image:      ImageField = Field(default=None, description="The output image")
-
-    class Config:
-        schema_extra = {
-            'required': [
-                'type',
-                'image',
-            ]
-        }
-```
-
-The resultant schema (and any API client or types generated from it) will now
-have see `type` as string literal `"image"` and `image` as an `ImageField`
-object.
-
-See this `pydantic` issue for discussion on this solution:
-<https://github.com/pydantic/pydantic/discussions/4577>
+Output classes look like an invocation class without the invoke method. Prefer to use an existing output class if available, and prefer to name inputs the same as outputs when possible, to promote automatic invocation linking.

docs/contributing/LOCAL_DEVELOPMENT.md

@@ -1,83 +0,0 @@
-# Local Development
-
-If you are looking to contribute you will need to have a local development
-environment. See the
-[Developer Install](../installation/020_INSTALL_MANUAL.md#developer-install) for
-full details.
-
-Broadly this involves cloning the repository, installing the pre-reqs, and
-InvokeAI (in editable form). Assuming this is working, choose your area of
-focus.
-
-## Documentation
-
-We use [mkdocs](https://www.mkdocs.org) for our documentation with the
-[material theme](https://squidfunk.github.io/mkdocs-material/). Documentation is
-written in markdown files under the `./docs` folder and then built into a static
-website for hosting with GitHub Pages at
-[invoke-ai.github.io/InvokeAI](https://invoke-ai.github.io/InvokeAI).
-
-To contribute to the documentation you'll need to install the dependencies. Note
-the use of `"`.
-
-```zsh
-pip install ".[docs]"
-```
-
-Now, to run the documentation locally with hot-reloading for changes made.
-
-```zsh
-mkdocs serve
-```
-
-You'll then be prompted to connect to `http://127.0.0.1:8080` in order to
-access.
-
-## Backend
-
-The backend is contained within the `./invokeai/backend` folder structure. To
-get started however please install the development dependencies.
-
-From the root of the repository run the following command. Note the use of `"`.
-
-```zsh
-pip install ".[test]"
-```
-
-This in an optional group of packages which is defined within the
-`pyproject.toml` and will be required for testing the changes you make the the
-code.
-
-### Running Tests
-
-We use [pytest](https://docs.pytest.org/en/7.2.x/) for our test suite. Tests can
-be found under the `./tests` folder and can be run with a single `pytest`
-command. Optionally, to review test coverage you can append `--cov`.
-
-```zsh
-pytest --cov
-```
-
-Test outcomes and coverage will be reported in the terminal. In addition a more
-detailed report is created in both XML and HTML format in the `./coverage`
-folder. The HTML one in particular can help identify missing statements
-requiring tests to ensure coverage. This can be run by opening
-`./coverage/html/index.html`.
-
-For example.
-
-```zsh
-pytest --cov; open ./coverage/html/index.html
-```
-
-??? info "HTML coverage report output"
-
-    ![html-overview](../assets/contributing/html-overview.png)
-
-    ![html-detail](../assets/contributing/html-detail.png)
-
-## Front End
-
-<!--#TODO: get input from blessedcoolant here, for the moment inserted the frontend README via snippets extension.-->
-
---8<-- "invokeai/frontend/web/README.md"

docs/features/INPAINTING.md

@@ -168,15 +168,11 @@ used by Stable Diffusion 1.4 and 1.5.
 After installation, your `models.yaml` should contain an entry that looks like
 this one:
 
-```yml
-inpainting-1.5:
-  weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
-  description: SD inpainting v1.5
-  config: configs/stable-diffusion/v1-inpainting-inference.yaml
-  vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
-  width: 512
-  height: 512
-```
+inpainting-1.5: weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
+description: SD inpainting v1.5 config:
+configs/stable-diffusion/v1-inpainting-inference.yaml vae:
+models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt width: 512
+height: 512
 
 As shown in the example, you may include a VAE fine-tuning weights file as well.
 This is strongly recommended.

docs/features/PROMPTS.md

@@ -268,7 +268,7 @@ model is so good at inpainting, a good substitute is to use the `clipseg` text
 masking option:
 
 ```bash
-invoke> a fluffy cat eating a hotdog
+invoke> a fluffy cat eating a hotdot
 Outputs:
 [1010] outputs/000025.2182095108.png: a fluffy cat eating a hotdog
 invoke> a smiling dog eating a hotdog -I 000025.2182095108.png -tm cat

docs/features/TEXTUAL_INVERSION.md

@@ -17,7 +17,7 @@ notebooks.
 
 You will need a GPU to perform training in a reasonable length of
 time, and at least 12 GB of VRAM. We recommend using the [`xformers`
-library](../installation/070_INSTALL_XFORMERS.md) to accelerate the
+library](../installation/070_INSTALL_XFORMERS) to accelerate the
 training process further. During training, about ~8 GB is temporarily
 needed in order to store intermediate models, checkpoints and logs.
 

docs/installation/010_INSTALL_AUTOMATED.md

@@ -417,7 +417,7 @@ Then type the following commands:
 
 === "AMD System"
     ```bash
-    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/rocm5.2
     ```
 
 ### Corrupted configuration file

docs/installation/020_INSTALL_MANUAL.md

@@ -154,7 +154,7 @@ manager, please follow these steps:
     === "ROCm (AMD)"
 
         ```bash
-        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.2
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"
@@ -315,7 +315,7 @@ installation protocol (important!)
 
     === "ROCm (AMD)"
         ```bash
-        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.2
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"

docs/installation/030_INSTALL_CUDA_AND_ROCM.md

@@ -110,7 +110,7 @@ recipes are available
 
 When installing torch and torchvision manually with `pip`, remember to provide
 the argument `--extra-index-url
-https://download.pytorch.org/whl/rocm5.4.2` as described in the [Manual
+https://download.pytorch.org/whl/rocm5.2` as described in the [Manual
 Installation Guide](020_INSTALL_MANUAL.md).
 
 This will be done automatically for you if you use the installer

docs/installation/050_INSTALLING_MODELS.md

@@ -50,7 +50,7 @@ subset that are currently installed are found in
 |stable-diffusion-1.5|runwayml/stable-diffusion-v1-5|Stable Diffusion version 1.5 diffusers model (4.27 GB)|https://huggingface.co/runwayml/stable-diffusion-v1-5 |
 |sd-inpainting-1.5|runwayml/stable-diffusion-inpainting|RunwayML SD 1.5 model optimized for inpainting, diffusers version (4.27 GB)|https://huggingface.co/runwayml/stable-diffusion-inpainting |
 |stable-diffusion-2.1|stabilityai/stable-diffusion-2-1|Stable Diffusion version 2.1 diffusers model, trained on 768 pixel images (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-1 |
-|sd-inpainting-2.0|stabilityai/stable-diffusion-2-inpainting|Stable Diffusion version 2.0 inpainting model (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-inpainting |
+|sd-inpainting-2.0|stabilityai/stable-diffusion-2-1|Stable Diffusion version 2.0 inpainting model (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-1 |
 |analog-diffusion-1.0|wavymulder/Analog-Diffusion|An SD-1.5 model trained on diverse analog photographs (2.13 GB)|https://huggingface.co/wavymulder/Analog-Diffusion |
 |deliberate-1.0|XpucT/Deliberate|Versatile model that produces detailed images up to 768px (4.27 GB)|https://huggingface.co/XpucT/Deliberate |
 |d&d-diffusion-1.0|0xJustin/Dungeons-and-Diffusion|Dungeons & Dragons characters (2.13 GB)|https://huggingface.co/0xJustin/Dungeons-and-Diffusion |

docs/installation/060_INSTALL_PATCHMATCH.md

@@ -24,7 +24,7 @@ You need to have opencv installed so that pypatchmatch can be built:
 brew install opencv
 ```
 
-The next time you start `invoke`, after successfully installing opencv, pypatchmatch will be built.
+The next time you start `invoke`, after sucesfully installing opencv, pypatchmatch will be built.
 
 ## Linux
 
@@ -56,7 +56,7 @@ Prior to installing PyPatchMatch, you need to take the following steps:
 
 5. Confirm that pypatchmatch is installed. At the command-line prompt enter
    `python`, and then at the `>>>` line type
-   `from patchmatch import patch_match`: It should look like the following:
+   `from patchmatch import patch_match`: It should look like the follwing:
 
     ```py
     Python 3.9.5 (default, Nov 23 2021, 15:27:38)
@@ -108,4 +108,4 @@ Prior to installing PyPatchMatch, you need to take the following steps:
 
 [**Next, Follow Steps 4-6 from the Debian Section above**](#linux)
 
-If you see no errors you're ready to go!
+If you see no errors, then you're ready to go!

installer/lib/installer.py

@@ -456,7 +456,7 @@ def get_torch_source() -> (Union[str, None],str):
     optional_modules = None
     if OS == "Linux":
         if device == "rocm":
-            url = "https://download.pytorch.org/whl/rocm5.4.2"
+            url = "https://download.pytorch.org/whl/rocm5.2"
         elif device == "cpu":
             url = "https://download.pytorch.org/whl/cpu"
 

installer/templates/invoke.sh.in

@@ -24,9 +24,9 @@ if [ "$(uname -s)" == "Darwin" ]; then
     export PYTORCH_ENABLE_MPS_FALLBACK=1
 fi
 
+while true
+do
 if [ "$0" != "bash" ]; then
-  while true
-  do
     echo "Do you want to generate images using the"
     echo "1. command-line interface"
     echo "2. browser-based UI"
@@ -67,29 +67,29 @@ if [ "$0" != "bash" ]; then
             ;;
         7)
             invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only
-            ;;
-        8)
-            echo "Developer Console:"
+	    ;;
+	8)
+	    echo "Developer Console:"
             file_name=$(basename "${BASH_SOURCE[0]}")
             bash --init-file "$file_name"
             ;;
         9)
-            echo "Update:"
+	    echo "Update:"
             invokeai-update
             ;;
         10)
             invokeai --help
             ;;
-        [qQ])
+	[qQ])
             exit 0
             ;;
         *)
             echo "Invalid selection"
             exit;;
     esac
- done
 else # in developer console
     python --version
     echo "Press ^D to exit"
     export PS1="(InvokeAI) \u@\h \w> "
 fi
+done

invokeai/app/api/dependencies.py

@@ -3,8 +3,6 @@
 import os
 from argparse import Namespace
 
-from ..services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
-
 from ...backend import Globals
 from ..services.model_manager_initializer import get_model_manager
 from ..services.restoration_services import RestorationServices
@@ -56,9 +54,7 @@ class ApiDependencies:
             os.path.join(os.path.dirname(__file__), "../../../../outputs")
         )
 
-        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents'))
-
-        images = DiskImageStorage(f'{output_folder}/images')
+        images = DiskImageStorage(output_folder)
 
         # TODO: build a file/path manager?
         db_location = os.path.join(output_folder, "invokeai.db")
@@ -66,7 +62,6 @@ class ApiDependencies:
         services = InvocationServices(
             model_manager=get_model_manager(config),
             events=events,
-            latents=latents,
             images=images,
             queue=MemoryInvocationQueue(),
             graph_execution_manager=SqliteItemStorage[GraphExecutionState](

invokeai/app/api/models/images.py

@@ -1,14 +0,0 @@
-from pydantic import BaseModel, Field
-
-from invokeai.app.models.image import ImageType
-from invokeai.app.models.metadata import ImageMetadata
-
-
-class ImageResponse(BaseModel):
-    """The response type for images"""
-
-    image_type: ImageType = Field(description="The type of the image")
-    image_name: str = Field(description="The name of the image")
-    image_url: str = Field(description="The url of the image")
-    thumbnail_url: str = Field(description="The url of the image's thumbnail")
-    metadata: ImageMetadata = Field(description="The image's metadata")

invokeai/app/api/routers/images.py

@@ -1,23 +1,18 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
-import io
-from datetime import datetime, timezone
-import json
-import os
-import uuid
 
-from fastapi import Path, Query, Request, UploadFile
+from datetime import datetime, timezone
+
+from fastapi import Path, Request, UploadFile
 from fastapi.responses import FileResponse, Response
 from fastapi.routing import APIRouter
 from PIL import Image
-from invokeai.app.api.models.images import ImageResponse
-from invokeai.app.models.metadata import ImageMetadata
-from invokeai.app.services.item_storage import PaginatedResults
 
 from ...services.image_storage import ImageType
 from ..dependencies import ApiDependencies
 
 images_router = APIRouter(prefix="/v1/images", tags=["images"])
 
+
 @images_router.get("/{image_type}/{image_name}", operation_id="get_image")
 async def get_image(
     image_type: ImageType = Path(description="The type of image to get"),
@@ -28,75 +23,34 @@ async def get_image(
     filename = ApiDependencies.invoker.services.images.get_path(image_type, image_name)
     return FileResponse(filename)
 
-@images_router.get("/{image_type}/thumbnails/{image_name}", operation_id="get_thumbnail")
-async def get_thumbnail(
-    image_type: ImageType = Path(description="The type of image to get"),
-    image_name: str = Path(description="The name of the image to get"),
-):
-    """Gets a thumbnail"""
-    # TODO: This is not really secure at all. At least make sure only output results are served
-    filename = ApiDependencies.invoker.services.images.get_path(image_type, 'thumbnails/' + image_name)
-    return FileResponse(filename)
-
 
 @images_router.post(
     "/uploads/",
     operation_id="upload_image",
     responses={
-        201: {"description": "The image was uploaded successfully", "model": ImageResponse},
+        201: {"description": "The image was uploaded successfully"},
         404: {"description": "Session not found"},
     },
-    status_code=201
 )
-async def upload_image(file: UploadFile, request: Request, response: Response) -> ImageResponse:
+async def upload_image(file: UploadFile, request: Request):
     if not file.content_type.startswith("image"):
         return Response(status_code=415)
 
     contents = await file.read()
     try:
-        img = Image.open(io.BytesIO(contents))
+        im = Image.open(contents)
     except:
         # Error opening the image
         return Response(status_code=415)
 
-    filename = f"{uuid.uuid4()}_{str(int(datetime.now(timezone.utc).timestamp()))}.png"
-    image_path = ApiDependencies.invoker.services.images.save(ImageType.UPLOAD, filename, img)
-    invokeai_metadata = json.loads(img.info.get("invokeai", "{}"))
+    filename = f"{str(int(datetime.now(timezone.utc).timestamp()))}.png"
+    ApiDependencies.invoker.services.images.save(ImageType.UPLOAD, filename, im)
 
-    res = ImageResponse(
-        image_type=ImageType.UPLOAD,
-        image_name=filename,
-        # TODO: DiskImageStorage should not be building URLs...?
-        image_url=f"api/v1/images/{ImageType.UPLOAD.value}/{filename}",
-        thumbnail_url=f"api/v1/images/{ImageType.UPLOAD.value}/thumbnails/{os.path.splitext(filename)[0]}.webp",
-        # TODO: Creation of this object should happen elsewhere, just making it fit here so it works
-        metadata=ImageMetadata(
-            created=int(os.path.getctime(image_path)),
-            width=img.width,
-            height=img.height,
-            invokeai=invokeai_metadata
-        ),
-    )
-
-    response.status_code = 201
-    response.headers["Location"] = request.url_for(
-                "get_image", image_type=ImageType.UPLOAD.value, image_name=filename
+    return Response(
+        status_code=201,
+        headers={
+            "Location": request.url_for(
+                "get_image", image_type=ImageType.UPLOAD, image_name=filename
             )
-
-    return res
-
-@images_router.get(
-    "/",
-    operation_id="list_images",
-    responses={200: {"model": PaginatedResults[ImageResponse]}},
-)
-async def list_images(
-    image_type: ImageType = Query(default=ImageType.RESULT, description="The type of images to get"),
-    page: int = Query(default=0, description="The page of images to get"),
-    per_page: int = Query(default=10, description="The number of images per page"),
-) -> PaginatedResults[ImageResponse]:
-    """Gets a list of images"""
-    result = ApiDependencies.invoker.services.images.list(
-        image_type, page, per_page
+        },
     )
-    return result

invokeai/app/api/routers/models.py

@@ -1,251 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and 2023 Kent Keirsey (https://github.com/hipsterusername)
-
-import shutil
-import asyncio
-from typing import Annotated, Any, List, Literal, Optional, Union
-
-from fastapi.routing import APIRouter, HTTPException
-from pydantic import BaseModel, Field, parse_obj_as
-from pathlib import Path
-from ..dependencies import ApiDependencies
-from invokeai.backend.globals import Globals, global_converted_ckpts_dir
-from invokeai.backend.args import Args
-
-
-
-models_router = APIRouter(prefix="/v1/models", tags=["models"])
-
-
-class VaeRepo(BaseModel):
-    repo_id: str = Field(description="The repo ID to use for this VAE")
-    path: Optional[str] = Field(description="The path to the VAE")
-    subfolder: Optional[str] = Field(description="The subfolder to use for this VAE")
-
-class ModelInfo(BaseModel):
-    description: Optional[str] = Field(description="A description of the model")
-    
-class CkptModelInfo(ModelInfo):
-    format: Literal['ckpt'] = 'ckpt'
-
-    config: str = Field(description="The path to the model config")
-    weights: str = Field(description="The path to the model weights")
-    vae: str = Field(description="The path to the model VAE")
-    width: Optional[int] = Field(description="The width of the model")
-    height: Optional[int] = Field(description="The height of the model")
-
-class DiffusersModelInfo(ModelInfo):
-    format: Literal['diffusers'] = 'diffusers'
-
-    vae: Optional[VaeRepo] = Field(description="The VAE repo to use for this model")
-    repo_id: Optional[str] = Field(description="The repo ID to use for this model")
-    path: Optional[str] = Field(description="The path to the model")
-
-class CreateModelRequest(BaseModel):
-    name: str = Field(description="The name of the model")
-    info: Union[CkptModelInfo, DiffusersModelInfo] = Field(discriminator="format", description="The model info")
-
-class CreateModelResponse(BaseModel):
-    name: str = Field(description="The name of the new model")
-    info: Union[CkptModelInfo, DiffusersModelInfo] = Field(discriminator="format", description="The model info")
-    status: str = Field(description="The status of the API response")
-
-class ConversionRequest(BaseModel):
-    name: str = Field(description="The name of the new model")
-    info: CkptModelInfo = Field(description="The converted model info")
-    save_location: str = Field(description="The path to save the converted model weights")
-    
-
-class ConvertedModelResponse(BaseModel):
-    name: str = Field(description="The name of the new model")
-    info: DiffusersModelInfo = Field(description="The converted model info")
-
-class ModelsList(BaseModel):
-    models: dict[str, Annotated[Union[(CkptModelInfo,DiffusersModelInfo)], Field(discriminator="format")]]
-
-
-@models_router.get(
-    "/",
-    operation_id="list_models",
-    responses={200: {"model": ModelsList }},
-)
-async def list_models() -> ModelsList:
-    """Gets a list of models"""
-    models_raw = ApiDependencies.invoker.services.model_manager.list_models()
-    models = parse_obj_as(ModelsList, { "models": models_raw })
-    return models
-
-
-@models_router.post(
-    "/",
-    operation_id="update_model",
-    responses={200: {"status": "success"}},
-)
-async def update_model(
-    model_request: CreateModelRequest
-) -> CreateModelResponse:
-    """ Add Model """
-    model_request_info = model_request.info
-    info_dict = model_request_info.dict()
-    model_response = CreateModelResponse(name=model_request.name, info=model_request.info, status="success")
-
-    ApiDependencies.invoker.services.model_manager.add_model(
-        model_name=model_request.name,
-        model_attributes=info_dict,
-        clobber=True,
-    )
-
-    return model_response
-
-
-@models_router.delete(
-    "/{model_name}",
-    operation_id="del_model",
-    responses={
-        204: {
-        "description": "Model deleted successfully"
-        }, 
-        404: {
-        "description": "Model not found"
-        }
-    },
-)
-async def delete_model(model_name: str) -> None:
-    """Delete Model"""
-    model_names = ApiDependencies.invoker.services.model_manager.model_names()
-    model_exists = model_name in model_names
-
-    # check if model exists
-    print(f">> Checking for model {model_name}...")
-           
-    if model_exists:
-        print(f">> Deleting Model: {model_name}")
-        ApiDependencies.invoker.services.model_manager.del_model(model_name, delete_files=True)
-        print(f">> Model Deleted: {model_name}")
-        raise HTTPException(status_code=204, detail=f"Model '{model_name}' deleted successfully")
-    
-    else:
-        print(f">> Model not found")
-        raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found")
-    
-
-            # @socketio.on("convertToDiffusers")
-        # def convert_to_diffusers(model_to_convert: dict):
-        #     try:
-        #         if model_info := self.generate.model_manager.model_info(
-        #             model_name=model_to_convert["model_name"]
-        #         ):
-        #             if "weights" in model_info:
-        #                 ckpt_path = Path(model_info["weights"])
-        #                 original_config_file = Path(model_info["config"])
-        #                 model_name = model_to_convert["model_name"]
-        #                 model_description = model_info["description"]
-        #             else:
-        #                 self.socketio.emit(
-        #                     "error", {"message": "Model is not a valid checkpoint file"}
-        #                 )
-        #         else:
-        #             self.socketio.emit(
-        #                 "error", {"message": "Could not retrieve model info."}
-        #             )
-
-        #         if not ckpt_path.is_absolute():
-        #             ckpt_path = Path(Globals.root, ckpt_path)
-
-        #         if original_config_file and not original_config_file.is_absolute():
-        #             original_config_file = Path(Globals.root, original_config_file)
-
-        #         diffusers_path = Path(
-        #             ckpt_path.parent.absolute(), f"{model_name}_diffusers"
-        #         )
-
-        #         if model_to_convert["save_location"] == "root":
-        #             diffusers_path = Path(
-        #                 global_converted_ckpts_dir(), f"{model_name}_diffusers"
-        #             )
-
-        #         if (
-        #             model_to_convert["save_location"] == "custom"
-        #             and model_to_convert["custom_location"] is not None
-        #         ):
-        #             diffusers_path = Path(
-        #                 model_to_convert["custom_location"], f"{model_name}_diffusers"
-        #             )
-
-        #         if diffusers_path.exists():
-        #             shutil.rmtree(diffusers_path)
-
-        #         self.generate.model_manager.convert_and_import(
-        #             ckpt_path,
-        #             diffusers_path,
-        #             model_name=model_name,
-        #             model_description=model_description,
-        #             vae=None,
-        #             original_config_file=original_config_file,
-        #             commit_to_conf=opt.conf,
-        #         )
-
-        #         new_model_list = self.generate.model_manager.list_models()
-        #         socketio.emit(
-        #             "modelConverted",
-        #             {
-        #                 "new_model_name": model_name,
-        #                 "model_list": new_model_list,
-        #                 "update": True,
-        #             },
-        #         )
-        #         print(f">> Model Converted: {model_name}")
-        #     except Exception as e:
-        #         self.handle_exceptions(e)
-
-        # @socketio.on("mergeDiffusersModels")
-        # def merge_diffusers_models(model_merge_info: dict):
-        #     try:
-        #         models_to_merge = model_merge_info["models_to_merge"]
-        #         model_ids_or_paths = [
-        #             self.generate.model_manager.model_name_or_path(x)
-        #             for x in models_to_merge
-        #         ]
-        #         merged_pipe = merge_diffusion_models(
-        #             model_ids_or_paths,
-        #             model_merge_info["alpha"],
-        #             model_merge_info["interp"],
-        #             model_merge_info["force"],
-        #         )
-
-        #         dump_path = global_models_dir() / "merged_models"
-        #         if model_merge_info["model_merge_save_path"] is not None:
-        #             dump_path = Path(model_merge_info["model_merge_save_path"])
-
-        #         os.makedirs(dump_path, exist_ok=True)
-        #         dump_path = dump_path / model_merge_info["merged_model_name"]
-        #         merged_pipe.save_pretrained(dump_path, safe_serialization=1)
-
-        #         merged_model_config = dict(
-        #             model_name=model_merge_info["merged_model_name"],
-        #             description=f'Merge of models {", ".join(models_to_merge)}',
-        #             commit_to_conf=opt.conf,
-        #         )
-
-        #         if vae := self.generate.model_manager.config[models_to_merge[0]].get(
-        #             "vae", None
-        #         ):
-        #             print(f">> Using configured VAE assigned to {models_to_merge[0]}")
-        #             merged_model_config.update(vae=vae)
-
-        #         self.generate.model_manager.import_diffuser_model(
-        #             dump_path, **merged_model_config
-        #         )
-        #         new_model_list = self.generate.model_manager.list_models()
-
-        #         socketio.emit(
-        #             "modelsMerged",
-        #             {
-        #                 "merged_models": models_to_merge,
-        #                 "merged_model_name": model_merge_info["merged_model_name"],
-        #                 "model_list": new_model_list,
-        #                 "update": True,
-        #             },
-        #         )
-        #         print(f">> Models Merged: {models_to_merge}")
-        #         print(f">> New Model Added: {model_merge_info['merged_model_name']}")
-        #     except Exception as e:

invokeai/app/api/routers/sessions.py

@@ -51,7 +51,7 @@ async def list_sessions(
     query: str = Query(default="", description="The query string to search for"),
 ) -> PaginatedResults[GraphExecutionState]:
     """Gets a list of sessions, optionally searching"""
-    if query == "":
+    if filter == "":
         result = ApiDependencies.invoker.services.graph_execution_manager.list(
             page, per_page
         )

invokeai/app/api_app.py

@@ -14,7 +14,7 @@ from pydantic.schema import schema
 
 from ..backend import Args
 from .api.dependencies import ApiDependencies
-from .api.routers import images, sessions, models
+from .api.routers import images, sessions
 from .api.sockets import SocketIO
 from .invocations import *
 from .invocations.baseinvocation import BaseInvocation
@@ -76,8 +76,6 @@ app.include_router(sessions.session_router, prefix="/api")
 
 app.include_router(images.images_router, prefix="/api")
 
-app.include_router(models.models_router, prefix="/api")
-
 
 # Build a custom OpenAPI to include all outputs
 # TODO: can outputs be included on metadata of invocation schemas somehow?

invokeai/app/cli/commands.py

@@ -4,10 +4,8 @@ from abc import ABC, abstractmethod
 import argparse
 from typing import Any, Callable, Iterable, Literal, get_args, get_origin, get_type_hints
 from pydantic import BaseModel, Field
-import networkx as nx
-import matplotlib.pyplot as plt
 
-from ..models.image import ImageField
+from ..invocations.image import ImageField
 from ..services.graph import GraphExecutionState
 from ..services.invoker import Invoker
 
@@ -48,7 +46,7 @@ def add_parsers(
                     f"--{name}",
                     dest=name,
                     type=field_type,
-                    default=field.default if field.default_factory is None else field.default_factory(),
+                    default=field.default,
                     choices=allowed_values,
                     help=field.field_info.description,
                 )
@@ -57,7 +55,7 @@ def add_parsers(
                     f"--{name}",
                     dest=name,
                     type=field.type_,
-                    default=field.default if field.default_factory is None else field.default_factory(),
+                    default=field.default,
                     help=field.field_info.description,
                 )
 
@@ -202,39 +200,3 @@ class SetDefaultCommand(BaseCommand):
                 del context.defaults[self.field]
         else:
             context.defaults[self.field] = self.value
-
-
-class DrawGraphCommand(BaseCommand):
-    """Debugs a graph"""
-    type: Literal['draw_graph'] = 'draw_graph'
-
-    def run(self, context: CliContext) -> None:
-        session: GraphExecutionState = context.invoker.services.graph_execution_manager.get(context.session.id)
-        nxgraph = session.graph.nx_graph_flat()
-
-        # Draw the networkx graph
-        plt.figure(figsize=(20, 20))
-        pos = nx.spectral_layout(nxgraph)
-        nx.draw_networkx_nodes(nxgraph, pos, node_size=1000)
-        nx.draw_networkx_edges(nxgraph, pos, width=2)
-        nx.draw_networkx_labels(nxgraph, pos, font_size=20, font_family="sans-serif")
-        plt.axis("off")
-        plt.show()
-
-
-class DrawExecutionGraphCommand(BaseCommand):
-    """Debugs an execution graph"""
-    type: Literal['draw_xgraph'] = 'draw_xgraph'
-
-    def run(self, context: CliContext) -> None:
-        session: GraphExecutionState = context.invoker.services.graph_execution_manager.get(context.session.id)
-        nxgraph = session.execution_graph.nx_graph_flat()
-
-        # Draw the networkx graph
-        plt.figure(figsize=(20, 20))
-        pos = nx.spectral_layout(nxgraph)
-        nx.draw_networkx_nodes(nxgraph, pos, node_size=1000)
-        nx.draw_networkx_edges(nxgraph, pos, width=2)
-        nx.draw_networkx_labels(nxgraph, pos, font_size=20, font_family="sans-serif")
-        plt.axis("off")
-        plt.show()

invokeai/app/cli/completer.py

@@ -1,167 +0,0 @@
-"""
-Readline helper functions for cli_app.py
-You may import the global singleton `completer` to get access to the
-completer object.
-"""
-import atexit
-import readline
-import shlex
-
-from pathlib import Path
-from typing import List, Dict, Literal, get_args, get_type_hints, get_origin
-
-from ...backend import ModelManager, Globals
-from ..invocations.baseinvocation import BaseInvocation
-from .commands import BaseCommand
-
-# singleton object, class variable
-completer = None
-
-class Completer(object):
-    
-    def __init__(self, model_manager: ModelManager):
-        self.commands = self.get_commands()
-        self.matches = None
-        self.linebuffer = None
-        self.manager = model_manager
-        return
-
-    def complete(self, text, state):
-        """
-        Complete commands and switches fromm the node CLI command line.
-        Switches are determined in a context-specific manner.
-        """
-
-        buffer = readline.get_line_buffer()
-        if state == 0:
-            options = None
-            try:
-                current_command, current_switch = self.get_current_command(buffer)
-                options = self.get_command_options(current_command, current_switch)
-            except IndexError:
-                pass
-            options = options or list(self.parse_commands().keys())
-            
-            if not text:  # first time
-                self.matches = options
-            else:
-                self.matches = [s for s in options if s and s.startswith(text)]
-
-        try:
-            match = self.matches[state]
-        except IndexError:
-            match = None
-        return match
-
-    @classmethod
-    def get_commands(self)->List[object]:
-        """
-        Return a list of all the client commands and invocations.
-        """
-        return BaseCommand.get_commands() + BaseInvocation.get_invocations()
-
-    def get_current_command(self, buffer: str)->tuple[str, str]:
-        """
-        Parse the readline buffer to find the most recent command and its switch.
-        """
-        if len(buffer)==0:
-            return None, None
-        tokens = shlex.split(buffer)
-        command = None
-        switch = None
-        for t in tokens:
-            if t[0].isalpha():
-                if switch is None:
-                    command = t
-            else:
-                switch = t
-        # don't try to autocomplete switches that are already complete
-        if switch and buffer.endswith(' '):
-            switch=None
-        return command or '', switch or ''
-
-    def parse_commands(self)->Dict[str, List[str]]:
-        """
-        Return a dict in which the keys are the command name
-        and the values are the parameters the command takes.
-        """
-        result = dict()
-        for command in self.commands:
-            hints = get_type_hints(command)
-            name = get_args(hints['type'])[0]
-            result.update({name:hints})
-        return result
-
-    def get_command_options(self, command: str, switch: str)->List[str]:
-        """
-        Return all the parameters that can be passed to the command as
-        command-line switches. Returns None if the command is unrecognized.
-        """
-        parsed_commands = self.parse_commands()
-        if command not in parsed_commands:
-            return None
-        
-        # handle switches in the format "-foo=bar"
-        argument = None
-        if switch and '=' in switch:
-            switch, argument = switch.split('=')
-            
-        parameter = switch.strip('-')
-        if parameter in parsed_commands[command]:
-            if argument is None:
-                return self.get_parameter_options(parameter, parsed_commands[command][parameter])
-            else:
-                return [f"--{parameter}={x}" for x in self.get_parameter_options(parameter, parsed_commands[command][parameter])]
-        else:
-            return [f"--{x}" for x in parsed_commands[command].keys()]
-
-    def get_parameter_options(self, parameter: str, typehint)->List[str]:
-        """
-        Given a parameter type (such as Literal), offers autocompletions.
-        """
-        if get_origin(typehint) == Literal:
-            return get_args(typehint)
-        if parameter == 'model':
-            return self.manager.model_names()
-        
-    def _pre_input_hook(self):
-        if self.linebuffer:
-            readline.insert_text(self.linebuffer)
-            readline.redisplay()
-            self.linebuffer = None
-    
-def set_autocompleter(model_manager: ModelManager) -> Completer:
-    global completer
-    
-    if completer:
-        return completer
-    
-    completer = Completer(model_manager)
-
-    readline.set_completer(completer.complete)
-    # pyreadline3 does not have a set_auto_history() method
-    try:
-        readline.set_auto_history(True)
-    except:
-        pass
-    readline.set_pre_input_hook(completer._pre_input_hook)
-    readline.set_completer_delims(" ")
-    readline.parse_and_bind("tab: complete")
-    readline.parse_and_bind("set print-completions-horizontally off")
-    readline.parse_and_bind("set page-completions on")
-    readline.parse_and_bind("set skip-completed-text on")
-    readline.parse_and_bind("set show-all-if-ambiguous on")
-
-    histfile = Path(Globals.root, ".invoke_history")
-    try:
-        readline.read_history_file(histfile)
-        readline.set_history_length(1000)
-    except FileNotFoundError:
-        pass
-    except OSError:  # file likely corrupted
-        newname = f"{histfile}.old"
-        print(
-            f"## Your history file {histfile} couldn't be loaded and may be corrupted. Renaming it to {newname}"
-        )
-        histfile.replace(Path(newname))
-    atexit.register(readline.write_history_file, histfile)

invokeai/app/cli_app.py

@@ -2,7 +2,6 @@
 
 import argparse
 import os
-import re
 import shlex
 import time
 from typing import (
@@ -13,17 +12,14 @@ from typing import (
 from pydantic import BaseModel
 from pydantic.fields import Field
 
-from .services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
-
 from ..backend import Args
 from .cli.commands import BaseCommand, CliContext, ExitCli, add_parsers, get_graph_execution_history
-from .cli.completer import set_autocompleter
 from .invocations import *
 from .invocations.baseinvocation import BaseInvocation
 from .services.events import EventServiceBase
 from .services.model_manager_initializer import get_model_manager
 from .services.restoration_services import RestorationServices
-from .services.graph import Edge, EdgeConnection, GraphExecutionState, are_connection_types_compatible
+from .services.graph import Edge, EdgeConnection, GraphExecutionState
 from .services.image_storage import DiskImageStorage
 from .services.invocation_queue import MemoryInvocationQueue
 from .services.invocation_services import InvocationServices
@@ -47,7 +43,7 @@ def add_invocation_args(command_parser):
         "-l",
         action="append",
         nargs=3,
-        help="A link in the format 'source_node source_field dest_field'. source_node can be relative to history (e.g. -1)",
+        help="A link in the format 'dest_field source_node source_field'. source_node can be relative to history (e.g. -1)",
     )
 
     command_parser.add_argument(
@@ -97,9 +93,6 @@ def generate_matching_edges(
     invalid_fields = set(["type", "id"])
     matching_fields = matching_fields.difference(invalid_fields)
 
-    # Validate types
-    matching_fields = [f for f in matching_fields if are_connection_types_compatible(afields[f], bfields[f])]
-
     edges = [
         Edge(
             source=EdgeConnection(node_id=a.id, field=field),
@@ -137,12 +130,6 @@ def invoke_cli():
     config.parse_args()
     model_manager = get_model_manager(config)
 
-    # This initializes the autocompleter and returns it.
-    # Currently nothing is done with the returned Completer
-    # object, but the object can be used to change autocompletion
-    # behavior on the fly, if desired.
-    completer = set_autocompleter(model_manager)
-
     events = EventServiceBase()
 
     output_folder = os.path.abspath(
@@ -155,8 +142,7 @@ def invoke_cli():
     services = InvocationServices(
         model_manager=model_manager,
         events=events,
-        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents')),
-        images=DiskImageStorage(f'{output_folder}/images'),
+        images=DiskImageStorage(output_folder),
         queue=MemoryInvocationQueue(),
         graph_execution_manager=SqliteItemStorage[GraphExecutionState](
             filename=db_location, table_name="graph_executions"
@@ -169,8 +155,6 @@ def invoke_cli():
     session: GraphExecutionState = invoker.create_execution_state()
     parser = get_command_parser()
 
-    re_negid = re.compile('^-[0-9]+$')
-
     # Uncomment to print out previous sessions at startup
     # print(services.session_manager.list())
 
@@ -178,8 +162,8 @@ def invoke_cli():
 
     while True:
         try:
-            cmd_input = input("invoke> ")
-        except (KeyboardInterrupt, EOFError):
+            cmd_input = input("> ")
+        except KeyboardInterrupt:
             # Ctrl-c exits
             break
 
@@ -236,11 +220,7 @@ def invoke_cli():
                 # Parse provided links
                 if "link_node" in args and args["link_node"]:
                     for link in args["link_node"]:
-                        node_id = link
-                        if re_negid.match(node_id):
-                            node_id = str(current_id + int(node_id))
-
-                        link_node = context.session.graph.get_node(node_id)
+                        link_node = context.session.graph.get_node(link)
                         matching_edges = generate_matching_edges(
                             link_node, command.command
                         )
@@ -250,15 +230,10 @@ def invoke_cli():
 
                 if "link" in args and args["link"]:
                     for link in args["link"]:
-                        edges = [e for e in edges if e.destination.node_id != command.command.id or e.destination.field != link[2]]
-
-                        node_id = link[0]
-                        if re_negid.match(node_id):
-                            node_id = str(current_id + int(node_id))
-
+                        edges = [e for e in edges if e.destination.node_id != command.command.id and e.destination.field != link[2]]
                         edges.append(
                             Edge(
-                                source=EdgeConnection(node_id=node_id, field=link[1]),
+                                source=EdgeConnection(node_id=link[1], field=link[0]),
                                 destination=EdgeConnection(
                                     node_id=command.command.id, field=link[2]
                                 )

invokeai/app/invocations/baseinvocation.py

@@ -2,7 +2,7 @@
 
 from abc import ABC, abstractmethod
 from inspect import signature
-from typing import get_args, get_type_hints, Dict, List, Literal, TypedDict
+from typing import get_args, get_type_hints
 
 from pydantic import BaseModel, Field
 
@@ -76,56 +76,3 @@ class BaseInvocation(ABC, BaseModel):
     #fmt: off
     id: str = Field(description="The id of this node. Must be unique among all nodes.")
     #fmt: on
-
-
-# TODO: figure out a better way to provide these hints
-# TODO: when we can upgrade to python 3.11, we can use the`NotRequired` type instead of `total=False`
-class UIConfig(TypedDict, total=False):
-    type_hints: Dict[
-        str,
-        Literal[
-            "integer",
-            "float",
-            "boolean",
-            "string",
-            "enum",
-            "image",
-            "latents",
-            "model",
-        ],
-    ]
-    tags: List[str]
-
-
-class CustomisedSchemaExtra(TypedDict):
-    ui: UIConfig
-
-
-class InvocationConfig(BaseModel.Config):
-    """Customizes pydantic's BaseModel.Config class for use by Invocations.
-
-    Provide `schema_extra` a `ui` dict to add hints for generated UIs.
-
-    `tags`
-    - A list of strings, used to categorise invocations.
-
-    `type_hints`
-    - A dict of field types which override the types in the invocation definition.
-    - Each key should be the name of one of the invocation's fields.
-    - Each value should be one of the valid types:
-      - `integer`, `float`, `boolean`, `string`, `enum`, `image`, `latents`, `model`
-
-    ```python
-    class Config(InvocationConfig):
-      schema_extra = {
-          "ui": {
-              "tags": ["stable-diffusion", "image"],
-              "type_hints": {
-                  "initial_image": "image",
-              },
-          },
-      }
-    ```
-    """
-
-    schema_extra: CustomisedSchemaExtra

invokeai/app/invocations/collections.py

@@ -1,50 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-from typing import Literal
-
-import cv2 as cv
-import numpy as np
-import numpy.random
-from PIL import Image, ImageOps
-from pydantic import Field
-
-from ..services.image_storage import ImageType
-from .baseinvocation import BaseInvocation, InvocationContext, BaseInvocationOutput
-from .image import ImageField, ImageOutput
-
-
-class IntCollectionOutput(BaseInvocationOutput):
-    """A collection of integers"""
-
-    type: Literal["int_collection"] = "int_collection"
-
-    # Outputs
-    collection: list[int] = Field(default=[], description="The int collection")
-
-
-class RangeInvocation(BaseInvocation):
-    """Creates a range"""
-
-    type: Literal["range"] = "range"
-
-    # Inputs
-    start: int = Field(default=0, description="The start of the range")
-    stop: int = Field(default=10, description="The stop of the range")
-    step: int = Field(default=1, description="The step of the range")
-
-    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
-        return IntCollectionOutput(collection=list(range(self.start, self.stop, self.step)))
-
-
-class RandomRangeInvocation(BaseInvocation):
-    """Creates a collection of random numbers"""
-
-    type: Literal["random_range"] = "random_range"
-
-    # Inputs
-    low: int = Field(default=0, description="The inclusive low value")
-    high: int = Field(default=np.iinfo(np.int32).max, description="The exclusive high value")
-    size: int = Field(default=1, description="The number of values to generate")
-
-    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
-        return IntCollectionOutput(collection=list(numpy.random.randint(self.low, self.high, size=self.size)))

invokeai/app/invocations/cv.py

@@ -5,26 +5,14 @@ from typing import Literal
 import cv2 as cv
 import numpy
 from PIL import Image, ImageOps
-from pydantic import BaseModel, Field
+from pydantic import Field
 
-from invokeai.app.models.image import ImageField, ImageType
-from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
-from .image import ImageOutput, build_image_output
+from ..services.image_storage import ImageType
+from .baseinvocation import BaseInvocation, InvocationContext
+from .image import ImageField, ImageOutput
 
 
-class CvInvocationConfig(BaseModel):
-    """Helper class to provide all OpenCV invocations with additional config"""
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["cv", "image"],
-            },
-        }
-
-
-class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
+class CvInpaintInvocation(BaseInvocation):
     """Simple inpaint using opencv."""
     #fmt: off
     type: Literal["cv_inpaint"] = "cv_inpaint"
@@ -56,9 +44,7 @@ class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, image_inpainted, self.dict())
-        return build_image_output(
-            image_type=image_type,
-            image_name=image_name,
-            image=image_inpainted,
+        context.services.images.save(image_type, image_name, image_inpainted)
+        return ImageOutput(
+            image=ImageField(image_type=image_type, image_name=image_name)
         )

invokeai/app/invocations/generate.py

@@ -1,42 +1,29 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from functools import partial
-from typing import Literal, Optional, Union
+from datetime import datetime, timezone
+from typing import Any, Literal, Optional, Union
 
 import numpy as np
+
 from torch import Tensor
+from PIL import Image
+from pydantic import Field
+from skimage.exposure.histogram_matching import match_histograms
 
-from pydantic import BaseModel, Field
-
-from invokeai.app.models.image import ImageField, ImageType
-from invokeai.app.invocations.util.choose_model import choose_model
-from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
-from .image import ImageOutput, build_image_output
-from ...backend.generator import Txt2Img, Img2Img, Inpaint, InvokeAIGenerator
+from ..services.image_storage import ImageType
+from ..services.invocation_services import InvocationServices
+from .baseinvocation import BaseInvocation, InvocationContext
+from .image import ImageField, ImageOutput
+from ...backend.generator import Txt2Img, Img2Img, Inpaint, InvokeAIGenerator, Generator
 from ...backend.stable_diffusion import PipelineIntermediateState
-from ..models.exceptions import CanceledException
-from ..util.step_callback import diffusers_step_callback_adapter
-
-SAMPLER_NAME_VALUES = Literal[tuple(InvokeAIGenerator.schedulers())]
-
-
-class SDImageInvocation(BaseModel):
-    """Helper class to provide all Stable Diffusion raster image invocations with additional config"""
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["stable-diffusion", "image"],
-                "type_hints": {
-                    "model": "model",
-                },
-            },
-        }
+from ...backend.util.util import image_to_dataURL
 
+SAMPLER_NAME_VALUES = Literal[
+    tuple(InvokeAIGenerator.schedulers())
+]
 
 # Text to image
-class TextToImageInvocation(BaseInvocation, SDImageInvocation):
+class TextToImageInvocation(BaseInvocation):
     """Generates an image using text2img."""
 
     type: Literal["txt2img"] = "txt2img"
@@ -50,7 +37,7 @@ class TextToImageInvocation(BaseInvocation, SDImageInvocation):
     width:       int = Field(default=512, multiple_of=64, gt=0, description="The width of the resulting image", )
     height:      int = Field(default=512, multiple_of=64, gt=0, description="The height of the resulting image", )
     cfg_scale: float = Field(default=7.5, gt=0, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
-    scheduler: SAMPLER_NAME_VALUES = Field(default="k_lms", description="The scheduler to use" )
+    sampler_name: SAMPLER_NAME_VALUES = Field(default="k_lms", description="The sampler to use" )
     seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
     model:       str = Field(default="", description="The model to use (currently ignored)")
     progress_images: bool = Field(default=False, description="Whether or not to produce progress images during generation",  )
@@ -58,29 +45,41 @@ class TextToImageInvocation(BaseInvocation, SDImageInvocation):
 
     # TODO: pass this an emitter method or something? or a session for dispatching?
     def dispatch_progress(
-        self, context: InvocationContext, intermediate_state: PipelineIntermediateState
-    ) -> None:
-        if (context.services.queue.is_canceled(context.graph_execution_state_id)):
-            raise CanceledException
+        self, context: InvocationContext, sample: Tensor, step: int
+    ) -> None:  
+        # TODO: only output a preview image when requested
+        image = Generator.sample_to_lowres_estimated_image(sample)
 
-        step = intermediate_state.step
-        if intermediate_state.predicted_original is not None:
-            # Some schedulers report not only the noisy latents at the current timestep,
-            # but also their estimate so far of what the de-noised latents will be.
-            sample = intermediate_state.predicted_original
-        else:
-            sample = intermediate_state.latents
-        
-        diffusers_step_callback_adapter(sample, step, steps=self.steps, id=self.id, context=context)
+        (width, height) = image.size
+        width *= 8
+        height *= 8
+
+        dataURL = image_to_dataURL(image, image_format="JPEG")
+
+        context.services.events.emit_generator_progress(
+            context.graph_execution_state_id,
+            self.id,
+            {
+                "width": width,
+                "height": height,
+                "dataURL": dataURL
+            },
+            step,
+            self.steps,
+        )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        # Handle invalid model parameter
-        model = choose_model(context.services.model_manager, self.model)
-        self.model_name = model["model_name"]
+        def step_callback(state: PipelineIntermediateState):
+            self.dispatch_progress(context, state.latents, state.step)
 
+        # Handle invalid model parameter
+        # TODO: figure out if this can be done via a validator that uses the model_cache
+        # TODO: How to get the default model name now?
+        #       (right now uses whatever current model is set in model manager)
+        model= context.services.model_manager.get_model()
         outputs = Txt2Img(model).generate(
             prompt=self.prompt,
-            step_callback=partial(self.dispatch_progress, context),
+            step_callback=step_callback,
             **self.dict(
                 exclude={"prompt"}
             ),  # Shorthand for passing all of the parameters above manually
@@ -96,22 +95,9 @@ class TextToImageInvocation(BaseInvocation, SDImageInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-
-        graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
-        source_id = graph_execution_state.prepared_source_mapping[self.id]
-        invocation = graph_execution_state.execution_graph.get_node(self.id)
-        
-        metadata = {
-          "session": context.graph_execution_state_id,
-          "source_id": source_id,
-          "invocation": invocation.dict()
-        }
-
-        context.services.images.save(image_type, image_name, generate_output.image, metadata)
-        return build_image_output(
-            image_type=image_type,
-            image_name=image_name,
-            image=generate_output.image
+        context.services.images.save(image_type, image_name, generate_output.image)
+        return ImageOutput(
+            image=ImageField(image_type=image_type, image_name=image_name)
         )
 
 
@@ -130,22 +116,6 @@ class ImageToImageInvocation(TextToImageInvocation):
         description="Whether or not the result should be fit to the aspect ratio of the input image",
     )
 
-    def dispatch_progress(
-        self, context: InvocationContext, intermediate_state: PipelineIntermediateState
-    ) -> None:  
-        if (context.services.queue.is_canceled(context.graph_execution_state_id)):
-            raise CanceledException
-
-        step = intermediate_state.step
-        if intermediate_state.predicted_original is not None:
-            # Some schedulers report not only the noisy latents at the current timestep,
-            # but also their estimate so far of what the de-noised latents will be.
-            sample = intermediate_state.predicted_original
-        else:
-            sample = intermediate_state.latents
-
-        diffusers_step_callback_adapter(sample, step, steps=self.steps, id=self.id, context=context)
-
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = (
             None
@@ -156,23 +126,24 @@ class ImageToImageInvocation(TextToImageInvocation):
         )
         mask = None
 
-        # Handle invalid model parameter
-        model = choose_model(context.services.model_manager, self.model)
-        self.model = model["model_name"]
+        def step_callback(sample, step=0):
+            self.dispatch_progress(context, sample, step)
 
-        outputs = Img2Img(model).generate(
+        # Handle invalid model parameter
+        # TODO: figure out if this can be done via a validator that uses the model_cache
+        # TODO: How to get the default model name now?
+        model = context.services.model_manager.get_model()
+        generator_output = next(
+            Img2Img(model).generate(
                 prompt=self.prompt,
                 init_image=image,
                 init_mask=mask,
-                step_callback=partial(self.dispatch_progress, context),
+                step_callback=step_callback,
                 **self.dict(
                     exclude={"prompt", "image", "mask"}
                 ),  # Shorthand for passing all of the parameters above manually
             )
-
-        # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
-        # each time it is called. We only need the first one.
-        generator_output = next(outputs)
+        )
 
         result_image = generator_output.image
 
@@ -183,11 +154,9 @@ class ImageToImageInvocation(TextToImageInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, result_image, self.dict())
-        return build_image_output(
-            image_type=image_type,
-            image_name=image_name,
-            image=result_image
+        context.services.images.save(image_type, image_name, result_image)
+        return ImageOutput(
+            image=ImageField(image_type=image_type, image_name=image_name)
         )
 
 class InpaintInvocation(ImageToImageInvocation):
@@ -204,22 +173,6 @@ class InpaintInvocation(ImageToImageInvocation):
         description="The amount by which to replace masked areas with latent noise",
     )
 
-    def dispatch_progress(
-        self, context: InvocationContext, intermediate_state: PipelineIntermediateState
-    ) -> None:  
-        if (context.services.queue.is_canceled(context.graph_execution_state_id)):
-            raise CanceledException
-
-        step = intermediate_state.step
-        if intermediate_state.predicted_original is not None:
-            # Some schedulers report not only the noisy latents at the current timestep,
-            # but also their estimate so far of what the de-noised latents will be.
-            sample = intermediate_state.predicted_original
-        else:
-            sample = intermediate_state.latents
-
-        diffusers_step_callback_adapter(sample, step, steps=self.steps, id=self.id, context=context)
-
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = (
             None
@@ -234,23 +187,24 @@ class InpaintInvocation(ImageToImageInvocation):
             else context.services.images.get(self.mask.image_type, self.mask.image_name)
         )
 
-        # Handle invalid model parameter
-        model = choose_model(context.services.model_manager, self.model)
-        self.model = model["model_name"]
+        def step_callback(sample, step=0):
+            self.dispatch_progress(context, sample, step)
 
-        outputs = Inpaint(model).generate(
+        # Handle invalid model parameter
+        # TODO: figure out if this can be done via a validator that uses the model_cache
+        # TODO: How to get the default model name now?
+        manager = context.services.model_manager.get_model()
+        generator_output = next(
+            Inpaint(model).generate(
                 prompt=self.prompt,
-                init_img=image,
-                init_mask=mask,
-                step_callback=partial(self.dispatch_progress, context),
+                init_image=image,
+                mask_image=mask,
+                step_callback=step_callback,
                 **self.dict(
                     exclude={"prompt", "image", "mask"}
                 ),  # Shorthand for passing all of the parameters above manually
             )
-
-        # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
-        # each time it is called. We only need the first one.
-        generator_output = next(outputs)
+        )
 
         result_image = generator_output.image
 
@@ -261,9 +215,7 @@ class InpaintInvocation(ImageToImageInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, result_image, self.dict())
-        return build_image_output(
-            image_type=image_type,
-            image_name=image_name,
-            image=result_image
+        context.services.images.save(image_type, image_name, result_image)
+        return ImageOutput(
+            image=ImageField(image_type=image_type, image_name=image_name)
         )

invokeai/app/invocations/image.py

@@ -7,90 +7,49 @@ import numpy
 from PIL import Image, ImageFilter, ImageOps
 from pydantic import BaseModel, Field
 
-from ..models.image import ImageField, ImageType
+from ..services.image_storage import ImageType
 from ..services.invocation_services import InvocationServices
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    InvocationContext,
-    InvocationConfig,
-)
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext
 
 
-class PILInvocationConfig(BaseModel):
-    """Helper class to provide all PIL invocations with additional config"""
+class ImageField(BaseModel):
+    """An image field used for passing image objects between invocations"""
 
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["PIL", "image"],
-            },
-        }
+    image_type: str = Field(
+        default=ImageType.RESULT, description="The type of the image"
+    )
+    image_name: Optional[str] = Field(default=None, description="The name of the image")
 
 
 class ImageOutput(BaseInvocationOutput):
     """Base class for invocations that output an image"""
-
-    # fmt: off
+    #fmt: off
     type: Literal["image"] = "image"
     image:      ImageField = Field(default=None, description="The output image")
-    width:             int = Field(description="The width of the image in pixels")
-    height:            int = Field(description="The height of the image in pixels")
-    # fmt: on
-
-    class Config:
-        schema_extra = {
-            "required": [
-                "type",
-                "image",
-                "width",
-                "height",
-            ]
-        }
-
-
-def build_image_output(
-    image_type: ImageType, image_name: str, image: Image.Image
-) -> ImageOutput:
-    image_field = ImageField(image_name=image_name, image_type=image_type)
-
-    return ImageOutput(image=image_field, width=image.width, height=image.height)
-
+    #fmt: on
 
 class MaskOutput(BaseInvocationOutput):
     """Base class for invocations that output a mask"""
-
-    # fmt: off
+    #fmt: off
     type: Literal["mask"] = "mask"
     mask:      ImageField = Field(default=None, description="The output mask")
-    # fmt: on
+    #fomt: on
 
-    class Config:
-        schema_extra = {
-            "required": [
-                "type",
-                "mask",
-            ]
-        }
+# TODO: this isn't really necessary anymore
+class LoadImageInvocation(BaseInvocation):
+    """Load an image from a filename and provide it as output."""
+    #fmt: off
+    type: Literal["load_image"] = "load_image"
 
+    # Inputs
+    image_type: ImageType = Field(description="The type of the image")
+    image_name:       str = Field(description="The name of the image")
+    #fmt: on
 
-# # TODO: this isn't really necessary anymore
-# class LoadImageInvocation(BaseInvocation):
-#     """Load an image from a filename and provide it as output."""
-#     #fmt: off
-#     type: Literal["load_image"] = "load_image"
-
-#     # Inputs
-#     image_type: ImageType = Field(description="The type of the image")
-#     image_name:       str = Field(description="The name of the image")
-#     #fmt: on
-
-#     def invoke(self, context: InvocationContext) -> ImageOutput:
-#         return ImageOutput(
-#             image_type=self.image_type,
-#             image_name=self.image_name,
-#             image=result_image
-#         )
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        return ImageOutput(
+            image=ImageField(image_type=self.image_type, image_name=self.image_name)
+        )
 
 
 class ShowImageInvocation(BaseInvocation):
@@ -110,17 +69,16 @@ class ShowImageInvocation(BaseInvocation):
 
         # TODO: how to handle failure?
 
-        return build_image_output(
-            image_type=self.image.image_type,
-            image_name=self.image.image_name,
-            image=image,
+        return ImageOutput(
+            image=ImageField(
+                image_type=self.image.image_type, image_name=self.image.image_name
+            )
         )
 
 
-class CropImageInvocation(BaseInvocation, PILInvocationConfig):
+class CropImageInvocation(BaseInvocation):
     """Crops an image to a specified box. The box can be outside of the image."""
-
-    # fmt: off
+    #fmt: off
     type: Literal["crop"] = "crop"
 
     # Inputs
@@ -129,7 +87,7 @@ class CropImageInvocation(BaseInvocation, PILInvocationConfig):
     y:      int = Field(default=0, description="The top y coordinate of the crop rectangle")
     width:  int = Field(default=512, gt=0, description="The width of the crop rectangle")
     height: int = Field(default=512, gt=0, description="The height of the crop rectangle")
-    # fmt: on
+    #fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get(
@@ -145,16 +103,15 @@ class CropImageInvocation(BaseInvocation, PILInvocationConfig):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, image_crop, self.dict())
-        return build_image_output(
-            image_type=image_type, image_name=image_name, image=image_crop
+        context.services.images.save(image_type, image_name, image_crop)
+        return ImageOutput(
+            image=ImageField(image_type=image_type, image_name=image_name)
         )
 
 
-class PasteImageInvocation(BaseInvocation, PILInvocationConfig):
+class PasteImageInvocation(BaseInvocation):
     """Pastes an image into another image."""
-
-    # fmt: off
+    #fmt: off
     type: Literal["paste"] = "paste"
 
     # Inputs
@@ -163,7 +120,7 @@ class PasteImageInvocation(BaseInvocation, PILInvocationConfig):
     mask: Optional[ImageField] = Field(default=None, description="The mask to use when pasting")
     x:                     int = Field(default=0, description="The left x coordinate at which to paste the image")
     y:                     int = Field(default=0, description="The top y coordinate at which to paste the image")
-    # fmt: on
+    #fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         base_image = context.services.images.get(
@@ -176,7 +133,7 @@ class PasteImageInvocation(BaseInvocation, PILInvocationConfig):
             None
             if self.mask is None
             else ImageOps.invert(
-                context.services.images.get(self.mask.image_type, self.mask.image_name)
+                services.images.get(self.mask.image_type, self.mask.image_name)
             )
         )
         # TODO: probably shouldn't invert mask here... should user be required to do it?
@@ -196,22 +153,21 @@ class PasteImageInvocation(BaseInvocation, PILInvocationConfig):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, new_image, self.dict())
-        return build_image_output(
-            image_type=image_type, image_name=image_name, image=new_image
+        context.services.images.save(image_type, image_name, new_image)
+        return ImageOutput(
+            image=ImageField(image_type=image_type, image_name=image_name)
         )
 
 
-class MaskFromAlphaInvocation(BaseInvocation, PILInvocationConfig):
+class MaskFromAlphaInvocation(BaseInvocation):
     """Extracts the alpha channel of an image as a mask."""
-
-    # fmt: off
+    #fmt: off
     type: Literal["tomask"] = "tomask"
 
     # Inputs
     image: ImageField = Field(default=None, description="The image to create the mask from")
     invert:      bool = Field(default=False, description="Whether or not to invert the mask")
-    # fmt: on
+    #fmt: on
 
     def invoke(self, context: InvocationContext) -> MaskOutput:
         image = context.services.images.get(
@@ -226,22 +182,22 @@ class MaskFromAlphaInvocation(BaseInvocation, PILInvocationConfig):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, image_mask, self.dict())
+        context.services.images.save(image_type, image_name, image_mask)
         return MaskOutput(mask=ImageField(image_type=image_type, image_name=image_name))
 
 
-class BlurInvocation(BaseInvocation, PILInvocationConfig):
+class BlurInvocation(BaseInvocation):
     """Blurs an image"""
 
-    # fmt: off
+    #fmt: off
     type: Literal["blur"] = "blur"
 
     # Inputs
     image: ImageField = Field(default=None, description="The image to blur")
     radius:     float = Field(default=8.0, ge=0, description="The blur radius")
     blur_type: Literal["gaussian", "box"] = Field(default="gaussian", description="The type of blur")
-    # fmt: on
-
+    #fmt: on
+    
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get(
             self.image.image_type, self.image.image_name
@@ -258,23 +214,22 @@ class BlurInvocation(BaseInvocation, PILInvocationConfig):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, blur_image, self.dict())
-        return build_image_output(
-            image_type=image_type, image_name=image_name, image=blur_image
+        context.services.images.save(image_type, image_name, blur_image)
+        return ImageOutput(
+            image=ImageField(image_type=image_type, image_name=image_name)
         )
 
 
-class LerpInvocation(BaseInvocation, PILInvocationConfig):
+class LerpInvocation(BaseInvocation):
     """Linear interpolation of all pixels of an image"""
-
-    # fmt: off
+    #fmt: off
     type: Literal["lerp"] = "lerp"
 
     # Inputs
     image: ImageField = Field(default=None, description="The image to lerp")
     min: int = Field(default=0, ge=0, le=255, description="The minimum output value")
     max: int = Field(default=255, ge=0, le=255, description="The maximum output value")
-    # fmt: on
+    #fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get(
@@ -290,24 +245,23 @@ class LerpInvocation(BaseInvocation, PILInvocationConfig):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, lerp_image, self.dict())
-        return build_image_output(
-            image_type=image_type, image_name=image_name, image=lerp_image
+        context.services.images.save(image_type, image_name, lerp_image)
+        return ImageOutput(
+            image=ImageField(image_type=image_type, image_name=image_name)
         )
 
 
-class InverseLerpInvocation(BaseInvocation, PILInvocationConfig):
+class InverseLerpInvocation(BaseInvocation):
     """Inverse linear interpolation of all pixels of an image"""
-
-    # fmt: off
+    #fmt: off
     type: Literal["ilerp"] = "ilerp"
 
     # Inputs
     image: ImageField = Field(default=None, description="The image to lerp")
     min: int = Field(default=0, ge=0, le=255, description="The minimum input value")
     max: int = Field(default=255, ge=0, le=255, description="The maximum input value")
-    # fmt: on
-
+    #fmt: on
+    
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get(
             self.image.image_type, self.image.image_name
@@ -327,7 +281,7 @@ class InverseLerpInvocation(BaseInvocation, PILInvocationConfig):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, ilerp_image, self.dict())
-        return build_image_output(
-            image_type=image_type, image_name=image_name, image=ilerp_image
+        context.services.images.save(image_type, image_name, ilerp_image)
+        return ImageOutput(
+            image=ImageField(image_type=image_type, image_name=image_name)
         )

invokeai/app/invocations/latent.py

@@ -1,358 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-from typing import Literal, Optional
-from pydantic import BaseModel, Field
-import torch
-
-from invokeai.app.models.exceptions import CanceledException
-from invokeai.app.invocations.util.choose_model import choose_model
-from invokeai.app.util.step_callback import diffusers_step_callback_adapter
-
-from ...backend.model_management.model_manager import ModelManager
-from ...backend.util.devices import choose_torch_device, torch_dtype
-from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import PostprocessingSettings
-from ...backend.image_util.seamless import configure_model_padding
-from ...backend.prompting.conditioning import get_uc_and_c_and_ec
-from ...backend.stable_diffusion.diffusers_pipeline import ConditioningData, StableDiffusionGeneratorPipeline
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
-import numpy as np
-from ..services.image_storage import ImageType
-from .baseinvocation import BaseInvocation, InvocationContext
-from .image import ImageField, ImageOutput, build_image_output
-from ...backend.stable_diffusion import PipelineIntermediateState
-from diffusers.schedulers import SchedulerMixin as Scheduler
-import diffusers
-from diffusers import DiffusionPipeline
-
-
-class LatentsField(BaseModel):
-    """A latents field used for passing latents between invocations"""
-
-    latents_name: Optional[str] = Field(default=None, description="The name of the latents")
-
-
-class LatentsOutput(BaseInvocationOutput):
-    """Base class for invocations that output latents"""
-    #fmt: off
-    type: Literal["latent_output"] = "latent_output"
-    latents: LatentsField            = Field(default=None, description="The output latents")
-    #fmt: on
-
-class NoiseOutput(BaseInvocationOutput):
-    """Invocation noise output"""
-    #fmt: off
-    type: Literal["noise_output"] = "noise_output"
-    noise: LatentsField            = Field(default=None, description="The output noise")
-    #fmt: on
-
-
-# TODO: this seems like a hack
-scheduler_map = dict(
-    ddim=diffusers.DDIMScheduler,
-    dpmpp_2=diffusers.DPMSolverMultistepScheduler,
-    k_dpm_2=diffusers.KDPM2DiscreteScheduler,
-    k_dpm_2_a=diffusers.KDPM2AncestralDiscreteScheduler,
-    k_dpmpp_2=diffusers.DPMSolverMultistepScheduler,
-    k_euler=diffusers.EulerDiscreteScheduler,
-    k_euler_a=diffusers.EulerAncestralDiscreteScheduler,
-    k_heun=diffusers.HeunDiscreteScheduler,
-    k_lms=diffusers.LMSDiscreteScheduler,
-    plms=diffusers.PNDMScheduler,
-)
-
-
-SAMPLER_NAME_VALUES = Literal[
-    tuple(list(scheduler_map.keys()))
-]
-
-
-def get_scheduler(scheduler_name:str, model: StableDiffusionGeneratorPipeline)->Scheduler:
-    scheduler_class = scheduler_map.get(scheduler_name,'ddim')
-    scheduler = scheduler_class.from_config(model.scheduler.config)
-    # hack copied over from generate.py
-    if not hasattr(scheduler, 'uses_inpainting_model'):
-        scheduler.uses_inpainting_model = lambda: False
-    return scheduler
-
-
-def get_noise(width:int, height:int, device:torch.device, seed:int = 0, latent_channels:int=4, use_mps_noise:bool=False, downsampling_factor:int = 8):
-    # limit noise to only the diffusion image channels, not the mask channels
-    input_channels = min(latent_channels, 4)
-    use_device = "cpu" if (use_mps_noise or device.type == "mps") else device
-    generator = torch.Generator(device=use_device).manual_seed(seed)
-    x = torch.randn(
-        [
-            1,
-            input_channels,
-            height // downsampling_factor,
-            width //  downsampling_factor,
-        ],
-        dtype=torch_dtype(device),
-        device=use_device,
-        generator=generator,
-    ).to(device)
-    # if self.perlin > 0.0:
-    #     perlin_noise = self.get_perlin_noise(
-    #         width // self.downsampling_factor, height // self.downsampling_factor
-    #     )
-    #     x = (1 - self.perlin) * x + self.perlin * perlin_noise
-    return x
-
-
-class NoiseInvocation(BaseInvocation):
-    """Generates latent noise."""
-
-    type: Literal["noise"] = "noise"
-
-    # Inputs
-    seed:        int = Field(default=0, ge=0, le=np.iinfo(np.uint32).max, description="The seed to use", )
-    width:       int = Field(default=512, multiple_of=64, gt=0, description="The width of the resulting noise", )
-    height:      int = Field(default=512, multiple_of=64, gt=0, description="The height of the resulting noise", )
-
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["latents", "noise"],
-            },
-        }
-
-    def invoke(self, context: InvocationContext) -> NoiseOutput:
-        device = torch.device(choose_torch_device())
-        noise = get_noise(self.width, self.height, device, self.seed)
-
-        name = f'{context.graph_execution_state_id}__{self.id}'
-        context.services.latents.set(name, noise)
-        return NoiseOutput(
-            noise=LatentsField(latents_name=name)
-        )
-
-
-# Text to image
-class TextToLatentsInvocation(BaseInvocation):
-    """Generates latents from a prompt."""
-
-    type: Literal["t2l"] = "t2l"
-
-    # Inputs
-    # TODO: consider making prompt optional to enable providing prompt through a link
-    # fmt: off
-    prompt: Optional[str] = Field(description="The prompt to generate an image from")
-    seed:        int = Field(default=-1,ge=-1, le=np.iinfo(np.uint32).max, description="The seed to use (-1 for a random seed)", )
-    noise: Optional[LatentsField] = Field(description="The noise to use")
-    steps:       int = Field(default=10, gt=0, description="The number of steps to use to generate the image")
-    width:       int = Field(default=512, multiple_of=64, gt=0, description="The width of the resulting image", )
-    height:      int = Field(default=512, multiple_of=64, gt=0, description="The height of the resulting image", )
-    cfg_scale: float = Field(default=7.5, gt=0, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
-    scheduler: SAMPLER_NAME_VALUES = Field(default="k_lms", description="The scheduler to use" )
-    seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
-    seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
-    model:       str = Field(default="", description="The model to use (currently ignored)")
-    progress_images: bool = Field(default=False, description="Whether or not to produce progress images during generation",  )
-    # fmt: on
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["latents", "image"],
-                "type_hints": {
-                  "model": "model"
-                }
-            },
-        }
-
-    # TODO: pass this an emitter method or something? or a session for dispatching?
-    def dispatch_progress(
-        self, context: InvocationContext, intermediate_state: PipelineIntermediateState
-    ) -> None:  
-        if (context.services.queue.is_canceled(context.graph_execution_state_id)):
-            raise CanceledException
-
-        step = intermediate_state.step
-        if intermediate_state.predicted_original is not None:
-            # Some schedulers report not only the noisy latents at the current timestep,
-            # but also their estimate so far of what the de-noised latents will be.
-            sample = intermediate_state.predicted_original
-        else:
-            sample = intermediate_state.latents
-
-        diffusers_step_callback_adapter(sample, step, steps=self.steps, id=self.id, context=context)
-
-    
-    def get_model(self, model_manager: ModelManager) -> StableDiffusionGeneratorPipeline:
-        model_info = choose_model(model_manager, self.model)
-        model_name = model_info['model_name']
-        model_hash = model_info['hash']
-        model: StableDiffusionGeneratorPipeline = model_info['model']
-        model.scheduler = get_scheduler(
-            model=model,
-            scheduler_name=self.scheduler
-        )
-        
-        if isinstance(model, DiffusionPipeline):
-            for component in [model.unet, model.vae]:
-                configure_model_padding(component,
-                                        self.seamless,
-                                        self.seamless_axes
-                                        )
-        else:
-            configure_model_padding(model,
-                                    self.seamless,
-                                    self.seamless_axes
-                                    )
-
-        return model
-
-
-    def get_conditioning_data(self, model: StableDiffusionGeneratorPipeline) -> ConditioningData:
-        uc, c, extra_conditioning_info = get_uc_and_c_and_ec(self.prompt, model=model)
-        conditioning_data = ConditioningData(
-            uc,
-            c,
-            self.cfg_scale,
-            extra_conditioning_info,
-            postprocessing_settings=PostprocessingSettings(
-                threshold=0.0,#threshold,
-                warmup=0.2,#warmup,
-                h_symmetry_time_pct=None,#h_symmetry_time_pct,
-                v_symmetry_time_pct=None#v_symmetry_time_pct,
-            ),
-        ).add_scheduler_args_if_applicable(model.scheduler, eta=None)#ddim_eta)
-        return conditioning_data
-
-
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
-        noise = context.services.latents.get(self.noise.latents_name)
-
-        def step_callback(state: PipelineIntermediateState):
-            self.dispatch_progress(context, state)
-
-        model = self.get_model(context.services.model_manager)
-        conditioning_data = self.get_conditioning_data(model)
-
-        # TODO: Verify the noise is the right size
-
-        result_latents, result_attention_map_saver = model.latents_from_embeddings(
-            latents=torch.zeros_like(noise, dtype=torch_dtype(model.device)),
-            noise=noise,
-            num_inference_steps=self.steps,
-            conditioning_data=conditioning_data,
-            callback=step_callback
-        )
-
-        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
-        torch.cuda.empty_cache()
-
-        name = f'{context.graph_execution_state_id}__{self.id}'
-        context.services.latents.set(name, result_latents)
-        return LatentsOutput(
-            latents=LatentsField(latents_name=name)
-        )
-
-
-class LatentsToLatentsInvocation(TextToLatentsInvocation):
-    """Generates latents using latents as base image."""
-
-    type: Literal["l2l"] = "l2l"
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["latents"],
-                "type_hints": {
-                    "model": "model"
-                }
-            },
-        }
-
-    # Inputs
-    latents: Optional[LatentsField] = Field(description="The latents to use as a base image")
-    strength: float = Field(default=0.5, description="The strength of the latents to use")
-
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
-        noise = context.services.latents.get(self.noise.latents_name)
-        latent = context.services.latents.get(self.latents.latents_name)
-
-        def step_callback(state: PipelineIntermediateState):
-            self.dispatch_progress(context, state)
-
-        model = self.get_model(context.services.model_manager)
-        conditioning_data = self.get_conditioning_data(model)
-
-        # TODO: Verify the noise is the right size
-
-        initial_latents = latent if self.strength < 1.0 else torch.zeros_like(
-            latent, device=model.device, dtype=latent.dtype
-        )
-        
-        timesteps, _ = model.get_img2img_timesteps(
-            self.steps,
-            self.strength,
-            device=model.device,
-        )
-
-        result_latents, result_attention_map_saver = model.latents_from_embeddings(
-            latents=initial_latents,
-            timesteps=timesteps,
-            noise=noise,
-            num_inference_steps=self.steps,
-            conditioning_data=conditioning_data,
-            callback=step_callback
-        )
-
-        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
-        torch.cuda.empty_cache()
-
-        name = f'{context.graph_execution_state_id}__{self.id}'
-        context.services.latents.set(name, result_latents)
-        return LatentsOutput(
-            latents=LatentsField(latents_name=name)
-        )
-
-
-# Latent to image
-class LatentsToImageInvocation(BaseInvocation):
-    """Generates an image from latents."""
-
-    type: Literal["l2i"] = "l2i"
-
-    # Inputs
-    latents: Optional[LatentsField] = Field(description="The latents to generate an image from")
-    model: str = Field(default="", description="The model to use")
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["latents", "image"],
-                "type_hints": {
-                  "model": "model"
-                }
-            },
-        }
-
-    @torch.no_grad()
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
-
-        # TODO: this only really needs the vae
-        model_info = choose_model(context.services.model_manager, self.model)
-        model: StableDiffusionGeneratorPipeline = model_info['model']
-
-        with torch.inference_mode():
-            np_image = model.decode_latents(latents)
-            image = model.numpy_to_pil(np_image)[0]
-
-            image_type = ImageType.RESULT
-            image_name = context.services.images.create_name(
-                context.graph_execution_state_id, self.id
-            )
-            context.services.images.save(image_type, image_name, image, self.dict())
-            return build_image_output(
-                image_type=image_type,
-                image_name=image_name,
-                image=image
-            )

invokeai/app/invocations/math.py

@@ -1,75 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-from typing import Literal
-
-from pydantic import BaseModel, Field
-
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
-
-
-class MathInvocationConfig(BaseModel):
-    """Helper class to provide all math invocations with additional config"""
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["math"],
-            }
-        }
-
-
-class IntOutput(BaseInvocationOutput):
-    """An integer output"""
-    #fmt: off
-    type: Literal["int_output"] = "int_output"
-    a: int = Field(default=None, description="The output integer")
-    #fmt: on
-
-
-class AddInvocation(BaseInvocation, MathInvocationConfig):
-    """Adds two numbers"""
-    #fmt: off
-    type: Literal["add"] = "add"
-    a: int = Field(default=0, description="The first number")
-    b: int = Field(default=0, description="The second number")
-    #fmt: on
-
-    def invoke(self, context: InvocationContext) -> IntOutput:
-        return IntOutput(a=self.a + self.b)
-
-
-class SubtractInvocation(BaseInvocation, MathInvocationConfig):
-    """Subtracts two numbers"""
-    #fmt: off
-    type: Literal["sub"] = "sub"
-    a: int = Field(default=0, description="The first number")
-    b: int = Field(default=0, description="The second number")
-    #fmt: on
-
-    def invoke(self, context: InvocationContext) -> IntOutput:
-        return IntOutput(a=self.a - self.b)
-
-
-class MultiplyInvocation(BaseInvocation, MathInvocationConfig):
-    """Multiplies two numbers"""
-    #fmt: off
-    type: Literal["mul"] = "mul"
-    a: int = Field(default=0, description="The first number")
-    b: int = Field(default=0, description="The second number")
-    #fmt: on
-
-    def invoke(self, context: InvocationContext) -> IntOutput:
-        return IntOutput(a=self.a * self.b)
-
-
-class DivideInvocation(BaseInvocation, MathInvocationConfig):
-    """Divides two numbers"""
-    #fmt: off
-    type: Literal["div"] = "div"
-    a: int = Field(default=0, description="The first number")
-    b: int = Field(default=0, description="The second number")
-    #fmt: on
-
-    def invoke(self, context: InvocationContext) -> IntOutput:
-        return IntOutput(a=int(self.a / self.b))

invokeai/app/invocations/prompt.py

@@ -12,11 +12,3 @@ class PromptOutput(BaseInvocationOutput):
 
     prompt: str = Field(default=None, description="The output prompt")
     #fmt: on
-
-    class Config:
-        schema_extra = {
-            'required': [
-                'type',
-                'prompt',
-            ]
-        }

invokeai/app/invocations/reconstruct.py

@@ -3,10 +3,10 @@ from typing import Literal, Union
 
 from pydantic import Field
 
-from invokeai.app.models.image import ImageField, ImageType
+from ..services.image_storage import ImageType
 from ..services.invocation_services import InvocationServices
-from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
-from .image import ImageOutput, build_image_output
+from .baseinvocation import BaseInvocation, InvocationContext
+from .image import ImageField, ImageOutput
 
 class RestoreFaceInvocation(BaseInvocation):
     """Restores faces in an image."""
@@ -18,14 +18,6 @@ class RestoreFaceInvocation(BaseInvocation):
     strength:                float = Field(default=0.75, gt=0, le=1, description="The strength of the restoration"  )
     #fmt: on
     
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["restoration", "image"],
-            },
-        }
-
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get(
             self.image.image_type, self.image.image_name
@@ -44,9 +36,7 @@ class RestoreFaceInvocation(BaseInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, results[0][0], self.dict())
-        return build_image_output(
-            image_type=image_type,
-            image_name=image_name,
-            image=results[0][0]
-        )
+        context.services.images.save(image_type, image_name, results[0][0])
+        return ImageOutput(
+            image=ImageField(image_type=image_type, image_name=image_name)
+        )

invokeai/app/invocations/upscale.py

@@ -5,10 +5,10 @@ from typing import Literal, Union
 
 from pydantic import Field
 
-from invokeai.app.models.image import ImageField, ImageType
+from ..services.image_storage import ImageType
 from ..services.invocation_services import InvocationServices
-from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
-from .image import ImageOutput, build_image_output
+from .baseinvocation import BaseInvocation, InvocationContext
+from .image import ImageField, ImageOutput
 
 
 class UpscaleInvocation(BaseInvocation):
@@ -22,15 +22,6 @@ class UpscaleInvocation(BaseInvocation):
     level: Literal[2, 4] = Field(default=2, description="The upscale level")
     #fmt: on
 
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["upscaling", "image"],
-            },
-        }
-
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get(
             self.image.image_type, self.image.image_name
@@ -49,9 +40,7 @@ class UpscaleInvocation(BaseInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, results[0][0], self.dict())
-        return build_image_output(
-            image_type=image_type,
-            image_name=image_name,
-            image=results[0][0]
-        )
+        context.services.images.save(image_type, image_name, results[0][0])
+        return ImageOutput(
+            image=ImageField(image_type=image_type, image_name=image_name)
+        )

invokeai/app/invocations/util/choose_model.py

@@ -1,14 +0,0 @@
-from invokeai.backend.model_management.model_manager import ModelManager
-
-
-def choose_model(model_manager: ModelManager, model_name: str):
-    """Returns the default model if the `model_name` not a valid model, else returns the selected model."""
-    if model_manager.valid_model(model_name):
-        model = model_manager.get_model(model_name)
-    else:
-        model = model_manager.get_model()
-        print(
-            f"* Warning: '{model_name}' is not a valid model name. Using default model \'{model['model_name']}\' instead."
-        )
-
-    return model

invokeai/app/models/exceptions.py

@@ -1,3 +0,0 @@
-class CanceledException(Exception):
-    """Execution canceled by user."""
-    pass

invokeai/app/models/image.py

@@ -1,26 +0,0 @@
-from enum import Enum
-from typing import Optional
-from pydantic import BaseModel, Field
-
-
-class ImageType(str, Enum):
-    RESULT = "results"
-    INTERMEDIATE = "intermediates"
-    UPLOAD = "uploads"
-
-
-class ImageField(BaseModel):
-    """An image field used for passing image objects between invocations"""
-
-    image_type: ImageType = Field(
-        default=ImageType.RESULT, description="The type of the image"
-    )
-    image_name: Optional[str] = Field(default=None, description="The name of the image")
-
-    class Config:
-        schema_extra = {
-            "required": [
-                "image_type",
-                "image_name",
-            ]
-        }

invokeai/app/models/metadata.py

@@ -1,26 +0,0 @@
-from typing import Any, Optional, Dict
-from pydantic import BaseModel, Field
-
-
-class InvokeAIMetadata(BaseModel):
-    """An image's InvokeAI-specific metadata"""
-
-    session: Optional[str] = Field(description="The session that generated this image")
-    source_id: Optional[str] = Field(
-        description="The source id of the invocation that generated this image"
-    )
-    # TODO: figure out metadata
-    invocation: Optional[Dict[str, Any]] = Field(
-        default={}, description="The prepared invocation that generated this image"
-    )
-
-
-class ImageMetadata(BaseModel):
-    """An image's general metadata"""
-
-    created: int = Field(description="The creation timestamp of the image")
-    width: int = Field(description="The width of the image in pixels")
-    height: int = Field(description="The height of the image in pixels")
-    invokeai: Optional[InvokeAIMetadata] = Field(
-        default={}, description="The image's InvokeAI-specific metadata"
-    )

invokeai/app/services/events.py

@@ -25,8 +25,7 @@ class EventServiceBase:
     def emit_generator_progress(
         self,
         graph_execution_state_id: str,
-        invocation_dict: dict,
-        source_id: str,
+        invocation_id: str,
         progress_image: ProgressImage | None,
         step: int,
         total_steps: int,
@@ -36,8 +35,7 @@ class EventServiceBase:
             event_name="generator_progress",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                invocation=invocation_dict,
-                source_id=source_id,
+                invocation_id=invocation_id,
                 progress_image=progress_image,
                 step=step,
                 total_steps=total_steps,
@@ -45,43 +43,40 @@ class EventServiceBase:
         )
 
     def emit_invocation_complete(
-        self, graph_execution_state_id: str, result: Dict, invocation_dict: Dict, source_id: str,
+        self, graph_execution_state_id: str, invocation_id: str, result: Dict
     ) -> None:
         """Emitted when an invocation has completed"""
         self.__emit_session_event(
             event_name="invocation_complete",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                invocation=invocation_dict,
-                source_id=source_id,
+                invocation_id=invocation_id,
                 result=result,
             ),
         )
 
     def emit_invocation_error(
-        self, graph_execution_state_id: str, invocation_dict: Dict, source_id: str, error: str
+        self, graph_execution_state_id: str, invocation_id: str, error: str
     ) -> None:
         """Emitted when an invocation has completed"""
         self.__emit_session_event(
             event_name="invocation_error",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                invocation=invocation_dict,
-                source_id=source_id,
+                invocation_id=invocation_id,
                 error=error,
             ),
         )
 
     def emit_invocation_started(
-        self, graph_execution_state_id: str, invocation_dict: Dict, source_id: str
+        self, graph_execution_state_id: str, invocation_id: str
     ) -> None:
         """Emitted when an invocation has started"""
         self.__emit_session_event(
             event_name="invocation_started",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                invocation=invocation_dict,
-                source_id=source_id,
+                invocation_id=invocation_id,
             ),
         )
 

invokeai/app/services/graph.py

@@ -127,13 +127,6 @@ class NodeAlreadyExecutedError(Exception):
 class GraphInvocationOutput(BaseInvocationOutput):
     type: Literal["graph_output"] = "graph_output"
 
-    class Config:
-        schema_extra = {
-            'required': [
-                'type',
-                'image',
-            ]
-        }
 
 # TODO: Fill this out and move to invocations
 class GraphInvocation(BaseInvocation):
@@ -154,13 +147,6 @@ class IterateInvocationOutput(BaseInvocationOutput):
 
     item: Any = Field(description="The item being iterated over")
 
-    class Config:
-        schema_extra = {
-            'required': [
-                'type',
-                'item',
-            ]
-        }
 
 # TODO: Fill this out and move to invocations
 class IterateInvocation(BaseInvocation):
@@ -183,13 +169,6 @@ class CollectInvocationOutput(BaseInvocationOutput):
 
     collection: list[Any] = Field(description="The collection of input items")
 
-    class Config:
-        schema_extra = {
-            'required': [
-                'type',
-                'collection',
-            ]
-        }
 
 class CollectInvocation(BaseInvocation):
     """Collects values into a collection"""
@@ -794,6 +773,9 @@ class GraphExecutionState(BaseModel):
         default_factory=dict,
     )
 
+    # Declare all fields as required; necessary for OpenAPI schema generation build.
+    # Technically only fields without a `default_factory` need to be listed here.
+    # See: https://github.com/pydantic/pydantic/discussions/4577
     class Config:
         schema_extra = {
             'required': [
@@ -1066,8 +1048,9 @@ class GraphExecutionState(BaseModel):
                 n
                 for n in prepared_nodes
                 if all(
-                    nx.has_path(execution_graph, pit[0], n)
+                    pit
                     for pit in parent_iterators
+                    if nx.has_path(execution_graph, pit[0], n)
                 )
             ),
             None,

invokeai/app/services/image_storage.py

@@ -2,26 +2,23 @@
 
 import datetime
 import os
-import json
-from glob import glob
 from abc import ABC, abstractmethod
 from enum import Enum
 from pathlib import Path
 from queue import Queue
-from typing import Any, Callable, Dict, List, Union
+from typing import Dict
 
 from PIL.Image import Image
-import PIL.Image as PILImage
-from pydantic import BaseModel, Json
-from invokeai.app.api.models.images import ImageResponse
-from invokeai.app.models.image import ImageField, ImageType
-from invokeai.app.models.metadata import ImageMetadata
-from invokeai.app.services.item_storage import PaginatedResults
-from invokeai.app.util.save_thumbnail import save_thumbnail
 
 from invokeai.backend.image_util import PngWriter
 
 
+class ImageType(str, Enum):
+    RESULT = "results"
+    INTERMEDIATE = "intermediates"
+    UPLOAD = "uploads"
+
+
 class ImageStorageBase(ABC):
     """Responsible for storing and retrieving images."""
 
@@ -29,21 +26,13 @@ class ImageStorageBase(ABC):
     def get(self, image_type: ImageType, image_name: str) -> Image:
         pass
 
-    @abstractmethod
-    def list(
-        self, image_type: ImageType, page: int = 0, per_page: int = 10
-    ) -> PaginatedResults[ImageResponse]:
-        pass
-
     # TODO: make this a bit more flexible for e.g. cloud storage
     @abstractmethod
-    def get_path(
-        self, image_type: ImageType, image_name: str, is_thumbnail: bool = False
-    ) -> str:
+    def get_path(self, image_type: ImageType, image_name: str) -> str:
         pass
 
     @abstractmethod
-    def save(self, image_type: ImageType, image_name: str, image: Image, metadata: Dict[str, Any] | None = None) -> str:
+    def save(self, image_type: ImageType, image_name: str, image: Image) -> None:
         pass
 
     @abstractmethod
@@ -77,60 +66,6 @@ class DiskImageStorage(ImageStorageBase):
             Path(os.path.join(output_folder, image_type)).mkdir(
                 parents=True, exist_ok=True
             )
-            Path(os.path.join(output_folder, image_type, "thumbnails")).mkdir(
-                parents=True, exist_ok=True
-            )
-
-    def list(
-        self, image_type: ImageType, page: int = 0, per_page: int = 10
-    ) -> PaginatedResults[ImageResponse]:
-        dir_path = os.path.join(self.__output_folder, image_type)
-        image_paths = glob(f"{dir_path}/*.png")
-        count = len(image_paths)
-
-        sorted_image_paths = sorted(
-            glob(f"{dir_path}/*.png"), key=os.path.getctime, reverse=True
-        )
-
-        page_of_image_paths = sorted_image_paths[
-            page * per_page : (page + 1) * per_page
-        ]
-
-        page_of_images: List[ImageResponse] = []
-
-        for path in page_of_image_paths:
-            filename = os.path.basename(path)
-            img = PILImage.open(path)
-            invokeai_metadata = json.loads(img.info.get("invokeai", "{}"))
-
-            page_of_images.append(
-                ImageResponse(
-                    image_type=image_type.value,
-                    image_name=filename,
-                    # TODO: DiskImageStorage should not be building URLs...?
-                    image_url=f"api/v1/images/{image_type.value}/{filename}",
-                    thumbnail_url=f"api/v1/images/{image_type.value}/thumbnails/{os.path.splitext(filename)[0]}.webp",
-                    # TODO: Creation of this object should happen elsewhere, just making it fit here so it works
-                    metadata=ImageMetadata(
-                        created=int(os.path.getctime(path)),
-                        width=img.width,
-                        height=img.height,
-                        invokeai=invokeai_metadata
-                    ),
-                )
-            )
-
-        page_count_trunc = int(count / per_page)
-        page_count_mod = count % per_page
-        page_count = page_count_trunc if page_count_mod == 0 else page_count_trunc + 1
-
-        return PaginatedResults[ImageResponse](
-            items=page_of_images,
-            page=page,
-            pages=page_count,
-            per_page=per_page,
-            total=count,
-        )
 
     def get(self, image_type: ImageType, image_name: str) -> Image:
         image_path = self.get_path(image_type, image_name)
@@ -138,52 +73,32 @@ class DiskImageStorage(ImageStorageBase):
         if cache_item:
             return cache_item
 
-        image = PILImage.open(image_path)
+        image = Image.open(image_path)
         self.__set_cache(image_path, image)
         return image
 
     # TODO: make this a bit more flexible for e.g. cloud storage
-    def get_path(
-        self, image_type: ImageType, image_name: str, is_thumbnail: bool = False
-    ) -> str:
-        if is_thumbnail:
-            path = os.path.join(
-                self.__output_folder, image_type, "thumbnails", image_name
-            )
-        else:
-            path = os.path.join(self.__output_folder, image_type, image_name)
+    def get_path(self, image_type: ImageType, image_name: str) -> str:
+        path = os.path.join(self.__output_folder, image_type, image_name)
         return path
 
-    def save(self, image_type: ImageType, image_name: str, image: Image, metadata: Dict[str, Any] | None = None) -> str:
-        print(metadata)
+    def save(self, image_type: ImageType, image_name: str, image: Image) -> None:
         image_subpath = os.path.join(image_type, image_name)
         self.__pngWriter.save_image_and_prompt_to_png(
-            image, "", image_subpath, metadata
+            image, "", image_subpath, None
         )  # TODO: just pass full path to png writer
-        save_thumbnail(
-            image=image,
-            filename=image_name,
-            path=os.path.join(self.__output_folder, image_type, "thumbnails"),
-        )
+
         image_path = self.get_path(image_type, image_name)
         self.__set_cache(image_path, image)
-        return image_path
 
     def delete(self, image_type: ImageType, image_name: str) -> None:
         image_path = self.get_path(image_type, image_name)
-        thumbnail_path = self.get_path(image_type, image_name, True)
         if os.path.exists(image_path):
             os.remove(image_path)
 
         if image_path in self.__cache:
             del self.__cache[image_path]
 
-        if os.path.exists(thumbnail_path):
-            os.remove(thumbnail_path)
-
-        if thumbnail_path in self.__cache:
-            del self.__cache[thumbnail_path]
-
     def __get_cache(self, image_name: str) -> Image:
         return None if image_name not in self.__cache else self.__cache[image_name]
 

invokeai/app/services/invocation_services.py

@@ -2,7 +2,6 @@
 from invokeai.backend import ModelManager
 
 from .events import EventServiceBase
-from .latent_storage import LatentsStorageBase
 from .image_storage import ImageStorageBase
 from .restoration_services import RestorationServices
 from .invocation_queue import InvocationQueueABC
@@ -12,7 +11,6 @@ class InvocationServices:
     """Services that can be used by invocations"""
 
     events: EventServiceBase
-    latents: LatentsStorageBase
     images: ImageStorageBase
     queue: InvocationQueueABC
     model_manager: ModelManager
@@ -26,7 +24,6 @@ class InvocationServices:
             self,
             model_manager: ModelManager,
             events: EventServiceBase,
-            latents: LatentsStorageBase,
             images: ImageStorageBase,
             queue: InvocationQueueABC,
             graph_execution_manager: ItemStorageABC["GraphExecutionState"],
@@ -35,7 +32,6 @@ class InvocationServices:
     ):
         self.model_manager = model_manager
         self.events = events
-        self.latents = latents
         self.images = images
         self.queue = queue
         self.graph_execution_manager = graph_execution_manager

invokeai/app/services/invoker.py

@@ -33,6 +33,7 @@ class Invoker:
         self.services.graph_execution_manager.set(graph_execution_state)
 
         # Queue the invocation
+        print(f"queueing item {invocation.id}")
         self.services.queue.put(
             InvocationQueueItem(
                 # session_id    = session.id,

invokeai/app/services/latent_storage.py

@@ -1,93 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-import os
-from abc import ABC, abstractmethod
-from pathlib import Path
-from queue import Queue
-from typing import Dict
-
-import torch
-
-class LatentsStorageBase(ABC):
-    """Responsible for storing and retrieving latents."""
-
-    @abstractmethod
-    def get(self, name: str) -> torch.Tensor:
-        pass
-
-    @abstractmethod
-    def set(self, name: str, data: torch.Tensor) -> None:
-        pass
-
-    @abstractmethod
-    def delete(self, name: str) -> None:
-        pass
-
-
-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):
-        self.__underlying_storage = underlying_storage
-        self.__cache = dict()
-        self.__cache_ids = Queue()
-        self.__max_cache_size = max_cache_size
-
-    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 set(self, name: str, data: torch.Tensor) -> None:
-        self.__underlying_storage.set(name, data)
-        self.__set_cache(name, data)
-
-    def delete(self, name: str) -> None:
-        self.__underlying_storage.delete(name)
-        if name in self.__cache:
-            del self.__cache[name]
-
-    def __get_cache(self, name: str) -> torch.Tensor|None:
-        return None if name not in self.__cache else self.__cache[name]
-
-    def __set_cache(self, name: str, data: torch.Tensor):
-        if not name 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())
-
-
-class DiskLatentsStorage(LatentsStorageBase):
-    """Stores latents in a folder on disk without caching"""
-
-    __output_folder: str
-
-    def __init__(self, output_folder: str):
-        self.__output_folder = output_folder
-        Path(output_folder).mkdir(parents=True, exist_ok=True)
-
-    def get(self, name: str) -> torch.Tensor:
-        latent_path = self.get_path(name)
-        return torch.load(latent_path)
-
-    def set(self, name: str, data: torch.Tensor) -> None:
-        latent_path = self.get_path(name)
-        torch.save(data, latent_path)
-
-    def delete(self, name: str) -> None:
-        latent_path = self.get_path(name)
-        os.remove(latent_path)
-
-    def get_path(self, name: str) -> str:
-        return os.path.join(self.__output_folder, name)
-    

invokeai/app/services/processor.py

@@ -4,7 +4,7 @@ from threading import Event, Thread
 from ..invocations.baseinvocation import InvocationContext
 from .invocation_queue import InvocationQueueItem
 from .invoker import InvocationProcessorABC, Invoker
-from ..models.exceptions import CanceledException
+
 
 class DefaultInvocationProcessor(InvocationProcessorABC):
     __invoker_thread: Thread
@@ -43,14 +43,10 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     queue_item.invocation_id
                 )
 
-                # get the source node to provide to cliepnts (the prepared node is not as useful)
-                source_id = graph_execution_state.prepared_source_mapping[invocation.id]
-
                 # Send starting event
                 self.__invoker.services.events.emit_invocation_started(
                     graph_execution_state_id=graph_execution_state.id,
-                    invocation_dict=invocation.dict(),
-                    source_id=source_id
+                    invocation_id=invocation.id,
                 )
 
                 # Invoke
@@ -79,17 +75,13 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     # Send complete event
                     self.__invoker.services.events.emit_invocation_complete(
                         graph_execution_state_id=graph_execution_state.id,
-                        invocation_dict=invocation.dict(),
-                        source_id=source_id,
+                        invocation_id=invocation.id,
                         result=outputs.dict(),
                     )
 
                 except KeyboardInterrupt:
                     pass
 
-                except CanceledException:
-                    pass
-
                 except Exception as e:
                     error = traceback.format_exc()
 
@@ -104,8 +96,7 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     # Send error event
                     self.__invoker.services.events.emit_invocation_error(
                         graph_execution_state_id=graph_execution_state.id,
-                        invocation_dict=invocation.dict(),
-                        source_id=source_id,
+                        invocation_id=invocation.id,
                         error=error,
                     )
 

invokeai/app/services/sqlite.py

@@ -1,25 +1,23 @@
+import sqlite3
+from threading import Lock
 from typing import Generic, TypeVar, Union, get_args
+
 from pydantic import BaseModel, parse_raw_as
 
 from .item_storage import ItemStorageABC, PaginatedResults
 
-from sqlalchemy import create_engine, String, TEXT, Engine, select
-from sqlalchemy.orm import DeclarativeBase, mapped_column, Session
-
-
 T = TypeVar("T", bound=BaseModel)
 
-
-class Base(DeclarativeBase):
-    pass
+sqlite_memory = ":memory:"
 
 
 class SqliteItemStorage(ItemStorageABC, Generic[T]):
     _filename: str
     _table_name: str
+    _conn: sqlite3.Connection
+    _cursor: sqlite3.Cursor
     _id_field: str
-    _engine: Engine
-    # _table: ??? # TODO: figure out how to type this
+    _lock: Lock
 
     def __init__(self, filename: str, table_name: str, id_field: str = "id"):
         super().__init__()
@@ -27,79 +25,84 @@ class SqliteItemStorage(ItemStorageABC, Generic[T]):
         self._filename = filename
         self._table_name = table_name
         self._id_field = id_field  # TODO: validate that T has this field
+        self._lock = Lock()
+
+        self._conn = sqlite3.connect(
+            self._filename, check_same_thread=False
+        )  # TODO: figure out a better threading solution
+        self._cursor = self._conn.cursor()
 
-        self._engine = create_engine(f"sqlite+pysqlite:///{self._filename}")
         self._create_table()
 
     def _create_table(self):
-        # dynamically create the ORM model class to avoid name collisions
-
-        # cannot access `self.__orig_class__` in `__init__` or `__new__` so
-        # format the table name into the class name
-        pascal_table_name = self._table_name.replace("_", " ").title()
-        pascal_table_name = pascal_table_name.replace(" ", "")
-
-        table_dict = dict(
-            __tablename__=self._table_name,
-            id=mapped_column(String, primary_key=True),
-            item=mapped_column(TEXT, nullable=False),
-        )
-
-        self._table = type(pascal_table_name, (Base,), table_dict)
-
-        Base.metadata.create_all(self._engine)
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                f"""CREATE TABLE IF NOT EXISTS {self._table_name} (
+                item TEXT,
+                id TEXT GENERATED ALWAYS AS (json_extract(item, '$.{self._id_field}')) VIRTUAL NOT NULL);"""
+            )
+            self._cursor.execute(
+                f"""CREATE UNIQUE INDEX IF NOT EXISTS {self._table_name}_id ON {self._table_name}(id);"""
+            )
+        finally:
+            self._lock.release()
 
     def _parse_item(self, item: str) -> T:
         item_type = get_args(self.__orig_class__)[0]
         return parse_raw_as(item_type, item)
 
     def set(self, item: T):
-        session = Session(self._engine)
-
-        item_id = str(getattr(item, self._id_field))
-        new_item = self._table(id=item_id, item=item.json())
-
-        session.merge(new_item)
-
-        session.commit()
-        session.close()
-
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                f"""INSERT OR REPLACE INTO {self._table_name} (item) VALUES (?);""",
+                (item.json(),),
+            )
+        finally:
+            self._lock.release()
         self._on_changed(item)
 
     def get(self, id: str) -> Union[T, None]:
-        session = Session(self._engine)
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                f"""SELECT item FROM {self._table_name} WHERE id = ?;""", (str(id),)
+            )
+            result = self._cursor.fetchone()
+        finally:
+            self._lock.release()
 
-        item = session.get(self._table, str(id))
-
-        session.close()
-
-        if not item:
+        if not result:
             return None
 
-        return self._parse_item(item.item)
+        return self._parse_item(result[0])
 
     def delete(self, id: str):
-        session = Session(self._engine)
-
-        item = session.get(self._table, id)
-        session.delete(item)
-
-        session.commit()
-        session.close()
-
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                f"""DELETE FROM {self._table_name} WHERE id = ?;""", (str(id),)
+            )
+        finally:
+            self._lock.release()
         self._on_deleted(id)
 
     def list(self, page: int = 0, per_page: int = 10) -> PaginatedResults[T]:
-        session = Session(self._engine)
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                f"""SELECT item FROM {self._table_name} LIMIT ? OFFSET ?;""",
+                (per_page, page * per_page),
+            )
+            result = self._cursor.fetchall()
 
-        stmt = select(self._table.item).limit(per_page).offset(page * per_page)
-        result = session.execute(stmt)
+            items = list(map(lambda r: self._parse_item(r[0]), result))
 
-        items = list(map(lambda r: self._parse_item(r[0]), result))
-        count = session.query(self._table.item).count()
-
-        session.commit()
-        session.close()
+            self._cursor.execute(f"""SELECT count(*) FROM {self._table_name};""")
+            count = self._cursor.fetchone()[0]
+        finally:
+            self._lock.release()
 
         pageCount = int(count / per_page) + 1
 
@@ -110,19 +113,23 @@ class SqliteItemStorage(ItemStorageABC, Generic[T]):
     def search(
         self, query: str, page: int = 0, per_page: int = 10
     ) -> PaginatedResults[T]:
-        session = Session(self._engine)
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                f"""SELECT item FROM {self._table_name} WHERE item LIKE ? LIMIT ? OFFSET ?;""",
+                (f"%{query}%", per_page, page * per_page),
+            )
+            result = self._cursor.fetchall()
 
-        stmt = (
-            session.query(self._table)
-            .where(self._table.item.like(f"%{query}%"))
-            .limit(per_page)
-            .offset(page * per_page)
-        )
+            items = list(map(lambda r: self._parse_item(r[0]), result))
 
-        result = session.execute(stmt)
-
-        items = list(map(lambda r: self._parse_item(r[0].item), result))
-        count = session.query(self._table.item).count()
+            self._cursor.execute(
+                f"""SELECT count(*) FROM {self._table_name} WHERE item LIKE ?;""",
+                (f"%{query}%",),
+            )
+            count = self._cursor.fetchone()[0]
+        finally:
+            self._lock.release()
 
         pageCount = int(count / per_page) + 1
 

invokeai/app/util/save_thumbnail.py

@@ -1,25 +0,0 @@
-import os
-from PIL import Image
-
-
-def save_thumbnail(
-    image: Image.Image,
-    filename: str,
-    path: str,
-    size: int = 256,
-) -> str:
-    """
-    Saves a thumbnail of an image, returning its path.
-    """
-    base_filename = os.path.splitext(filename)[0]
-    thumbnail_path = os.path.join(path, base_filename + ".webp")
-
-    if os.path.exists(thumbnail_path):
-        return thumbnail_path
-
-    image_copy = image.copy()
-    image_copy.thumbnail(size=(size, size))
-
-    image_copy.save(thumbnail_path, "WEBP")
-
-    return thumbnail_path

invokeai/app/util/step_callback.py

@@ -1,50 +0,0 @@
-from re import S
-import torch
-from ..invocations.baseinvocation import InvocationContext
-from ...backend.util.util import image_to_dataURL
-from ...backend.generator.base import Generator
-from ...backend.stable_diffusion import PipelineIntermediateState
-
-def fast_latents_step_callback(
-    sample: torch.Tensor,
-    step: int,
-    steps: int,
-    id: str,
-    context: InvocationContext,
-):
-    # TODO: only output a preview image when requested
-    image = Generator.sample_to_lowres_estimated_image(sample)
-
-    (width, height) = image.size
-    width *= 8
-    height *= 8
-
-    dataURL = image_to_dataURL(image, image_format="JPEG")
-
-    graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
-    source_id = graph_execution_state.prepared_source_mapping[id]
-
-    invocation = graph_execution_state.execution_graph.get_node(id)
-
-    context.services.events.emit_generator_progress(
-        graph_execution_state_id=context.graph_execution_state_id,
-        invocation_dict=invocation.dict(),
-        source_id=source_id,
-        progress_image={"width": width, "height": height, "dataURL": dataURL},
-        step=step,
-        total_steps=steps,
-    )
-
-
-def diffusers_step_callback_adapter(*cb_args, **kwargs):
-    """
-    txt2img gives us a Tensor in the step_callbak, while img2img gives us a PipelineIntermediateState.
-    This adapter grabs the needed data and passes it along to the callback function.
-    """
-    if isinstance(cb_args[0], PipelineIntermediateState):
-        progress_state: PipelineIntermediateState = cb_args[0]
-        return fast_latents_step_callback(
-            progress_state.latents, progress_state.step, **kwargs
-        )
-    else:
-        return fast_latents_step_callback(*cb_args, **kwargs)

invokeai/backend/args.py

@@ -561,7 +561,7 @@ class Args(object):
             "--autoimport",
             default=None,
             type=str,
-            help="(DEPRECATED - NONFUNCTIONAL). Check the indicated directory for .ckpt/.safetensors weights files at startup and import directly",
+            help="Check the indicated directory for .ckpt/.safetensors weights files at startup and import directly",
         )
         model_group.add_argument(
             "--autoconvert",

invokeai/backend/config/model_install_backend.py

@@ -67,6 +67,7 @@ def install_requested_models(
     scan_directory: Path = None,
     external_models: List[str] = None,
     scan_at_startup: bool = False,
+    convert_to_diffusers: bool = False,
     precision: str = "float16",
     purge_deleted: bool = False,
     config_file_path: Path = None,
@@ -112,6 +113,7 @@ def install_requested_models(
             try:
                 model_manager.heuristic_import(
                     path_url_or_repo,
+                    convert=convert_to_diffusers,
                     commit_to_conf=config_file_path,
                 )
             except KeyboardInterrupt:
@@ -120,7 +122,7 @@ def install_requested_models(
                 pass
 
     if scan_at_startup and scan_directory.is_dir():
-        argument = "--autoconvert"
+        argument = "--autoconvert" if convert_to_diffusers else "--autoimport"
         initfile = Path(Globals.root, Globals.initfile)
         replacement = Path(Globals.root, f"{Globals.initfile}.new")
         directory = str(scan_directory).replace("\\", "/")

invokeai/backend/generator/base.py

@@ -21,7 +21,7 @@ from PIL import Image, ImageChops, ImageFilter
 from accelerate.utils import set_seed
 from diffusers import DiffusionPipeline
 from tqdm import trange
-from typing import Callable, List, Iterator, Optional, Type
+from typing import List, Iterator, Type
 from dataclasses import dataclass, field
 from diffusers.schedulers import SchedulerMixin as Scheduler
 
@@ -35,23 +35,23 @@ downsampling = 8
 
 @dataclass
 class InvokeAIGeneratorBasicParams:
-    seed: Optional[int]=None
+    seed: int=None
     width: int=512
     height: int=512
-    cfg_scale: float=7.5
+    cfg_scale: int=7.5
     steps: int=20
     ddim_eta: float=0.0
-    scheduler: str='ddim'
+    scheduler: int='ddim'
     precision: str='float16'
     perlin: float=0.0
-    threshold: float=0.0
+    threshold: int=0.0
     seamless: bool=False
     seamless_axes: List[str]=field(default_factory=lambda: ['x', 'y'])
-    h_symmetry_time_pct: Optional[float]=None
-    v_symmetry_time_pct: Optional[float]=None
+    h_symmetry_time_pct: float=None
+    v_symmetry_time_pct: float=None
     variation_amount: float = 0.0
     with_variations: list=field(default_factory=list)
-    safety_checker: Optional[SafetyChecker]=None
+    safety_checker: SafetyChecker=None
 
 @dataclass
 class InvokeAIGeneratorOutput:
@@ -61,10 +61,10 @@ class InvokeAIGeneratorOutput:
     and the model hash, as well as all the generate() parameters that went into
     generating the image (in .params, also available as attributes)
     '''
-    image: Image.Image
+    image: Image
     seed: int
     model_hash: str
-    attention_maps_images: List[Image.Image]
+    attention_maps_images: List[Image]
     params: Namespace
 
 # we are interposing a wrapper around the original Generator classes so that
@@ -92,8 +92,8 @@ class InvokeAIGenerator(metaclass=ABCMeta):
 
     def generate(self,
                  prompt: str='',
-                 callback: Optional[Callable]=None,
-                 step_callback: Optional[Callable]=None,
+                 callback: callable=None,
+                 step_callback: callable=None,
                  iterations: int=1,
                  **keyword_args,
                  )->Iterator[InvokeAIGeneratorOutput]:
@@ -154,7 +154,6 @@ class InvokeAIGenerator(metaclass=ABCMeta):
         for i in iteration_count:
             results = generator.generate(prompt,
                                          conditioning=(uc, c, extra_conditioning_info),
-                                         step_callback=step_callback,
                                          sampler=scheduler,
                                          **generator_args,
                                          )
@@ -206,10 +205,10 @@ class Txt2Img(InvokeAIGenerator):
 # ------------------------------------
 class Img2Img(InvokeAIGenerator):
     def generate(self,
-               init_image: Image.Image | torch.FloatTensor,
+               init_image: Image | torch.FloatTensor,
                strength: float=0.75,
                **keyword_args
-               )->Iterator[InvokeAIGeneratorOutput]:
+               )->List[InvokeAIGeneratorOutput]:
         return super().generate(init_image=init_image,
                                 strength=strength,
                                 **keyword_args
@@ -223,7 +222,7 @@ class Img2Img(InvokeAIGenerator):
 # Takes all the arguments of Img2Img and adds the mask image and the seam/infill stuff
 class Inpaint(Img2Img):
     def generate(self,
-                 mask_image: Image.Image | torch.FloatTensor,
+                 mask_image: Image | torch.FloatTensor,
                  # Seam settings - when 0, doesn't fill seam
                  seam_size: int = 0,
                  seam_blur: int = 0,
@@ -236,7 +235,7 @@ class Inpaint(Img2Img):
                  inpaint_height=None,
                  inpaint_fill: tuple(int) = (0x7F, 0x7F, 0x7F, 0xFF),
                  **keyword_args
-                 )->Iterator[InvokeAIGeneratorOutput]:
+                 )->List[InvokeAIGeneratorOutput]:
         return super().generate(
             mask_image=mask_image,
             seam_size=seam_size,
@@ -263,7 +262,7 @@ class Embiggen(Txt2Img):
             embiggen: list=None,
             embiggen_tiles: list = None,
             strength: float=0.75,
-            **kwargs)->Iterator[InvokeAIGeneratorOutput]:
+            **kwargs)->List[InvokeAIGeneratorOutput]:
         return super().generate(embiggen=embiggen,
                                 embiggen_tiles=embiggen_tiles,
                                 strength=strength,

invokeai/backend/image_util/pngwriter.py

@@ -41,7 +41,7 @@ class PngWriter:
         info = PngImagePlugin.PngInfo()
         info.add_text("Dream", dream_prompt)
         if metadata:
-            info.add_text("invokeai", json.dumps(metadata))
+            info.add_text("sd-metadata", json.dumps(metadata))
         image.save(path, "PNG", pnginfo=info, compress_level=compress_level)
         return path
 

invokeai/backend/model_management/__init__.py

@@ -7,4 +7,3 @@ from .convert_ckpt_to_diffusers import (
 )
 from .model_manager import ModelManager
 
-

invokeai/backend/model_management/convert_ckpt_to_diffusers.py

@@ -372,32 +372,22 @@ def convert_ldm_unet_checkpoint(checkpoint, config, path=None, extract_ema=False
     unet_key = "model.diffusion_model."
     # at least a 100 parameters have to start with `model_ema` in order for the checkpoint to be EMA
     if sum(k.startswith("model_ema") for k in keys) > 100:
-        print(f"   | Checkpoint {path} has both EMA and non-EMA weights.")
+        print(f"  | Checkpoint {path} has both EMA and non-EMA weights.")
         if extract_ema:
-            print("   | Extracting EMA weights (usually better for inference)")
+            print("  | Extracting EMA weights (usually better for inference)")
             for key in keys:
                 if key.startswith("model.diffusion_model"):
                     flat_ema_key = "model_ema." + "".join(key.split(".")[1:])
-                    flat_ema_key_alt = "model_ema." + "".join(key.split(".")[2:])
-                    if flat_ema_key in checkpoint:
-                        unet_state_dict[key.replace(unet_key, "")] = checkpoint.pop(
-                            flat_ema_key
-                        )
-                    elif flat_ema_key_alt in checkpoint:
-                        unet_state_dict[key.replace(unet_key, "")] = checkpoint.pop(
-                            flat_ema_key_alt
-                        )
-                    else:
-                        unet_state_dict[key.replace(unet_key, "")] = checkpoint.pop(
-                            key
-                        )
+                    unet_state_dict[key.replace(unet_key, "")] = checkpoint.pop(
+                        flat_ema_key
+                    )
         else:
             print(
-                "   | Extracting only the non-EMA weights (usually better for fine-tuning)"
+                "  | Extracting only the non-EMA weights (usually better for fine-tuning)"
             )
 
     for key in keys:
-        if key.startswith("model.diffusion_model") and key in checkpoint:
+        if key.startswith(unet_key):
             unet_state_dict[key.replace(unet_key, "")] = checkpoint.pop(key)
 
     new_checkpoint = {}
@@ -1036,15 +1026,6 @@ def convert_open_clip_checkpoint(checkpoint):
 
     return text_model
 
-def replace_checkpoint_vae(checkpoint, vae_path:str):
-    if vae_path.endswith(".safetensors"):
-        vae_ckpt = load_file(vae_path)
-    else:
-        vae_ckpt = torch.load(vae_path, map_location="cpu")
-    state_dict = vae_ckpt['state_dict'] if "state_dict" in vae_ckpt else vae_ckpt
-    for vae_key in state_dict:
-        new_key = f'first_stage_model.{vae_key}'
-        checkpoint[new_key] = state_dict[vae_key]
 
 def load_pipeline_from_original_stable_diffusion_ckpt(
     checkpoint_path: str,
@@ -1057,10 +1038,8 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
     extract_ema: bool = True,
     upcast_attn: bool = False,
     vae: AutoencoderKL = None,
-    vae_path: str = None,
     precision: torch.dtype = torch.float32,
     return_generator_pipeline: bool = False,
-    scan_needed:bool=True,
 ) -> Union[StableDiffusionPipeline, StableDiffusionGeneratorPipeline]:
     """
     Load a Stable Diffusion pipeline object from a CompVis-style `.ckpt`/`.safetensors` file and (ideally) a `.yaml`
@@ -1088,8 +1067,6 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
     :param precision: precision to use - torch.float16, torch.float32 or torch.autocast
     :param upcast_attention: Whether the attention computation should always be upcasted. This is necessary when
     running stable diffusion 2.1.
-    :param vae: A diffusers VAE to load into the pipeline.
-    :param vae_path: Path to a checkpoint VAE that will be converted into diffusers and loaded into the pipeline.
     """
 
     with warnings.catch_warnings():
@@ -1097,13 +1074,12 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
         verbosity = dlogging.get_verbosity()
         dlogging.set_verbosity_error()
 
-        if Path(checkpoint_path).suffix == '.ckpt':
-            if scan_needed:
-                ModelManager.scan_model(checkpoint_path,checkpoint_path)
-            checkpoint = torch.load(checkpoint_path)
-        else:
-            checkpoint = load_file(checkpoint_path)
-
+        checkpoint = (
+            torch.load(checkpoint_path)
+            if Path(checkpoint_path).suffix == ".ckpt"
+            else load_file(checkpoint_path)
+            
+        )
         cache_dir = global_cache_dir("hub")
         pipeline_class = (
             StableDiffusionGeneratorPipeline
@@ -1115,7 +1091,7 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
         if "global_step" in checkpoint:
             global_step = checkpoint["global_step"]
         else:
-            print("   | global_step key not found in model")
+            print("  | global_step key not found in model")
             global_step = None
 
         # sometimes there is a state_dict key and sometimes not
@@ -1226,19 +1202,9 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
 
         unet.load_state_dict(converted_unet_checkpoint)
 
-        # If a replacement VAE path was specified, we'll incorporate that into
-        # the checkpoint model and then convert it
-        if vae_path:
-            print(f"   | Converting VAE {vae_path}")
-            replace_checkpoint_vae(checkpoint,vae_path)
-        # otherwise we use the original VAE, provided that
-        # an externally loaded diffusers VAE was not passed
-        elif not vae:
-            print("   | Using checkpoint model's original VAE")
-
-        if vae:
-            print("   | Using replacement diffusers VAE")
-        else:  # convert the original or replacement VAE
+        # Convert the VAE model, or use the one passed
+        if not vae:
+            print("  | Using checkpoint model's original VAE")
             vae_config = create_vae_diffusers_config(
                 original_config, image_size=image_size
             )
@@ -1248,6 +1214,8 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
 
             vae = AutoencoderKL(**vae_config)
             vae.load_state_dict(converted_vae_checkpoint)
+        else:
+            print("  | Using external VAE specified in config")
 
         # Convert the text model.
         model_type = pipeline_type
@@ -1264,10 +1232,10 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
                 cache_dir=cache_dir,
             )
             pipe = pipeline_class(
-                vae=vae.to(precision),
-                text_encoder=text_model.to(precision),
+                vae=vae,
+                text_encoder=text_model,
                 tokenizer=tokenizer,
-                unet=unet.to(precision),
+                unet=unet,
                 scheduler=scheduler,
                 safety_checker=None,
                 feature_extractor=None,

invokeai/backend/model_management/model_manager.py

@@ -1,4 +1,4 @@
-"""enum
+"""
 Manage a cache of Stable Diffusion model files for fast switching.
 They are moved between GPU and CPU as necessary. If CPU memory falls
 below a preset minimum, the least recently used model will be
@@ -15,21 +15,17 @@ import sys
 import textwrap
 import time
 import warnings
-from enum import Enum, auto
+from enum import Enum
 from pathlib import Path
 from shutil import move, rmtree
-from typing import Any, Optional, Union, Callable
+from typing import Any, Optional, Union
 
 import safetensors
 import safetensors.torch
 import torch
 import transformers
-from diffusers import (
-    AutoencoderKL,
-    UNet2DConditionModel,
-    SchedulerMixin,
-    logging as dlogging,
-)    
+from diffusers import AutoencoderKL
+from diffusers import logging as dlogging
 from huggingface_hub import scan_cache_dir
 from omegaconf import OmegaConf
 from omegaconf.dictconfig import DictConfig
@@ -37,58 +33,40 @@ from picklescan.scanner import scan_file_path
 
 from invokeai.backend.globals import Globals, global_cache_dir
 
-from transformers import (
-    CLIPTextModel,
-    CLIPTokenizer,
-    CLIPFeatureExtractor,
-)
-from diffusers.pipelines.stable_diffusion.safety_checker import (
-    StableDiffusionSafetyChecker,
-    )
-from ..stable_diffusion import (
-    StableDiffusionGeneratorPipeline,
-)
-from ..util import CUDA_DEVICE, ask_user, download_with_resume
-
+from ..stable_diffusion import StableDiffusionGeneratorPipeline
+from ..util import CUDA_DEVICE, CPU_DEVICE, ask_user, download_with_resume
 
 class SDLegacyType(Enum):
-    V1 = auto()
-    V1_INPAINT = auto()
-    V2 = auto()
-    V2_e = auto()
-    V2_v = auto()
-    UNKNOWN = auto()
+    V1 = 1
+    V1_INPAINT = 2
+    V2   = 3
+    V2_e = 4
+    V2_v = 5
+    UNKNOWN = 99
 
-class SDModelComponent(Enum):
-    vae="vae"
-    text_encoder="text_encoder"
-    tokenizer="tokenizer"
-    unet="unet"
-    scheduler="scheduler"
-    safety_checker="safety_checker"
-    feature_extractor="feature_extractor"
-    
 DEFAULT_MAX_MODELS = 2
+VAE_TO_REPO_ID = {  # hack, see note in convert_and_import()
+    "vae-ft-mse-840000-ema-pruned": "stabilityai/sd-vae-ft-mse",
+}
 
 class ModelManager(object):
-    """
+    '''
     Model manager handles loading, caching, importing, deleting, converting, and editing models.
-    """
-
+    '''
     def __init__(
-        self,
-        config: OmegaConf | Path,
-        device_type: torch.device = CUDA_DEVICE,
-        precision: str = "float16",
-        max_loaded_models=DEFAULT_MAX_MODELS,
-        sequential_offload=False,
-        embedding_path: Path = None,
+            self,
+            config: OmegaConf|Path,
+            device_type: torch.device = CUDA_DEVICE,
+            precision: str = "float16",
+            max_loaded_models=DEFAULT_MAX_MODELS,
+            sequential_offload=False,
+            embedding_path: Path=None,
     ):
         """
         Initialize with the path to the models.yaml config file or
         an initialized OmegaConf dictionary. Optional parameters
         are the torch device type, precision, max_loaded_models,
-        and sequential_offload boolean. Note that the default device
+        and sequential_offload boolean. Note that the default device 
         type and precision are set up for a CUDA system running at half precision.
         """
         # prevent nasty-looking CLIP log message
@@ -112,25 +90,15 @@ class ModelManager(object):
         """
         return model_name in self.config
 
-    def get_model(self, model_name: str = None) -> dict:
-        """Given a model named identified in models.yaml, return a dict
-        containing the model object and some of its key features. If
-        in RAM will load into GPU VRAM.  If on disk, will load from
-        there.
-        The dict has the following keys:
-        'model': The StableDiffusionGeneratorPipeline object
-        'model_name': The name of the model in models.yaml
-        'width': The width of images trained by this model
-        'height': The height of images trained by this model
-        'hash': A unique hash of this model's files on disk.
+    def get_model(self, model_name: str=None)->dict:
+        """
+        Given a model named identified in models.yaml, return
+        the model object. If in RAM will load into GPU VRAM.
+        If on disk, will load from there.
         """
         if not model_name:
-            return (
-                self.get_model(self.current_model)
-                if self.current_model
-                else self.get_model(self.default_model())
-            )
-
+            return self.get_model(self.current_model) if self.current_model else self.get_model(self.default_model())
+        
         if not self.valid_model(model_name):
             print(
                 f'** "{model_name}" is not a known model name. Please check your models.yaml file'
@@ -170,81 +138,6 @@ class ModelManager(object):
             "hash": hash,
         }
 
-    def get_model_vae(self, model_name: str=None)->AutoencoderKL:
-        """Given a model name identified in models.yaml, load the model into
-        GPU if necessary and return its assigned VAE as an
-        AutoencoderKL object. If no model name is provided, return the
-        vae from the model currently in the GPU.
-        """
-        return self._get_sub_model(model_name, SDModelComponent.vae)
-                                   
-    def get_model_tokenizer(self, model_name: str=None)->CLIPTokenizer:
-        """Given a model name identified in models.yaml, load the model into
-        GPU if necessary and return its assigned CLIPTokenizer. If no
-        model name is provided, return the tokenizer from the model
-        currently in the GPU.
-        """
-        return self._get_sub_model(model_name, SDModelComponent.tokenizer)
-                                   
-    def get_model_unet(self, model_name: str=None)->UNet2DConditionModel:
-        """Given a model name identified in models.yaml, load the model into
-        GPU if necessary and return its assigned UNet2DConditionModel. If no model
-        name is provided, return the UNet from the model
-        currently in the GPU.  
-        """
-        return self._get_sub_model(model_name, SDModelComponent.unet)
-
-    def get_model_text_encoder(self, model_name: str=None)->CLIPTextModel:
-        """Given a model name identified in models.yaml, load the model into
-        GPU if necessary and return its assigned CLIPTextModel. If no
-        model name is provided, return the text encoder from the model
-        currently in the GPU.
-        """
-        return self._get_sub_model(model_name, SDModelComponent.text_encoder)
-
-    def get_model_feature_extractor(self, model_name: str=None)->CLIPFeatureExtractor:
-        """Given a model name identified in models.yaml, load the model into
-        GPU if necessary and return its assigned CLIPFeatureExtractor. If no
-        model name is provided, return the text encoder from the model
-        currently in the GPU.
-        """
-        return self._get_sub_model(model_name, SDModelComponent.feature_extractor)
-
-    def get_model_scheduler(self, model_name: str=None)->SchedulerMixin:
-        """Given a model name identified in models.yaml, load the model into
-        GPU if necessary and return its assigned scheduler. If no
-        model name is provided, return the text encoder from the model
-        currently in the GPU.
-        """
-        return self._get_sub_model(model_name, SDModelComponent.scheduler)
-    
-    def _get_sub_model(
-            self,
-            model_name: str=None,
-            model_part: SDModelComponent=SDModelComponent.vae,
-    ) -> Union[
-        AutoencoderKL,
-        CLIPTokenizer,
-        CLIPFeatureExtractor,
-        UNet2DConditionModel,
-        CLIPTextModel,
-        StableDiffusionSafetyChecker,
-    ]:
-        """Given a model name identified in models.yaml, and the part of the
-        model you wish to retrieve, return that part. Parts are in an Enum
-        class named SDModelComponent, and consist of:
-        SDModelComponent.vae
-        SDModelComponent.text_encoder
-        SDModelComponent.tokenizer
-        SDModelComponent.unet
-        SDModelComponent.scheduler
-        SDModelComponent.safety_checker
-        SDModelComponent.feature_extractor
-        """
-        model_dict = self.get_model(model_name)
-        model = model_dict["model"]
-        return getattr(model, model_part.value)
-
     def default_model(self) -> str | None:
         """
         Returns the name of the default model, or None
@@ -392,13 +285,13 @@ class ModelManager(object):
             self.stack.remove(model_name)
         if delete_files:
             if weights:
-                print(f"** Deleting file {weights}")
+                print(f"** deleting file {weights}")
                 Path(weights).unlink(missing_ok=True)
             elif path:
-                print(f"** Deleting directory {path}")
+                print(f"** deleting directory {path}")
                 rmtree(path, ignore_errors=True)
             elif repo_id:
-                print(f"** Deleting the cached model directory for {repo_id}")
+                print(f"** deleting the cached model directory for {repo_id}")
                 self._delete_model_from_cache(repo_id)
 
     def add_model(
@@ -469,8 +362,7 @@ class ModelManager(object):
             raise NotImplementedError(
                 f"Unknown model format {model_name}: {model_format}"
             )
-        self._add_embeddings_to_model(model)
-
+        
         # usage statistics
         toc = time.time()
         print(">> Model loaded in", "%4.2fs" % (toc - tic))
@@ -489,9 +381,9 @@ class ModelManager(object):
 
         print(f">> Loading diffusers model from {name_or_path}")
         if using_fp16:
-            print("   | Using faster float16 precision")
+            print("  | Using faster float16 precision")
         else:
-            print("   | Using more accurate float32 precision")
+            print("  | Using more accurate float32 precision")
 
         # TODO: scan weights maybe?
         pipeline_args: dict[str, Any] = dict(
@@ -542,7 +434,9 @@ class ModelManager(object):
         # square images???
         width = pipeline.unet.config.sample_size * pipeline.vae_scale_factor
         height = width
-        print(f"   | Default image dimensions = {width} x {height}")
+
+        print(f"  | Default image dimensions = {width} x {height}")
+        self._add_embeddings_to_model(pipeline)
 
         return pipeline, width, height, model_hash
 
@@ -563,25 +457,15 @@ class ModelManager(object):
 
         from . import load_pipeline_from_original_stable_diffusion_ckpt
 
-        try:
-            if self.list_models()[self.current_model]["status"] == "active":
-                self.offload_model(self.current_model)
-        except Exception as e:
-            pass
-
-        vae_path = None
-        if vae:
-            vae_path = (
-                vae
-                if os.path.isabs(vae)
-                else os.path.normpath(os.path.join(Globals.root, vae))
-            )
+        self.offload_model(self.current_model)
+        if vae_config := self._choose_diffusers_vae(model_name):
+            vae = self._load_vae(vae_config)
         if self._has_cuda():
             torch.cuda.empty_cache()
         pipeline = load_pipeline_from_original_stable_diffusion_ckpt(
             checkpoint_path=weights,
             original_config_file=config,
-            vae_path=vae_path,
+            vae=vae,
             return_generator_pipeline=True,
             precision=torch.float16 if self.precision == "float16" else torch.float32,
         )
@@ -589,6 +473,7 @@ class ModelManager(object):
             pipeline.enable_offload_submodels(self.device)
         else:
             pipeline.to(self.device)
+
         return (
             pipeline,
             width,
@@ -627,20 +512,18 @@ class ModelManager(object):
         print(f">> Offloading {model_name} to CPU")
         model = self.models[model_name]["model"]
         model.offload_all()
-        self.current_model = None
 
         gc.collect()
         if self._has_cuda():
             torch.cuda.empty_cache()
 
-    @classmethod
     def scan_model(self, model_name, checkpoint):
         """
         Apply picklescanner to the indicated checkpoint and issue a warning
         and option to exit if an infected file is identified.
         """
         # scan model
-        print(f"   | Scanning Model: {model_name}")
+        print(f">> Scanning Model: {model_name}")
         scan_result = scan_file_path(checkpoint)
         if scan_result.infected_files != 0:
             if scan_result.infected_files == 1:
@@ -663,7 +546,7 @@ class ModelManager(object):
                     print("### Exiting InvokeAI")
                     sys.exit()
         else:
-            print("   | Model scanned ok")
+            print(">> Model scanned ok")
 
     def import_diffuser_model(
         self,
@@ -685,7 +568,9 @@ class ModelManager(object):
         models.yaml file.
         """
         model_name = model_name or Path(repo_or_path).stem
-        model_description = description or f"Imported diffusers model {model_name}"
+        model_description = (
+            description or f"Imported diffusers model {model_name}"
+        )
         new_config = dict(
             description=model_description,
             vae=vae,
@@ -714,7 +599,7 @@ class ModelManager(object):
         SDLegacyType.V2_v   (V2 using 'v_prediction' prediction type)
         SDLegacyType.UNKNOWN
         """
-        global_step = checkpoint.get("global_step")
+        global_step = checkpoint.get('global_step')
         state_dict = checkpoint.get("state_dict") or checkpoint
 
         try:
@@ -740,15 +625,16 @@ class ModelManager(object):
             return SDLegacyType.UNKNOWN
 
     def heuristic_import(
-        self,
-        path_url_or_repo: str,
-        model_name: str = None,
-        description: str = None,
-        model_config_file: Path = None,
-        commit_to_conf: Path = None,
-        config_file_callback: Callable[[Path], Path] = None,
+            self,
+            path_url_or_repo: str,
+            convert: bool = True,
+            model_name: str = None,
+            description: str = None,
+            model_config_file: Path = None,
+            commit_to_conf: Path = None,
     ) -> str:
-        """Accept a string which could be:
+        """
+        Accept a string which could be:
            - a HF diffusers repo_id
            - a URL pointing to a legacy .ckpt or .safetensors file
            - a local path pointing to a legacy .ckpt or .safetensors file
@@ -762,20 +648,16 @@ class ModelManager(object):
         The model_name and/or description can be provided. If not, they will
         be generated automatically.
 
+        If convert is true, legacy models will be converted to diffusers
+        before importing.
+
         If commit_to_conf is provided, the newly loaded model will be written
         to the `models.yaml` file at the indicated path. Otherwise, the changes
         will only remain in memory.
 
-        The routine will do its best to figure out the config file
-        needed to convert legacy checkpoint file, but if it can't it
-        will call the config_file_callback routine, if provided. The
-        callback accepts a single argument, the Path to the checkpoint
-        file, and returns a Path to the config file to use.
-
-        The (potentially derived) name of the model is returned on
-        success, or None on failure. When multiple models are added
-        from a directory, only the last imported one is returned.
-
+        The (potentially derived) name of the model is returned on success, or None
+        on failure. When multiple models are added from a directory, only the last
+        imported one is returned.
         """
         model_path: Path = None
         thing = path_url_or_repo  # to save typing
@@ -783,7 +665,7 @@ class ModelManager(object):
         print(f">> Probing {thing} for import")
 
         if thing.startswith(("http:", "https:", "ftp:")):
-            print(f"   | {thing} appears to be a URL")
+            print(f"  | {thing} appears to be a URL")
             model_path = self._resolve_path(
                 thing, "models/ldm/stable-diffusion-v1"
             )  # _resolve_path does a download if needed
@@ -791,15 +673,15 @@ class ModelManager(object):
         elif Path(thing).is_file() and thing.endswith((".ckpt", ".safetensors")):
             if Path(thing).stem in ["model", "diffusion_pytorch_model"]:
                 print(
-                    f"   | {Path(thing).name} appears to be part of a diffusers model. Skipping import"
+                    f"  | {Path(thing).name} appears to be part of a diffusers model. Skipping import"
                 )
                 return
             else:
-                print(f"   | {thing} appears to be a checkpoint file on disk")
+                print(f"  | {thing} appears to be a checkpoint file on disk")
                 model_path = self._resolve_path(thing, "models/ldm/stable-diffusion-v1")
 
         elif Path(thing).is_dir() and Path(thing, "model_index.json").exists():
-            print(f"   | {thing} appears to be a diffusers file on disk")
+            print(f"  | {thing} appears to be a diffusers file on disk")
             model_name = self.import_diffuser_model(
                 thing,
                 vae=dict(repo_id="stabilityai/sd-vae-ft-mse"),
@@ -810,25 +692,25 @@ class ModelManager(object):
 
         elif Path(thing).is_dir():
             if (Path(thing) / "model_index.json").exists():
-                print(f"   | {thing} appears to be a diffusers model.")
+                print(f"  | {thing} appears to be a diffusers model.")
                 model_name = self.import_diffuser_model(
                     thing, commit_to_conf=commit_to_conf
                 )
             else:
                 print(
-                    f"   |{thing} appears to be a directory. Will scan for models to import"
+                    f"  |{thing} appears to be a directory. Will scan for models to import"
                 )
                 for m in list(Path(thing).rglob("*.ckpt")) + list(
                     Path(thing).rglob("*.safetensors")
                 ):
                     if model_name := self.heuristic_import(
-                        str(m), commit_to_conf=commit_to_conf
+                        str(m), convert, commit_to_conf=commit_to_conf
                     ):
                         print(f" >> {model_name} successfully imported")
                 return model_name
 
         elif re.match(r"^[\w.+-]+/[\w.+-]+$", thing):
-            print(f"   | {thing} appears to be a HuggingFace diffusers repo_id")
+            print(f"  | {thing} appears to be a HuggingFace diffusers repo_id")
             model_name = self.import_diffuser_model(
                 thing, commit_to_conf=commit_to_conf
             )
@@ -845,72 +727,55 @@ class ModelManager(object):
             return
 
         if model_path.stem in self.config:  # already imported
-            print("   | Already imported. Skipping")
+            print("  | Already imported. Skipping")
             return model_path.stem
 
         # another round of heuristics to guess the correct config file.
-        checkpoint = None
-        if model_path.suffix in [".ckpt", ".pt"]:
-            self.scan_model(model_path, model_path)
-            checkpoint = torch.load(model_path)
-        else:
-            checkpoint = safetensors.torch.load_file(model_path)
+        checkpoint = (
+            torch.load(model_path)
+            if model_path.suffix == ".ckpt"
+            else safetensors.torch.load_file(model_path)
+        )
 
         # additional probing needed if no config file provided
         if model_config_file is None:
-            # look for a like-named .yaml file in same directory
-            if model_path.with_suffix(".yaml").exists():
-                model_config_file = model_path.with_suffix(".yaml")
-                print(f"   | Using config file {model_config_file.name}")
-
+            model_type = self.probe_model_type(checkpoint)
+            if model_type == SDLegacyType.V1:
+                print("  | SD-v1 model detected")
+                model_config_file = Path(
+                    Globals.root, "configs/stable-diffusion/v1-inference.yaml"
+                )
+            elif model_type == SDLegacyType.V1_INPAINT:
+                print("  | SD-v1 inpainting model detected")
+                model_config_file = Path(
+                    Globals.root, "configs/stable-diffusion/v1-inpainting-inference.yaml"
+                )
+            elif model_type == SDLegacyType.V2_v:
+                print(
+                    "  | SD-v2-v model detected; model will be converted to diffusers format"
+                )
+                model_config_file = Path(
+                    Globals.root, "configs/stable-diffusion/v2-inference-v.yaml"
+                )
+                convert = True
+            elif model_type == SDLegacyType.V2_e:
+                print(
+                    "  | SD-v2-e model detected; model will be converted to diffusers format"
+                )
+                model_config_file = Path(
+                    Globals.root, "configs/stable-diffusion/v2-inference.yaml"
+                )
+                convert = True
+            elif model_type == SDLegacyType.V2:
+                print(
+                    f"** {thing} is a V2 checkpoint file, but its parameterization cannot be determined. Please provide configuration file path."
+                )
+                return
             else:
-                model_type = self.probe_model_type(checkpoint)
-                if model_type == SDLegacyType.V1:
-                    print("   | SD-v1 model detected")
-                    model_config_file = Path(
-                        Globals.root, "configs/stable-diffusion/v1-inference.yaml"
-                    )
-                elif model_type == SDLegacyType.V1_INPAINT:
-                    print("   | SD-v1 inpainting model detected")
-                    model_config_file = Path(
-                        Globals.root,
-                        "configs/stable-diffusion/v1-inpainting-inference.yaml",
-                    )
-                elif model_type == SDLegacyType.V2_v:
-                    print("   | SD-v2-v model detected")
-                    model_config_file = Path(
-                        Globals.root, "configs/stable-diffusion/v2-inference-v.yaml"
-                    )
-                elif model_type == SDLegacyType.V2_e:
-                    print("   | SD-v2-e model detected")
-                    model_config_file = Path(
-                        Globals.root, "configs/stable-diffusion/v2-inference.yaml"
-                    )
-                elif model_type == SDLegacyType.V2:
-                    print(
-                        f"** {thing} is a V2 checkpoint file, but its parameterization cannot be determined. Please provide configuration file path."
-                    )
-                    return
-                else:
-                    print(
-                        f"** {thing} is a legacy checkpoint file but not a known Stable Diffusion model. Please provide configuration file path."
-                    )
-                    return
-
-        if not model_config_file and config_file_callback:
-            model_config_file = config_file_callback(model_path)
-
-        # despite our best efforts, we could not find a model config file, so give up
-        if not model_config_file:
-            return
-
-        # look for a custom vae, a like-named file ending with .vae in the same directory
-        vae_path = None
-        for suffix in ["pt", "ckpt", "safetensors"]:
-            if (model_path.with_suffix(f".vae.{suffix}")).exists():
-                vae_path = model_path.with_suffix(f".vae.{suffix}")
-                print(f"   | Using VAE file {vae_path.name}")
-        vae = None if vae_path else dict(repo_id="stabilityai/sd-vae-ft-mse")
+                print(
+                    f"** {thing} is a legacy checkpoint file but not a known Stable Diffusion model. Please provide configuration file path."
+                )
+                return
 
         diffuser_path = Path(
             Globals.root, "models", Globals.converted_ckpts_dir, model_path.stem
@@ -918,13 +783,11 @@ class ModelManager(object):
         model_name = self.convert_and_import(
             model_path,
             diffusers_path=diffuser_path,
-            vae=vae,
-            vae_path=str(vae_path),
+            vae=dict(repo_id="stabilityai/sd-vae-ft-mse"),
             model_name=model_name,
             model_description=description,
             original_config_file=model_config_file,
             commit_to_conf=commit_to_conf,
-            scan_needed=False,
         )
         return model_name
 
@@ -934,11 +797,9 @@ class ModelManager(object):
         diffusers_path: Path,
         model_name=None,
         model_description=None,
-        vae: dict = None,
-        vae_path: Path = None,
+        vae=None,
         original_config_file: Path = None,
         commit_to_conf: Path = None,
-        scan_needed: bool = True,
     ) -> str:
         """
         Convert a legacy ckpt weights file to diffuser model and import
@@ -961,28 +822,23 @@ class ModelManager(object):
             return
 
         model_name = model_name or diffusers_path.name
-        model_description = model_description or f"Converted version of {model_name}"
-        print(f"   | Converting {model_name} to diffusers (30-60s)")
+        model_description = model_description or f"Optimized version of {model_name}"
+        print(f">> Optimizing {model_name} (30-60s)")
         try:
             # By passing the specified VAE to the conversion function, the autoencoder
             # will be built into the model rather than tacked on afterward via the config file
-            vae_model = None
-            if vae:
-                vae_model = self._load_vae(vae)
-                vae_path = None
+            vae_model = self._load_vae(vae) if vae else None
             convert_ckpt_to_diffusers(
                 ckpt_path,
                 diffusers_path,
                 extract_ema=True,
                 original_config_file=original_config_file,
                 vae=vae_model,
-                vae_path=vae_path,
-                scan_needed=scan_needed,
             )
             print(
-                f"   | Success. Converted model is now located at {str(diffusers_path)}"
+                f"  | Success. Optimized model is now located at {str(diffusers_path)}"
             )
-            print(f"   | Writing new config file entry for {model_name}")
+            print(f"  | Writing new config file entry for {model_name}")
             new_config = dict(
                 path=str(diffusers_path),
                 description=model_description,
@@ -993,7 +849,7 @@ class ModelManager(object):
             self.add_model(model_name, new_config, True)
             if commit_to_conf:
                 self.commit(commit_to_conf)
-            print("   | Conversion succeeded")
+            print(">> Conversion succeeded")
         except Exception as e:
             print(f"** Conversion failed: {str(e)}")
             print(
@@ -1023,6 +879,36 @@ class ModelManager(object):
 
         return search_folder, found_models
 
+    def _choose_diffusers_vae(
+        self, model_name: str, vae: str = None
+    ) -> Union[dict, str]:
+        # In the event that the original entry is using a custom ckpt VAE, we try to
+        # map that VAE onto a diffuser VAE using a hard-coded dictionary.
+        # I would prefer to do this differently: We load the ckpt model into memory, swap the
+        # VAE in memory, and then pass that to convert_ckpt_to_diffuser() so that the swapped
+        # VAE is built into the model. However, when I tried this I got obscure key errors.
+        if vae:
+            return vae
+        if model_name in self.config and (
+            vae_ckpt_path := self.model_info(model_name).get("vae", None)
+        ):
+            vae_basename = Path(vae_ckpt_path).stem
+            diffusers_vae = None
+            if diffusers_vae := VAE_TO_REPO_ID.get(vae_basename, None):
+                print(
+                    f">> {vae_basename} VAE corresponds to known {diffusers_vae} diffusers version"
+                )
+                vae = {"repo_id": diffusers_vae}
+            else:
+                print(
+                    f'** Custom VAE "{vae_basename}" found, but corresponding diffusers model unknown'
+                )
+                print(
+                    '** Using "stabilityai/sd-vae-ft-mse"; If this isn\'t right, please edit the model config'
+                )
+                vae = {"repo_id": "stabilityai/sd-vae-ft-mse"}
+        return vae
+
     def _make_cache_room(self) -> None:
         num_loaded_models = len(self.models)
         if num_loaded_models >= self.max_loaded_models:
@@ -1085,16 +971,16 @@ class ModelManager(object):
         legacy_locations = [
             Path(
                 models_dir,
-                "CompVis/stable-diffusion-safety-checker/models--CompVis--stable-diffusion-safety-checker",
+                "CompVis/stable-diffusion-safety-checker/models--CompVis--stable-diffusion-safety-checker"
             ),
             Path(models_dir, "bert-base-uncased/models--bert-base-uncased"),
             Path(
                 models_dir,
-                "openai/clip-vit-large-patch14/models--openai--clip-vit-large-patch14",
+                "openai/clip-vit-large-patch14/models--openai--clip-vit-large-patch14"
             ),
         ]
-        legacy_locations.extend(list(global_cache_dir("diffusers").glob("*")))
-
+        legacy_locations.extend(list(global_cache_dir("diffusers").glob('*')))
+        
         legacy_layout = False
         for model in legacy_locations:
             legacy_layout = legacy_layout or model.exists()
@@ -1112,7 +998,7 @@ class ModelManager(object):
 >> make adjustments, please press ctrl-C now to abort and relaunch InvokeAI when you are ready.
 >> Otherwise press <enter> to continue."""
         )
-        input("continue> ")
+        input('continue> ')
 
         # transformer files get moved into the hub directory
         if cls._is_huggingface_hub_directory_present():
@@ -1199,12 +1085,12 @@ class ModelManager(object):
             print(
                 f'>> Textual inversion triggers: {", ".join(sorted(model.textual_inversion_manager.get_all_trigger_strings()))}'
             )
-
+            
     def _has_cuda(self) -> bool:
         return self.device.type == "cuda"
 
     def _diffuser_sha256(
-        self, name_or_path: Union[str, Path], chunksize=16777216
+        self, name_or_path: Union[str, Path], chunksize=4096
     ) -> Union[str, bytes]:
         path = None
         if isinstance(name_or_path, Path):
@@ -1219,7 +1105,7 @@ class ModelManager(object):
             with open(hashpath) as f:
                 hash = f.read()
             return hash
-        print("   | Calculating sha256 hash of model files")
+        print("  | Calculating sha256 hash of model files")
         tic = time.time()
         sha = hashlib.sha256()
         count = 0
@@ -1231,7 +1117,7 @@ class ModelManager(object):
                         sha.update(chunk)
         hash = sha.hexdigest()
         toc = time.time()
-        print(f"   | sha256 = {hash} ({count} files hashed in", "%4.2fs)" % (toc - tic))
+        print(f"  | sha256 = {hash} ({count} files hashed in", "%4.2fs)" % (toc - tic))
         with open(hashpath, "w") as f:
             f.write(hash)
         return hash
@@ -1276,12 +1162,12 @@ class ModelManager(object):
             local_files_only=not Globals.internet_available,
         )
 
-        print(f"   | Loading diffusers VAE from {name_or_path}")
+        print(f"  | Loading diffusers VAE from {name_or_path}")
         if using_fp16:
             vae_args.update(torch_dtype=torch.float16)
             fp_args_list = [{"revision": "fp16"}, {}]
         else:
-            print("   | Using more accurate float32 precision")
+            print("  | Using more accurate float32 precision")
             fp_args_list = [{}]
 
         vae = None
@@ -1322,7 +1208,7 @@ class ModelManager(object):
                     hashes_to_delete.add(revision.commit_hash)
         strategy = cache_info.delete_revisions(*hashes_to_delete)
         print(
-            f"** Deletion of this model is expected to free {strategy.expected_freed_size_str}"
+            f"** deletion of this model is expected to free {strategy.expected_freed_size_str}"
         )
         strategy.execute()
 

invokeai/backend/stable_diffusion/concepts_lib.py

@@ -6,6 +6,7 @@ The interface is through the Concepts() object.
 """
 import os
 import re
+import traceback
 from typing import Callable
 from urllib import error as ul_error
 from urllib import request
@@ -14,6 +15,7 @@ from huggingface_hub import (
     HfApi,
     HfFolder,
     ModelFilter,
+    ModelSearchArguments,
     hf_hub_url,
 )
 
@@ -82,7 +84,7 @@ class HuggingFaceConceptsLibrary(object):
         """
         if not concept_name in self.list_concepts():
             print(
-                f"{concept_name} is not a local embedding trigger, nor is it a HuggingFace concept. Generation will continue without the concept."
+                f"This concept is not a local embedding trigger, nor is it a HuggingFace concept. Generation will continue without the concept."
             )
             return None
         return self.get_concept_file(concept_name.lower(), "learned_embeds.bin")
@@ -234,7 +236,7 @@ class HuggingFaceConceptsLibrary(object):
         except ul_error.HTTPError as e:
             if e.code == 404:
                 print(
-                    f"Concept {concept_name} is not known to the Hugging Face library. Generation will continue without the concept."
+                    f"This concept is not known to the Hugging Face library. Generation will continue without the concept."
                 )
             else:
                 print(
@@ -244,7 +246,7 @@ class HuggingFaceConceptsLibrary(object):
             return False
         except ul_error.URLError as e:
             print(
-                f"ERROR while downloading {concept_name}: {str(e)}. This may reflect a network issue. Generation will continue without the concept."
+                f"ERROR: {str(e)}. This may reflect a network issue. Generation will continue without the concept."
             )
             os.rmdir(dest)
             return False

invokeai/backend/stable_diffusion/textual_inversion_manager.py

@@ -1,26 +1,16 @@
+import os
 import traceback
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Optional, Union, List
+from typing import Optional, Union
 
-import safetensors.torch
 import torch
-
 from compel.embeddings_provider import BaseTextualInversionManager
 from picklescan.scanner import scan_file_path
 from transformers import CLIPTextModel, CLIPTokenizer
 
 from .concepts_lib import HuggingFaceConceptsLibrary
 
-@dataclass
-class EmbeddingInfo:
-    name: str
-    embedding: torch.Tensor
-    num_vectors_per_token: int
-    token_dim: int 
-    trained_steps: int = None
-    trained_model_name: str = None
-    trained_model_checksum: str = None
 
 @dataclass
 class TextualInversion:
@@ -82,46 +72,66 @@ class TextualInversionManager(BaseTextualInversionManager):
         if str(ckpt_path).endswith(".DS_Store"):
             return
 
-        embedding_list = self._parse_embedding(str(ckpt_path))
-        for embedding_info in embedding_list:
-            if (self.text_encoder.get_input_embeddings().weight.data[0].shape[0] != embedding_info.token_dim):
+        try:
+            scan_result = scan_file_path(str(ckpt_path))
+            if scan_result.infected_files == 1:
                 print(
-                    f"   ** Notice: {ckpt_path.parents[0].name}/{ckpt_path.name} was trained on a model with an incompatible token dimension: {self.text_encoder.get_input_embeddings().weight.data[0].shape[0]} vs {embedding_info.token_dim}."
+                    f"\n### Security Issues Found in Model: {scan_result.issues_count}"
                 )
-                continue
-
-            # Resolve the situation in which an earlier embedding has claimed the same
-            # trigger string. We replace the trigger with '<source_file>', as we used to.
-            trigger_str = embedding_info.name
-            sourcefile = (
-                f"{ckpt_path.parent.name}/{ckpt_path.name}"
-                if ckpt_path.name == "learned_embeds.bin"
-                else ckpt_path.name
+                print("### For your safety, InvokeAI will not load this embed.")
+                return
+        except Exception:
+            print(
+                f"### {ckpt_path.parents[0].name}/{ckpt_path.name} is damaged or corrupt."
             )
+            return
 
-            if trigger_str in self.trigger_to_sourcefile:
-                replacement_trigger_str = (
-                    f"<{ckpt_path.parent.name}>"
-                    if ckpt_path.name == "learned_embeds.bin"
-                    else f"<{ckpt_path.stem}>"
-                )
-                print(
-                    f">> {sourcefile}: Trigger token '{trigger_str}' is already claimed by '{self.trigger_to_sourcefile[trigger_str]}'. Trigger this concept with {replacement_trigger_str}"
-                )
-                trigger_str = replacement_trigger_str
+        embedding_info = self._parse_embedding(str(ckpt_path))
 
-            try:
-                self._add_textual_inversion(
-                    trigger_str,
-                    embedding_info.embedding,
-                    defer_injecting_tokens=defer_injecting_tokens,
-                )
-                # remember which source file claims this trigger
-                self.trigger_to_sourcefile[trigger_str] = sourcefile
+        if embedding_info is None:
+            # We've already put out an error message about the bad embedding in _parse_embedding, so just return.
+            return
+        elif (
+            self.text_encoder.get_input_embeddings().weight.data[0].shape[0]
+            != embedding_info["token_dim"]
+        ):
+            print(
+                f"** Notice: {ckpt_path.parents[0].name}/{ckpt_path.name} was trained on a model with an incompatible token dimension: {self.text_encoder.get_input_embeddings().weight.data[0].shape[0]} vs {embedding_info['token_dim']}."
+            )
+            return
 
-            except ValueError as e:
-                print(f'   | Ignoring incompatible embedding {embedding_info["name"]}')
-                print(f"   | The error was {str(e)}")
+        # Resolve the situation in which an earlier embedding has claimed the same
+        # trigger string. We replace the trigger with '<source_file>', as we used to.
+        trigger_str = embedding_info["name"]
+        sourcefile = (
+            f"{ckpt_path.parent.name}/{ckpt_path.name}"
+            if ckpt_path.name == "learned_embeds.bin"
+            else ckpt_path.name
+        )
+
+        if trigger_str in self.trigger_to_sourcefile:
+            replacement_trigger_str = (
+                f"<{ckpt_path.parent.name}>"
+                if ckpt_path.name == "learned_embeds.bin"
+                else f"<{ckpt_path.stem}>"
+            )
+            print(
+                f">> {sourcefile}: Trigger token '{trigger_str}' is already claimed by '{self.trigger_to_sourcefile[trigger_str]}'. Trigger this concept with {replacement_trigger_str}"
+            )
+            trigger_str = replacement_trigger_str
+
+        try:
+            self._add_textual_inversion(
+                trigger_str,
+                embedding_info["embedding"],
+                defer_injecting_tokens=defer_injecting_tokens,
+            )
+            # remember which source file claims this trigger
+            self.trigger_to_sourcefile[trigger_str] = sourcefile
+
+        except ValueError as e:
+            print(f'   | Ignoring incompatible embedding {embedding_info["name"]}')
+            print(f"   | The error was {str(e)}")
 
     def _add_textual_inversion(
         self, trigger_str, embedding, defer_injecting_tokens=False
@@ -299,130 +309,111 @@ class TextualInversionManager(BaseTextualInversionManager):
 
         return token_id
 
-
-    def _parse_embedding(self, embedding_file: str)->List[EmbeddingInfo]:
-        suffix = Path(embedding_file).suffix
-        try:
-            if suffix in [".pt",".ckpt",".bin"]:
-                scan_result = scan_file_path(embedding_file)
-                if scan_result.infected_files > 0:
-                    print(
-                        f"   ** Security Issues Found in Model: {scan_result.issues_count}"
-                    )
-                    print("   ** For your safety, InvokeAI will not load this embed.")
-                    return list()
-                ckpt = torch.load(embedding_file,map_location="cpu")
-            else:
-                ckpt = safetensors.torch.load_file(embedding_file)
-        except Exception as e:
-            print(f"   ** Notice: unrecognized embedding file format: {embedding_file}: {e}")
-            return list()
-        
-        # try to figure out what kind of embedding file it is and parse accordingly
-        keys = list(ckpt.keys())
-        if all(x in keys for x in ['string_to_token','string_to_param','name','step']):
-            return self._parse_embedding_v1(ckpt, embedding_file)     # example rem_rezero.pt
-        
-        elif all(x in keys for x in ['string_to_token','string_to_param']):
-            return self._parse_embedding_v2(ckpt, embedding_file)     # example midj-strong.pt
-        
-        elif 'emb_params' in keys:
-            return self._parse_embedding_v3(ckpt, embedding_file)     # example easynegative.safetensors
-        
+    def _parse_embedding(self, embedding_file: str):
+        file_type = embedding_file.split(".")[-1]
+        if file_type == "pt":
+            return self._parse_embedding_pt(embedding_file)
+        elif file_type == "bin":
+            return self._parse_embedding_bin(embedding_file)
         else:
-            return self._parse_embedding_v4(ckpt, embedding_file)     # usually a '.bin' file
+            print(f"** Notice: unrecognized embedding file format: {embedding_file}")
+            return None
 
-    def _parse_embedding_v1(self, embedding_ckpt: dict, file_path: str)->List[EmbeddingInfo]:
-        basename = Path(file_path).stem
-        print(f'   | Loading v1 embedding file: {basename}')
+    def _parse_embedding_pt(self, embedding_file):
+        embedding_ckpt = torch.load(embedding_file, map_location="cpu")
+        embedding_info = {}
 
-        embeddings = list()
-        token_counter = -1
-        for token,embedding in embedding_ckpt["string_to_param"].items():
-            if token_counter < 0:
-                trigger = embedding_ckpt["name"]
-            elif token_counter == 0:
-                trigger = f'<basename>'
-            else:
-                trigger = f'<{basename}-{int(token_counter:=token_counter)}>'
-            token_counter += 1
-            embedding_info = EmbeddingInfo(
-                name = trigger,
-                embedding = embedding,
-                num_vectors_per_token = embedding.size()[0],
-                token_dim = embedding.size()[1],
-                trained_steps = embedding_ckpt["step"],
-                trained_model_name = embedding_ckpt["sd_checkpoint_name"],
-                trained_model_checksum = embedding_ckpt["sd_checkpoint"]
-            )
-            embeddings.append(embedding_info)
-        return embeddings
+        # Check if valid embedding file
+        if "string_to_token" and "string_to_param" in embedding_ckpt:
+            # Catch variants that do not have the expected keys or values.
+            try:
+                embedding_info["name"] = embedding_ckpt["name"] or os.path.basename(
+                    os.path.splitext(embedding_file)[0]
+                )
 
-    def _parse_embedding_v2 (
-        self, embedding_ckpt: dict, file_path: str
-    ) -> List[EmbeddingInfo]:
+                # Check num of embeddings and warn user only the first will be used
+                embedding_info["num_of_embeddings"] = len(
+                    embedding_ckpt["string_to_token"]
+                )
+                if embedding_info["num_of_embeddings"] > 1:
+                    print(">> More than 1 embedding found. Will use the first one")
+
+                embedding = list(embedding_ckpt["string_to_param"].values())[0]
+            except (AttributeError, KeyError):
+                return self._handle_broken_pt_variants(embedding_ckpt, embedding_file)
+
+            embedding_info["embedding"] = embedding
+            embedding_info["num_vectors_per_token"] = embedding.size()[0]
+            embedding_info["token_dim"] = embedding.size()[1]
+
+            try:
+                embedding_info["trained_steps"] = embedding_ckpt["step"]
+                embedding_info["trained_model_name"] = embedding_ckpt[
+                    "sd_checkpoint_name"
+                ]
+                embedding_info["trained_model_checksum"] = embedding_ckpt[
+                    "sd_checkpoint"
+                ]
+            except AttributeError:
+                print(">> No Training Details Found. Passing ...")
+
+        # .pt files found at https://cyberes.github.io/stable-diffusion-textual-inversion-models/
+        # They are actually .bin files
+        elif len(embedding_ckpt.keys()) == 1:
+            embedding_info = self._parse_embedding_bin(embedding_file)
+
+        else:
+            print(">> Invalid embedding format")
+            embedding_info = None
+
+        return embedding_info
+
+    def _parse_embedding_bin(self, embedding_file):
+        embedding_ckpt = torch.load(embedding_file, map_location="cpu")
+        embedding_info = {}
+
+        if list(embedding_ckpt.keys()) == 0:
+            print(">> Invalid concepts file")
+            embedding_info = None
+        else:
+            for token in list(embedding_ckpt.keys()):
+                embedding_info["name"] = (
+                    token
+                    or f"<{os.path.basename(os.path.splitext(embedding_file)[0])}>"
+                )
+                embedding_info["embedding"] = embedding_ckpt[token]
+                embedding_info[
+                    "num_vectors_per_token"
+                ] = 1  # All Concepts seem to default to 1
+                embedding_info["token_dim"] = embedding_info["embedding"].size()[0]
+
+        return embedding_info
+
+    def _handle_broken_pt_variants(
+        self, embedding_ckpt: dict, embedding_file: str
+    ) -> dict:
         """
-        This handles embedding .pt file variant #2.
+        This handles the broken .pt file variants. We only know of one at present.
         """
-        basename = Path(file_path).stem
-        print(f'   | Loading v2 embedding file: {basename}')
-        embeddings = list()
-        
+        embedding_info = {}
         if isinstance(
             list(embedding_ckpt["string_to_token"].values())[0], torch.Tensor
         ):
-            token_counter = 0
-            for token,embedding in embedding_ckpt["string_to_param"].items():
-                trigger = token if token != '*' \
-                    else f'<{basename}>' if token_counter == 0 \
-                         else f'<{basename}-{int(token_counter:=token_counter+1)}>'
-                embedding_info = EmbeddingInfo(
-                    name = trigger,
-                    embedding = embedding,
-                    num_vectors_per_token = embedding.size()[0],
-                    token_dim = embedding.size()[1],
+            for token in list(embedding_ckpt["string_to_token"].keys()):
+                embedding_info["name"] = (
+                    token
+                    if token != "*"
+                    else f"<{os.path.basename(os.path.splitext(embedding_file)[0])}>"
                 )
-                embeddings.append(embedding_info)
+                embedding_info["embedding"] = embedding_ckpt[
+                    "string_to_param"
+                ].state_dict()[token]
+                embedding_info["num_vectors_per_token"] = embedding_info[
+                    "embedding"
+                ].shape[0]
+                embedding_info["token_dim"] = embedding_info["embedding"].size()[1]
         else:
-            print(f"   ** {basename}: Unrecognized embedding format")
+            print(">> Invalid embedding format")
+            embedding_info = None
 
-        return embeddings
-
-    def _parse_embedding_v3(self, embedding_ckpt: dict, file_path: str)->List[EmbeddingInfo]:
-        """
-        Parse 'version 3' of the .pt textual inversion embedding files.
-        """
-        basename = Path(file_path).stem
-        print(f'   | Loading v3 embedding file: {basename}')
-        embedding = embedding_ckpt['emb_params']
-        embedding_info = EmbeddingInfo(
-            name = f'<{basename}>',
-            embedding = embedding,
-            num_vectors_per_token = embedding.size()[0],
-            token_dim = embedding.size()[1],
-        )
-        return [embedding_info]
-    
-    def _parse_embedding_v4(self, embedding_ckpt: dict, filepath: str)->List[EmbeddingInfo]:
-        """
-        Parse 'version 4' of the textual inversion embedding files. This one
-        is usually associated with .bin files trained by HuggingFace diffusers.
-        """
-        basename = Path(filepath).stem
-        short_path = Path(filepath).parents[0].name+'/'+Path(filepath).name
-        
-        print(f'   | Loading v4 embedding file: {short_path}')
-        
-        embeddings = list()
-        if list(embedding_ckpt.keys()) == 0:
-            print(f"   ** Invalid embeddings file: {short_path}")
-        else:
-            for token,embedding in embedding_ckpt.items():
-                embedding_info = EmbeddingInfo(
-                    name = token or f"<{basename}>",
-                    embedding = embedding,
-                    num_vectors_per_token = 1,  # All Concepts seem to default to 1
-                    token_dim = embedding.size()[0],
-                )
-                embeddings.append(embedding_info)
-        return embeddings
+        return embedding_info

invokeai/backend/web/invoke_ai_web_server.py

@@ -1022,7 +1022,7 @@ class InvokeAIWebServer:
                     "RGB"
                 )
 
-            def image_progress(intermediate_state: PipelineIntermediateState):
+            def image_progress(sample, step):
                 if self.canceled.is_set():
                     raise CanceledException
 
@@ -1030,14 +1030,6 @@ class InvokeAIWebServer:
                 nonlocal generation_parameters
                 nonlocal progress
 
-                step = intermediate_state.step
-                if intermediate_state.predicted_original is not None:
-                    # Some schedulers report not only the noisy latents at the current timestep,
-                    # but also their estimate so far of what the de-noised latents will be.
-                    sample = intermediate_state.predicted_original
-                else:
-                    sample = intermediate_state.latents
-
                 generation_messages = {
                     "txt2img": "common.statusGeneratingTextToImage",
                     "img2img": "common.statusGeneratingImageToImage",
@@ -1310,9 +1302,16 @@ class InvokeAIWebServer:
 
                 progress.set_current_iteration(progress.current_iteration + 1)
 
+            def diffusers_step_callback_adapter(*cb_args, **kwargs):
+                if isinstance(cb_args[0], PipelineIntermediateState):
+                    progress_state: PipelineIntermediateState = cb_args[0]
+                    return image_progress(progress_state.latents, progress_state.step)
+                else:
+                    return image_progress(*cb_args, **kwargs)
+
             self.generate.prompt2image(
                 **generation_parameters,
-                step_callback=image_progress,
+                step_callback=diffusers_step_callback_adapter,
                 image_callback=image_done,
             )
 

invokeai/frontend/CLI/CLI.py

@@ -158,9 +158,14 @@ def main():
         report_model_error(opt, e)
 
     # try to autoconvert new models
+    if path := opt.autoimport:
+        gen.model_manager.heuristic_import(
+            str(path), convert=False, commit_to_conf=opt.conf
+        )
+
     if path := opt.autoconvert:
         gen.model_manager.heuristic_import(
-            str(path), commit_to_conf=opt.conf
+            str(path), convert=True, commit_to_conf=opt.conf
         )
 
     # web server loops forever
@@ -576,7 +581,6 @@ def do_command(command: str, gen, opt: Args, completer) -> tuple:
 
     elif command.startswith("!replay"):
         file_path = command.replace("!replay", "", 1).strip()
-        file_path = os.path.join(opt.outdir, file_path)
         if infile is None and os.path.isfile(file_path):
             infile = open(file_path, "r", encoding="utf-8")
         completer.add_history(command)
@@ -622,7 +626,7 @@ def set_default_output_dir(opt: Args, completer: Completer):
     completer.set_default_dir(opt.outdir)
 
 
-def import_model(model_path: str, gen, opt, completer):
+def import_model(model_path: str, gen, opt, completer, convert=False):
     """
     model_path can be (1) a URL to a .ckpt file; (2) a local .ckpt file path;
     (3) a huggingface repository id; or (4) a local directory containing a
@@ -653,6 +657,7 @@ def import_model(model_path: str, gen, opt, completer):
         model_path,
         model_name=model_name,
         description=model_desc,
+        convert=convert,
     )
 
     if not imported_name:
@@ -661,6 +666,7 @@ def import_model(model_path: str, gen, opt, completer):
                 model_path,
                 model_name=model_name,
                 description=model_desc,
+                convert=convert,
                 model_config_file=config_file,
             )
     if not imported_name:
@@ -751,6 +757,7 @@ def _get_model_name_and_desc(
     )
     return model_name, model_description
 
+
 def convert_model(model_name_or_path: Union[Path, str], gen, opt, completer):
     model_name_or_path = model_name_or_path.replace("\\", "/")  # windows
     manager = gen.model_manager
@@ -765,10 +772,16 @@ def convert_model(model_name_or_path: Union[Path, str], gen, opt, completer):
             original_config_file = Path(model_info["config"])
             model_name = model_name_or_path
             model_description = model_info["description"]
-            vae_path = model_info.get("vae")
+            vae = model_info["vae"]
         else:
             print(f"** {model_name_or_path} is not a legacy .ckpt weights file")
             return
+        if vae_repo := invokeai.backend.model_management.model_manager.VAE_TO_REPO_ID.get(
+            Path(vae).stem
+        ):
+            vae_repo = dict(repo_id=vae_repo)
+        else:
+            vae_repo = None
         model_name = manager.convert_and_import(
             ckpt_path,
             diffusers_path=Path(
@@ -777,11 +790,11 @@ def convert_model(model_name_or_path: Union[Path, str], gen, opt, completer):
             model_name=model_name,
             model_description=model_description,
             original_config_file=original_config_file,
-            vae_path=vae_path,
+            vae=vae_repo,
         )
     else:
         try:
-            import_model(model_name_or_path, gen, opt, completer)
+            import_model(model_name_or_path, gen, opt, completer, convert=True)
         except KeyboardInterrupt:
             return
 

invokeai/frontend/install/model_install.py

@@ -199,6 +199,17 @@ class addModelsForm(npyscreen.FormMultiPage):
             relx=4,
             scroll_exit=True,
         )
+        self.nextrely += 1
+        self.convert_models = self.add_widget_intelligent(
+            npyscreen.TitleSelectOne,
+            name="== CONVERT IMPORTED MODELS INTO DIFFUSERS==",
+            values=["Keep original format", "Convert to diffusers"],
+            value=0,
+            begin_entry_at=4,
+            max_height=4,
+            hidden=True,  # will appear when imported models box is edited
+            scroll_exit=True,
+        )
         self.cancel = self.add_widget_intelligent(
             npyscreen.ButtonPress,
             name="CANCEL",
@@ -233,6 +244,8 @@ class addModelsForm(npyscreen.FormMultiPage):
             self.show_directory_fields.addVisibleWhenSelected(i)
 
         self.show_directory_fields.when_value_edited = self._clear_scan_directory
+        self.import_model_paths.when_value_edited = self._show_hide_convert
+        self.autoload_directory.when_value_edited = self._show_hide_convert
 
     def resize(self):
         super().resize()
@@ -243,6 +256,13 @@ class addModelsForm(npyscreen.FormMultiPage):
         if not self.show_directory_fields.value:
             self.autoload_directory.value = ""
 
+    def _show_hide_convert(self):
+        model_paths = self.import_model_paths.value or ""
+        autoload_directory = self.autoload_directory.value or ""
+        self.convert_models.hidden = (
+            len(model_paths) == 0 and len(autoload_directory) == 0
+        )
+
     def _get_starter_model_labels(self) -> List[str]:
         window_width, window_height = get_terminal_size()
         label_width = 25
@@ -302,6 +322,7 @@ class addModelsForm(npyscreen.FormMultiPage):
         .scan_directory: Path to a directory of models to scan and import
         .autoscan_on_startup:  True if invokeai should scan and import at startup time
         .import_model_paths:   list of URLs, repo_ids and file paths to import
+        .convert_to_diffusers: if True, convert legacy checkpoints into diffusers
         """
         # we're using a global here rather than storing the result in the parentapp
         # due to some bug in npyscreen that is causing attributes to be lost
@@ -338,6 +359,7 @@ class addModelsForm(npyscreen.FormMultiPage):
 
         # URLs and the like
         selections.import_model_paths = self.import_model_paths.value.split()
+        selections.convert_to_diffusers = self.convert_models.value[0] == 1
 
 
 class AddModelApplication(npyscreen.NPSAppManaged):
@@ -350,6 +372,7 @@ class AddModelApplication(npyscreen.NPSAppManaged):
             scan_directory=None,
             autoscan_on_startup=None,
             import_model_paths=None,
+            convert_to_diffusers=None,
         )
 
     def onStart(self):
@@ -370,6 +393,7 @@ def process_and_execute(opt: Namespace, selections: Namespace):
     directory_to_scan = selections.scan_directory
     scan_at_startup = selections.autoscan_on_startup
     potential_models_to_install = selections.import_model_paths
+    convert_to_diffusers = selections.convert_to_diffusers
 
     install_requested_models(
         install_initial_models=models_to_install,
@@ -377,6 +401,7 @@ def process_and_execute(opt: Namespace, selections: Namespace):
         scan_directory=Path(directory_to_scan) if directory_to_scan else None,
         external_models=potential_models_to_install,
         scan_at_startup=scan_at_startup,
+        convert_to_diffusers=convert_to_diffusers,
         precision="float32"
         if opt.full_precision
         else choose_precision(torch.device(choose_torch_device())),

invokeai/frontend/web/.eslintignore

@@ -6,5 +6,3 @@ stats.html
 index.html
 .yarn/
 *.scss
-src/services/api/
-src/services/fixtures/*

invokeai/frontend/web/.prettierignore

@@ -3,8 +3,4 @@ dist/
 node_modules/
 patches/
 stats.html
-index.html
 .yarn/
-*.scss
-src/services/api/
-src/services/fixtures/*

invokeai/frontend/web/README.md

@@ -1,16 +1,10 @@
 # InvokeAI Web UI
 
-- [InvokeAI Web UI](#invokeai-web-ui)
-  - [Stack](#stack)
-  - [Contributing](#contributing)
-    - [Dev Environment](#dev-environment)
-    - [Production builds](#production-builds)
-
 The UI is a fairly straightforward Typescript React app. The only really fancy stuff is the Unified Canvas.
 
 Code in `invokeai/frontend/web/` if you want to have a look.
 
-## Stack
+## Details
 
 State management is Redux via [Redux Toolkit](https://github.com/reduxjs/redux-toolkit). Communication with server is a mix of HTTP and [socket.io](https://github.com/socketio/socket.io-client) (with a custom redux middleware to help).
 
@@ -38,7 +32,7 @@ Start everything in dev mode:
 
 1. Start the dev server: `yarn dev`
 2. Start the InvokeAI UI per usual: `invokeai --web`
-3. Point your browser to the dev server address e.g. <http://localhost:5173/>
+3. Point your browser to the dev server address e.g. `http://localhost:5173/`
 
 ### Production builds
 

invokeai/frontend/web/dist/assets/ThemeLocaleProvider-51f66919.js

@@ -1,4 +1,4 @@
-import{j as y,cN as Ie,r as _,cO as bt,q as Lr,cP as o,cQ as b,cR as v,cS as S,cT as Vr,cU as ut,cV as vt,cM as ft,cW as mt,n as gt,cX as ht,E as pt}from"./index-f7f41e1f.js";import{d as yt,i as St,T as xt,j as $t,h as kt}from"./storeHooks-eaf47ae3.js";var Or=`
+import{j as y,cN as Ie,r as _,cO as bt,q as Lr,cP as o,cQ as b,cR as v,cS as S,cT as Vr,cU as ut,cV as vt,cM as ft,cW as mt,n as gt,cX as ht,E as pt}from"./index-d64f4654.js";import{d as yt,i as St,T as xt,j as $t,h as kt}from"./storeHooks-0eed8e9f.js";var Or=`
   :root {
     --chakra-vh: 100vh;
   }

invokeai/frontend/web/dist/index.html

@@ -12,7 +12,7 @@
         margin: 0;
       }
     </style>
-    <script type="module" crossorigin src="./assets/index-f7f41e1f.js"></script>
+    <script type="module" crossorigin src="./assets/index-d64f4654.js"></script>
     <link rel="stylesheet" href="./assets/index-5483945c.css">
   </head>
 

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

@@ -64,8 +64,6 @@
         "trainingDesc2": "InvokeAI already supports training custom embeddings using Textual Inversion using the main script.",
         "upload": "Upload",
         "close": "Close",
-        "cancel": "Cancel",
-        "accept": "Accept",
         "load": "Load",
         "back": "Back",
         "statusConnected": "Connected",
@@ -335,7 +333,6 @@
         "addNewModel": "Add New Model",
         "addCheckpointModel": "Add Checkpoint / Safetensor Model",
         "addDiffuserModel": "Add Diffusers",
-        "scanForModels": "Scan For Models",
         "addManually": "Add Manually",
         "manual": "Manual",
         "name": "Name",

invokeai/frontend/web/docs/API_CLIENT.md

@@ -1,87 +0,0 @@
-# Generated axios API client
-
-- [Generated axios API client](#generated-axios-api-client)
-  - [Generation](#generation)
-    - [Generate the API client from the nodes web server](#generate-the-api-client-from-the-nodes-web-server)
-    - [Generate the API client from JSON](#generate-the-api-client-from-json)
-      - [Getting the JSON from the nodes web server](#getting-the-json-from-the-nodes-web-server)
-      - [Getting the JSON with a python script](#getting-the-json-with-a-python-script)
-      - [Generate the API client](#generate-the-api-client)
-  - [The generated client](#the-generated-client)
-  - [API client customisation](#api-client-customisation)
-
-This API client is generated by an [openapi code generator](https://github.com/ferdikoomen/openapi-typescript-codegen).
-
-All files in `invokeai/frontend/web/src/services/api/` are made by the generator.
-
-## Generation
-
-The axios client may be generated by from the OpenAPI schema from the nodes web server, or from JSON.
-
-### Generate the API client from the nodes web server
-
-We need to start the nodes web server, which serves the OpenAPI schema to the generator.
-
-1. Start the nodes web server.
-
-```bash
-# from the repo root
-python scripts/invoke-new.py --web
-```
-
-2. Generate the API client.
-
-```bash
-# from invokeai/frontend/web/
-yarn api:web
-```
-
-### Generate the API client from JSON
-
-The JSON can be acquired from the nodes web server, or with a python script.
-
-#### Getting the JSON from the nodes web server
-
-Start the nodes web server as described above, then download the file.
-
-```bash
-# from invokeai/frontend/web/
-curl http://localhost:9090/openapi.json -o openapi.json
-```
-
-#### Getting the JSON with a python script
-
-Run this python script from the repo root, so it can access the nodes server modules.
-
-The script will output `openapi.json` in the repo root. Then we need to move it to `invokeai/frontend/web/`.
-
-```bash
-# from the repo root
-python invokeai/app/util/generate_openapi_json.py
-mv invokeai/app/util/openapi.json invokeai/frontend/web/services/fixtures/
-```
-
-#### Generate the API client
-
-Now we can generate the API client from the JSON.
-
-```bash
-# from invokeai/frontend/web/
-yarn api:file
-```
-
-## The generated client
-
-The client will be written to `invokeai/frontend/web/services/api/`:
-
-- `axios` client
-- TS types
-- An easily parseable schema, which we can use to generate UI
-
-## API client customisation
-
-The generator has a default `request.ts` file that implements a base `axios` client. The generated client uses this base client.
-
-One shortcoming of this is base client is it does not provide response headers unless the response body is empty. To fix this, we provide our own lightly-patched `request.ts`.
-
-To access the headers, call `getHeaders(response)` on any response from the generated api client. This function is exported from `invokeai/frontend/web/src/services/util/getHeaders.ts`.

invokeai/frontend/web/docs/EVENTS.md

@@ -1,21 +0,0 @@
-# Events
-
-Events via `socket.io`
-
-## `actions.ts`
-
-Redux actions for all socket events. Payloads all include a timestamp, and optionally some other data.
-
-Any reducer (or middleware) can respond to the actions.
-
-## `middleware.ts`
-
-Redux middleware for events.
-
-Handles dispatching the event actions. Only put logic here if it can't really go anywhere else.
-
-For example, on connect we want to load images to the gallery if it's not populated. This requires dispatching a thunk, so we need to directly dispatch this in the middleware.
-
-## `types.ts`
-
-Hand-written types for the socket events. Cannot generate these from the server, but fortunately they are few and simple.

invokeai/frontend/web/docs/NODE_EDITOR.md

@@ -1,17 +0,0 @@
-# Node Editor Design
-
-WIP
-
-nodes
-
-everything in `src/features/nodes/`
-
-have a look at `state.nodes.invocation`
-
-- on socket connect, if no schema saved, fetch `localhost:9090/openapi.json`, save JSON to `state.nodes.schema`
-- on fulfilled schema fetch, `parseSchema()` the schema. this outputs a `Record<string, Invocation>` which is saved to `state.nodes.invocations` - `Invocation` is like a template for the node
-- when you add a node, the the `Invocation` template is passed to `InvocationComponent.tsx` to build the UI component for that node
-- inputs/outputs have field types - and each field type gets an `FieldComponent` which includes a dispatcher to write state changes to redux `nodesSlice`
-- `reactflow` sends changes to nodes/edges to redux
-- to invoke, `buildNodesGraph()` state, then send this
-- changed onClick Invoke button actions to build the schema, then when schema builds it dispatches the actual network request to create the session - see `session.ts`

invokeai/frontend/web/docs/PACKAGE_SCRIPTS.md

@@ -1,29 +0,0 @@
-# Package Scripts
-
-WIP walkthrough of `package.json` scripts.
-
-## `theme` & `theme:watch`
-
-These run the Chakra CLI to generate types for the theme, or watch for code change and re-generate the types.
-
-The CLI essentially monkeypatches Chakra's files in `node_modules`.
-
-## `postinstall`
-
-The `postinstall` script patches a few packages and runs the Chakra CLI to generate types for the theme.
-
-### Patch `@chakra-ui/cli`
-
-See: <https://github.com/chakra-ui/chakra-ui/issues/7394>
-
-### Patch `redux-persist`
-
-We want to persist the canvas state to `localStorage` but many canvas operations change data very quickly, so we need to debounce the writes to `localStorage`.
-
-`redux-persist` is unfortunately unmaintained. The repo's current code is nonfunctional, but the last release's code depends on a package that was removed from `npm` for being malware, so we cannot just fork it.
-
-So, we have to patch it directly. Perhaps a better way would be to write a debounced storage adapter, but I couldn't figure out how to do that.
-
-### Patch `redux-deep-persist`
-
-This package makes blacklisting and whitelisting persist configs very simple, but we have to patch it to match `redux-persist` for the types to work.

invokeai/frontend/web/index.d.ts

@@ -1,7 +1,4 @@
 import React, { PropsWithChildren } from 'react';
-import { IAIPopoverProps } from '../web/src/common/components/IAIPopover';
-import { IAIIconButtonProps } from '../web/src/common/components/IAIIconButton';
-import { InvokeTabName } from 'features/ui/store/tabMap';
 
 export {};
 
@@ -53,44 +50,9 @@ declare module '@invoke-ai/invoke-ai-ui' {
   declare class InvokeAiLogoComponent extends React.Component<InvokeAILogoComponentProps> {
     public constructor(props: InvokeAILogoComponentProps);
   }
-
-  declare class IAIPopover extends React.Component<IAIPopoverProps> {
-    public constructor(props: IAIPopoverProps);
-  }
-
-  declare class IAIIconButton extends React.Component<IAIIconButtonProps> {
-    public constructor(props: IAIIconButtonProps);
-  }
-
-  declare class SettingsModal extends React.Component<SettingsModalProps> {
-    public constructor(props: SettingsModalProps);
-  }
-
-  declare class StatusIndicator extends React.Component<StatusIndicatorProps> {
-    public constructor(props: StatusIndicatorProps);
-  }
-
-  declare class ModelSelect extends React.Component<ModelSelectProps> {
-    public constructor(props: ModelSelectProps);
-  }
 }
 
-interface InvokeProps extends PropsWithChildren {
-  apiUrl?: string;
-  disabledPanels?: string[];
-  disabledTabs?: InvokeTabName[];
-  token?: string;
-}
+declare function Invoke(props: PropsWithChildren): JSX.Element;
 
-declare function Invoke(props: InvokeProps): JSX.Element;
-
-export {
-  ThemeChanger,
-  InvokeAiLogoComponent,
-  IAIPopover,
-  IAIIconButton,
-  SettingsModal,
-  StatusIndicator,
-  ModelSelect,
-};
+export { ThemeChanger, InvokeAiLogoComponent };
 export = Invoke;

invokeai/frontend/web/package.json

@@ -5,10 +5,8 @@
   "scripts": {
     "prepare": "cd ../../../ && husky install invokeai/frontend/web/.husky",
     "dev": "concurrently \"vite dev\" \"yarn run theme:watch\"",
-    "dev:nodes": "concurrently \"vite dev --mode nodes\" \"yarn run theme:watch\"",
     "build": "yarn run lint && vite build",
-    "api:web": "openapi -i http://localhost:9090/openapi.json -o src/services/api --client axios --useOptions --useUnionTypes --exportSchemas true --indent 2 --request src/services/fixtures/request.ts",
-    "api:file": "openapi -i src/services/fixtures/openapi.json -o src/services/api --client axios --useOptions --useUnionTypes --exportSchemas true --indent 2 --request src/services/fixtures/request.ts",
+    "build:package": "vite build --mode=package",
     "preview": "vite preview",
     "lint:madge": "madge --circular src/main.tsx",
     "lint:eslint": "eslint --max-warnings=0 .",
@@ -44,10 +42,9 @@
     "@chakra-ui/react": "^2.5.1",
     "@chakra-ui/styled-system": "^2.6.1",
     "@chakra-ui/theme-tools": "^2.0.16",
-    "@dagrejs/graphlib": "^2.1.12",
     "@emotion/react": "^11.10.6",
     "@emotion/styled": "^11.10.6",
-    "@reduxjs/toolkit": "^1.9.3",
+    "@reduxjs/toolkit": "^1.9.2",
     "chakra-ui-contextmenu": "^1.0.5",
     "dateformat": "^5.0.3",
     "formik": "^2.2.9",
@@ -71,9 +68,7 @@
     "react-redux": "^8.0.5",
     "react-transition-group": "^4.4.5",
     "react-zoom-pan-pinch": "^2.6.1",
-    "reactflow": "^11.7.0",
     "redux-deep-persist": "^1.0.7",
-    "redux-dynamic-middlewares": "^2.2.0",
     "redux-persist": "^6.0.0",
     "socket.io-client": "^4.6.0",
     "use-image": "^1.1.0",
@@ -89,7 +84,6 @@
     "@typescript-eslint/eslint-plugin": "^5.52.0",
     "@typescript-eslint/parser": "^5.52.0",
     "@vitejs/plugin-react-swc": "^3.2.0",
-    "axios": "^1.3.4",
     "babel-plugin-transform-imports": "^2.0.0",
     "concurrently": "^7.6.0",
     "eslint": "^8.34.0",
@@ -97,17 +91,13 @@
     "eslint-plugin-prettier": "^4.2.1",
     "eslint-plugin-react": "^7.32.2",
     "eslint-plugin-react-hooks": "^4.6.0",
-    "form-data": "^4.0.0",
     "husky": "^8.0.3",
     "lint-staged": "^13.1.2",
     "madge": "^6.0.0",
-    "openapi-types": "^12.1.0",
-    "openapi-typescript-codegen": "^0.23.0",
     "postinstall-postinstall": "^2.1.0",
     "prettier": "^2.8.4",
     "rollup-plugin-visualizer": "^5.9.0",
     "terser": "^5.16.4",
-    "typescript": "4.9.5",
     "vite": "^4.1.2",
     "vite-plugin-eslint": "^1.8.1",
     "vite-tsconfig-paths": "^4.0.5",

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

@@ -8,6 +8,7 @@
         "darkTheme": "داكن",
         "lightTheme": "فاتح",
         "greenTheme": "أخضر",
+        "text2img": "نص إلى صورة",
         "img2img": "صورة إلى صورة",
         "unifiedCanvas": "لوحة موحدة",
         "nodes": "عقد",

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

@@ -7,6 +7,7 @@
         "darkTheme": "Dunkel",
         "lightTheme": "Hell",
         "greenTheme": "Grün",
+        "text2img": "Text zu Bild",
         "img2img": "Bild zu Bild",
         "nodes": "Knoten",
         "langGerman": "Deutsch",

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

@@ -64,8 +64,6 @@
         "trainingDesc2": "InvokeAI already supports training custom embeddings using Textual Inversion using the main script.",
         "upload": "Upload",
         "close": "Close",
-        "cancel": "Cancel",
-        "accept": "Accept",
         "load": "Load",
         "back": "Back",
         "statusConnected": "Connected",
@@ -335,7 +333,6 @@
         "addNewModel": "Add New Model",
         "addCheckpointModel": "Add Checkpoint / Safetensor Model",
         "addDiffuserModel": "Add Diffusers",
-        "scanForModels": "Scan For Models",
         "addManually": "Add Manually",
         "manual": "Manual",
         "name": "Name",
@@ -522,10 +519,6 @@
         "resetComplete": "Web UI has been reset. Refresh the page to reload."
     },
     "toast": {
-        "serverError": "Server Error",
-        "disconnected": "Disconnected from Server",
-        "connected": "Connected to Server",
-        "canceled": "Processing Canceled",
         "tempFoldersEmptied": "Temp Folder Emptied",
         "uploadFailed": "Upload failed",
         "uploadFailedMultipleImagesDesc": "Multiple images pasted, may only upload one image at a time",

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

@@ -8,6 +8,7 @@
         "darkTheme": "Oscuro",
         "lightTheme": "Claro",
         "greenTheme": "Verde",
+        "text2img": "Texto a Imagen",
         "img2img": "Imagen a Imagen",
         "unifiedCanvas": "Lienzo Unificado",
         "nodes": "Nodos",
@@ -69,11 +70,7 @@
         "langHebrew": "Hebreo",
         "pinOptionsPanel": "Pin del panel de opciones",
         "loading": "Cargando",
-        "loadingInvokeAI": "Cargando invocar a la IA",
-        "postprocessing": "Tratamiento posterior",
-        "txt2img": "De texto a imagen",
-        "accept": "Aceptar",
-        "cancel": "Cancelar"
+        "loadingInvokeAI": "Cargando invocar a la IA"
     },
     "gallery": {
         "generations": "Generaciones",
@@ -407,8 +404,7 @@
         "none": "ninguno",
         "pickModelType": "Elige el tipo de modelo",
         "v2_768": "v2 (768px)",
-        "addDifference": "Añadir una diferencia",
-        "scanForModels": "Buscar modelos"
+        "addDifference": "Añadir una diferencia"
     },
     "parameters": {
         "images": "Imágenes",
@@ -578,7 +574,7 @@
         "autoSaveToGallery": "Guardar automáticamente en galería",
         "saveBoxRegionOnly": "Guardar solo región dentro de la caja",
         "limitStrokesToBox": "Limitar trazos a la caja",
-        "showCanvasDebugInfo": "Mostrar la información adicional del lienzo",
+        "showCanvasDebugInfo": "Mostrar información de depuración de lienzo",
         "clearCanvasHistory": "Limpiar historial de lienzo",
         "clearHistory": "Limpiar historial",
         "clearCanvasHistoryMessage": "Limpiar el historial de lienzo también restablece completamente el lienzo unificado. Esto incluye todo el historial de deshacer/rehacer, las imágenes en el área de preparación y la capa base del lienzo.",

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

@@ -8,6 +8,7 @@
         "darkTheme": "Sombre",
         "lightTheme": "Clair",
         "greenTheme": "Vert",
+        "text2img": "Texte en image",
         "img2img": "Image en image",
         "unifiedCanvas": "Canvas unifié",
         "nodes": "Nœuds",
@@ -46,19 +47,7 @@
         "statusLoadingModel": "Chargement du modèle",
         "statusModelChanged": "Modèle changé",
         "discordLabel": "Discord",
-        "githubLabel": "Github",
-        "accept": "Accepter",
-        "statusMergingModels": "Mélange des modèles",
-        "loadingInvokeAI": "Chargement de Invoke AI",
-        "cancel": "Annuler",
-        "langEnglish": "Anglais",
-        "statusConvertingModel": "Conversion du modèle",
-        "statusModelConverted": "Modèle converti",
-        "loading": "Chargement",
-        "pinOptionsPanel": "Épingler la page d'options",
-        "statusMergedModels": "Modèles mélangés",
-        "txt2img": "Texte vers image",
-        "postprocessing": "Post-Traitement"
+        "githubLabel": "Github"
     },
     "gallery": {
         "generations": "Générations",
@@ -529,15 +518,5 @@
         "betaDarkenOutside": "Assombrir à l'extérieur",
         "betaLimitToBox": "Limiter à la boîte",
         "betaPreserveMasked": "Conserver masqué"
-    },
-    "accessibility": {
-        "uploadImage": "Charger une image",
-        "reset": "Réinitialiser",
-        "nextImage": "Image suivante",
-        "previousImage": "Image précédente",
-        "useThisParameter": "Utiliser ce paramètre",
-        "zoomIn": "Zoom avant",
-        "zoomOut": "Zoom arrière",
-        "showOptionsPanel": "Montrer la page d'options"
     }
 }

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

@@ -125,6 +125,7 @@
         "langSimplifiedChinese": "סינית",
         "langUkranian": "אוקראינית",
         "langSpanish": "ספרדית",
+        "text2img": "טקסט לתמונה",
         "img2img": "תמונה לתמונה",
         "unifiedCanvas": "קנבס מאוחד",
         "nodes": "צמתים",

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

@@ -8,6 +8,7 @@
         "darkTheme": "Scuro",
         "lightTheme": "Chiaro",
         "greenTheme": "Verde",
+        "text2img": "Testo a Immagine",
         "img2img": "Immagine a Immagine",
         "unifiedCanvas": "Tela unificata",
         "nodes": "Nodi",
@@ -69,11 +70,7 @@
         "loading": "Caricamento in corso",
         "oceanTheme": "Oceano",
         "langHebrew": "Ebraico",
-        "loadingInvokeAI": "Caricamento Invoke AI",
-        "postprocessing": "Post Elaborazione",
-        "txt2img": "Testo a Immagine",
-        "accept": "Accetta",
-        "cancel": "Annulla"
+        "loadingInvokeAI": "Caricamento Invoke AI"
     },
     "gallery": {
         "generations": "Generazioni",
@@ -407,8 +404,7 @@
         "v2_768": "v2 (768px)",
         "none": "niente",
         "addDifference": "Aggiungi differenza",
-        "pickModelType": "Scegli il tipo di modello",
-        "scanForModels": "Cerca modelli"
+        "pickModelType": "Scegli il tipo di modello"
     },
     "parameters": {
         "images": "Immagini",
@@ -578,7 +574,7 @@
         "autoSaveToGallery": "Salvataggio automatico nella Galleria",
         "saveBoxRegionOnly": "Salva solo l'area di selezione",
         "limitStrokesToBox": "Limita i tratti all'area di selezione",
-        "showCanvasDebugInfo": "Mostra ulteriori informazioni sulla Tela",
+        "showCanvasDebugInfo": "Mostra informazioni di debug della Tela",
         "clearCanvasHistory": "Cancella cronologia Tela",
         "clearHistory": "Cancella la cronologia",
         "clearCanvasHistoryMessage": "La cancellazione della cronologia della tela lascia intatta la tela corrente, ma cancella in modo irreversibile la cronologia degli annullamenti e dei ripristini.",
@@ -616,7 +612,7 @@
         "copyMetadataJson": "Copia i metadati JSON",
         "exitViewer": "Esci dal visualizzatore",
         "zoomIn": "Zoom avanti",
-        "zoomOut": "Zoom indietro",
+        "zoomOut": "Zoom Indietro",
         "rotateCounterClockwise": "Ruotare in senso antiorario",
         "rotateClockwise": "Ruotare in senso orario",
         "flipHorizontally": "Capovolgi orizzontalmente",

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

@@ -11,6 +11,7 @@
         "langArabic": "العربية",
         "langEnglish": "English",
         "langDutch": "Nederlands",
+        "text2img": "텍스트->이미지",
         "unifiedCanvas": "통합 캔버스",
         "langFrench": "Français",
         "langGerman": "Deutsch",

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

@@ -8,6 +8,7 @@
         "darkTheme": "Donker",
         "lightTheme": "Licht",
         "greenTheme": "Groen",
+        "text2img": "Tekst naar afbeelding",
         "img2img": "Afbeelding naar afbeelding",
         "unifiedCanvas": "Centraal canvas",
         "nodes": "Knooppunten",

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

@@ -8,6 +8,7 @@
         "darkTheme": "Ciemny",
         "lightTheme": "Jasny",
         "greenTheme": "Zielony",
+        "text2img": "Tekst na obraz",
         "img2img": "Obraz na obraz",
         "unifiedCanvas": "Tryb uniwersalny",
         "nodes": "Węzły",

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

@@ -20,6 +20,7 @@
         "langSpanish": "Espanhol",
         "langRussian": "Русский",
         "langUkranian": "Украї́нська",
+        "text2img": "Texto para Imagem",
         "img2img": "Imagem para Imagem",
         "unifiedCanvas": "Tela Unificada",
         "nodes": "Nós",

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

@@ -8,6 +8,7 @@
         "darkTheme": "Noite",
         "lightTheme": "Dia",
         "greenTheme": "Verde",
+        "text2img": "Texto Para Imagem",
         "img2img": "Imagem Para Imagem",
         "unifiedCanvas": "Tela Unificada",
         "nodes": "Nódulos",