chore: v4.0.3

Currently translated at 98.4% (1108 of 1126 strings)

Co-authored-by: Riccardo Giovanetti <riccardo.giovanetti@gmail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/it/
Translation: InvokeAI/Web UI

docs/help/FAQ.md

@@ -18,6 +18,22 @@ Note that any releases marked as _pre-release_ are in a beta state. You may expe
 
 The Model Manager tab in the UI provides a few ways to install models, including using your already-downloaded models. You'll see a popup directing you there on first startup. For more information, see the [model install docs].
 
+## Missing models after updating to v4
+
+If you find some models are missing after updating to v4, it's likely they weren't correctly registered before the update and didn't get picked up in the migration.
+
+You can use the `Scan Folder` tab in the Model Manager UI to fix this. The models will either be in the old, now-unused `autoimport` folder, or your `models` folder.
+
+- Find and copy your install's old `autoimport` folder path, install the main install folder.
+- Go to the Model Manager and click `Scan Folder`.
+- Paste the path and scan.
+- IMPORTANT: Uncheck `Inplace install`.
+- Click `Install All` to install all found models, or just install the models you want.
+
+Next, find and copy your install's `models` folder path (this could be your custom models folder path, or the `models` folder inside the main install folder).
+
+Follow the same steps to scan and import the missing models.
+
 ## Slow generation
 
 - Check the [system requirements] to ensure that your system is capable of generating images.

docs/installation/010_INSTALL_AUTOMATED.md

@@ -44,7 +44,7 @@ The installation process is simple, with a few prompts:
 
 - Select the version to install. Unless you have a specific reason to install a specific version, select the default (the latest version).
 - Select location for the install. Be sure you have enough space in this folder for the base application, as described in the [installation requirements].
-- Select a GPU device. If you are unsure, you can let the installer figure it out.
+- Select a GPU device.
 
 !!! info "Slow Installation"
 

docs/installation/020_INSTALL_MANUAL.md

@@ -6,11 +6,7 @@
 
 ## Introduction
 
-!!! tip "Conda"
-
-    As of InvokeAI v2.3.0 installation using the `conda` package manager is no longer being supported. It will likely still work, but we are not testing this installation method.
-
-InvokeAI is distributed as a python package on PyPI, installable with `pip`. There are a few things that are handled by the installer that you'll need to manage manually, described in this guide.
+InvokeAI is distributed as a python package on PyPI, installable with `pip`. There are a few things that are handled by the installer and launcher that you'll need to manage manually, described in this guide.
 
 ### Requirements
 
@@ -40,11 +36,11 @@ Before you start, go through the [installation requirements].
 
 1. Enter the root (invokeai) directory and create a virtual Python environment within it named `.venv`.
 
-    !!! info "Virtual Environment Location"
+    !!! warning "Virtual Environment Location"
 
         While you may create the virtual environment anywhere in the file system, we recommend that you create it within the root directory as shown here. This allows the application to automatically detect its data directories.
 
-        If you choose a different location for the venv, then you must set the `INVOKEAI_ROOT` environment variable or pass the directory using the `--root` CLI arg.
+        If you choose a different location for the venv, then you _must_ set the `INVOKEAI_ROOT` environment variable or specify the root directory using the `--root` CLI arg.
 
     ```terminal
     cd $INVOKEAI_ROOT
@@ -81,31 +77,23 @@ Before you start, go through the [installation requirements].
     python3 -m pip install --upgrade pip
     ```
 
-1. Install the InvokeAI Package. The `--extra-index-url` option is used to select the correct `torch` backend:
+1. Install the InvokeAI Package. The base command is `pip install InvokeAI --use-pep517`, but you may need to change this depending on your system and the desired features.
 
-    === "CUDA (NVidia)"
+    - You may need to provide an [extra index URL]. Select your platform configuration using [this tool on the PyTorch website]. Copy the `--extra-index-url` string from this and append it to your install command.
 
-         ```bash
-         pip install "InvokeAI[xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
-         ```
+        !!! example "Install with an extra index URL"
 
-    === "ROCm (AMD)"
+            ```bash
+            pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
+            ```
 
-         ```bash
-         pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
-         ```
+    - If you have a CUDA GPU and want to install with `xformers`, you need to add an option to the package name. Note that `xformers` is not necessary. PyTorch includes an implementation of the SDP attention algorithm with the same performance.
 
-    === "CPU (Intel Macs & non-GPU systems)"
+        !!! example "Install with `xformers`"
 
-         ```bash
-         pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/cpu
-         ```
-
-    === "MPS (Apple Silicon)"
-
-         ```bash
-         pip install InvokeAI --use-pep517
-         ```
+            ```bash
+            pip install "InvokeAI[xformers]" --use-pep517
+            ```
 
 1. Deactivate and reactivate your runtime directory so that the invokeai-specific commands become available in the environment:
 
@@ -126,37 +114,6 @@ Before you start, go through the [installation requirements].
 
     Run `invokeai-web` to start the UI. You must activate the virtual environment before running the app.
 
-    If the virtual environment you selected is NOT inside `INVOKEAI_ROOT`, then you must specify the path to the root directory by adding
-    `--root_dir \path\to\invokeai`.
+    !!! warning
 
-    !!! tip
-
-        You can permanently set the location of the runtime directory
-        by setting the environment variable `INVOKEAI_ROOT` to the
-        path of the directory. As mentioned previously, this is
-        recommended if your virtual environment is located outside of
-        your runtime directory.
-
-## Unsupported Conda Install
-
-Congratulations, you found the "secret" Conda installation instructions. If you really **really** want to use Conda with InvokeAI, you can do so using this unsupported recipe:
-
-```sh
-mkdir ~/invokeai
-conda create -n invokeai python=3.11
-conda activate invokeai
-# Adjust this as described above for the appropriate torch backend
-pip install InvokeAI[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
-invokeai-web --root ~/invokeai
-```
-
-The `pip install` command shown in this recipe is for Linux/Windows
-systems with an NVIDIA GPU. See step (6) above for the command to use
-with other platforms/GPU combinations. If you don't wish to pass the
-`--root` argument to `invokeai` with each launch, you may set the
-environment variable `INVOKEAI_ROOT` to point to the installation directory.
-
-Note that if you run into problems with the Conda installation, the InvokeAI
-staff will **not** be able to help you out. Caveat Emptor!
-
-[installation requirements]: INSTALL_REQUIREMENTS.md
+        If the virtual environment is _not_ inside the root directory, then you _must_ specify the path to the root directory with `--root_dir \path\to\invokeai` or the `INVOKEAI_ROOT` environment variable.

docs/installation/INSTALL_DEVELOPMENT.md

@@ -32,5 +32,5 @@ As described in the [frontend dev toolchain] docs, you can run the UI using a de
 [Fork and clone]: https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/fork-a-repo
 [InvokeAI repo]: https://github.com/invoke-ai/InvokeAI
 [frontend dev toolchain]: ../contributing/frontend/OVERVIEW.md
-[manual installation]: installation/020_INSTALL_MANUAL.md
+[manual installation]: ./020_INSTALL_MANUAL.md
 [editable install]: https://pip.pypa.io/en/latest/cli/pip_install/#cmdoption-e

installer/lib/installer.py

@@ -3,6 +3,7 @@
 InvokeAI installer script
 """
 
+import locale
 import os
 import platform
 import re
@@ -316,7 +317,9 @@ def upgrade_pip(venv_path: Path) -> str | None:
     python = str(venv_path.expanduser().resolve() / python)
 
     try:
-        result = subprocess.check_output([python, "-m", "pip", "install", "--upgrade", "pip"]).decode()
+        result = subprocess.check_output([python, "-m", "pip", "install", "--upgrade", "pip"]).decode(
+            encoding=locale.getpreferredencoding()
+        )
     except subprocess.CalledProcessError as e:
         print(e)
         result = None
@@ -404,22 +407,29 @@ def get_torch_source() -> Tuple[str | None, str | None]:
     # device can be one of: "cuda", "rocm", "cpu", "cuda_and_dml, autodetect"
     device = select_gpu()
 
+    # The correct extra index URLs for torch are inconsistent, see https://pytorch.org/get-started/locally/#start-locally
+
     url = None
-    optional_modules = "[onnx]"
+    optional_modules: str | None = None
     if OS == "Linux":
         if device.value == "rocm":
             url = "https://download.pytorch.org/whl/rocm5.6"
         elif device.value == "cpu":
             url = "https://download.pytorch.org/whl/cpu"
-
+        elif device.value == "cuda":
+            # CUDA uses the default PyPi index
+            optional_modules = "[xformers,onnx-cuda]"
     elif OS == "Windows":
         if device.value == "cuda":
             url = "https://download.pytorch.org/whl/cu121"
             optional_modules = "[xformers,onnx-cuda]"
-        if device.value == "cuda_and_dml":
-            url = "https://download.pytorch.org/whl/cu121"
-            optional_modules = "[xformers,onnx-directml]"
+        elif device.value == "cpu":
+            # CPU  uses the default PyPi index, no optional modules
+            pass
+    elif OS == "Darwin":
+        # macOS uses the default PyPi index, no optional modules
+        pass
 
-    # in all other cases, Torch wheels should be coming from PyPi as of Torch 1.13
+    # Fall back to defaults
 
     return (url, optional_modules)

installer/lib/messages.py

@@ -207,10 +207,8 @@ def dest_path(dest: Optional[str | Path] = None) -> Path | None:
 
 class GpuType(Enum):
     CUDA = "cuda"
-    CUDA_AND_DML = "cuda_and_dml"
     ROCM = "rocm"
     CPU = "cpu"
-    AUTODETECT = "autodetect"
 
 
 def select_gpu() -> GpuType:
@@ -226,10 +224,6 @@ def select_gpu() -> GpuType:
         "an [gold1 b]NVIDIA[/] GPU (using CUDA™)",
         GpuType.CUDA,
     )
-    nvidia_with_dml = (
-        "an [gold1 b]NVIDIA[/] GPU (using CUDA™, and DirectML™ for ONNX) -- ALPHA",
-        GpuType.CUDA_AND_DML,
-    )
     amd = (
         "an [gold1 b]AMD[/] GPU (using ROCm™)",
         GpuType.ROCM,
@@ -238,27 +232,19 @@ def select_gpu() -> GpuType:
         "Do not install any GPU support, use CPU for generation (slow)",
         GpuType.CPU,
     )
-    autodetect = (
-        "I'm not sure what to choose",
-        GpuType.AUTODETECT,
-    )
 
     options = []
     if OS == "Windows":
-        options = [nvidia, nvidia_with_dml, cpu]
+        options = [nvidia, cpu]
     if OS == "Linux":
         options = [nvidia, amd, cpu]
     elif OS == "Darwin":
         options = [cpu]
-        # future CoreML?
 
     if len(options) == 1:
         print(f'Your platform [gold1]{OS}-{ARCH}[/] only supports the "{options[0][1]}" driver. Proceeding with that.')
         return options[0][1]
 
-    # "I don't know" is always added the last option
-    options.append(autodetect)  # type: ignore
-
     options = {str(i): opt for i, opt in enumerate(options, 1)}
 
     console.rule(":space_invader: GPU (Graphics Card) selection :space_invader:")
@@ -292,11 +278,6 @@ def select_gpu() -> GpuType:
         ),
     )
 
-    if options[choice][1] is GpuType.AUTODETECT:
-        console.print(
-            "No problem. We will install CUDA support first :crossed_fingers: If Invoke does not detect a GPU, please re-run the installer and select one of the other GPU types."
-        )
-
     return options[choice][1]
 
 

invokeai/app/api/routers/app_info.py

@@ -12,7 +12,7 @@ from pydantic import BaseModel, Field
 
 from invokeai.app.invocations.upscale import ESRGAN_MODELS
 from invokeai.app.services.invocation_cache.invocation_cache_common import InvocationCacheStatus
-from invokeai.backend.image_util.patchmatch import PatchMatch
+from invokeai.backend.image_util.infill_methods.patchmatch import PatchMatch
 from invokeai.backend.image_util.safety_checker import SafetyChecker
 from invokeai.backend.util.logging import logging
 from invokeai.version import __version__
@@ -100,7 +100,7 @@ async def get_app_deps() -> AppDependencyVersions:
 
 @app_router.get("/config", operation_id="get_config", status_code=200, response_model=AppConfig)
 async def get_config() -> AppConfig:
-    infill_methods = ["tile", "lama", "cv2"]
+    infill_methods = ["tile", "lama", "cv2", "color"]  # TODO: add mosaic back
     if PatchMatch.patchmatch_available():
         infill_methods.append("patchmatch")
 

invokeai/app/api/routers/model_manager.py

@@ -219,28 +219,13 @@ async def scan_for_models(
         non_core_model_paths = [p for p in found_model_paths if not p.is_relative_to(core_models_path)]
 
         installed_models = ApiDependencies.invoker.services.model_manager.store.search_by_attr()
-        resolved_installed_model_paths: list[str] = []
-        installed_model_sources: list[str] = []
-
-        # This call lists all installed models.
-        for model in installed_models:
-            path = pathlib.Path(model.path)
-            # If the model has a source, we need to add it to the list of installed sources.
-            if model.source:
-                installed_model_sources.append(model.source)
-            # If the path is not absolute, that means it is in the app models directory, and we need to join it with
-            # the models path before resolving.
-            if not path.is_absolute():
-                resolved_installed_model_paths.append(str(pathlib.Path(models_path, path).resolve()))
-                continue
-            resolved_installed_model_paths.append(str(path.resolve()))
 
         scan_results: list[FoundModel] = []
 
-        # Check if the model is installed by comparing the resolved paths, appending to the scan result.
+        # Check if the model is installed by comparing paths, appending to the scan result.
         for p in non_core_model_paths:
             path = str(p)
-            is_installed = path in resolved_installed_model_paths or path in installed_model_sources
+            is_installed = any(str(models_path / m.path) == path for m in installed_models)
             found_model = FoundModel(path=path, is_installed=is_installed)
             scan_results.append(found_model)
     except Exception as e:
@@ -614,8 +599,8 @@ async def convert_model(
     The return value is the model configuration for the converted model.
     """
     model_manager = ApiDependencies.invoker.services.model_manager
+    loader = model_manager.load
     logger = ApiDependencies.invoker.services.logger
-    loader = ApiDependencies.invoker.services.model_manager.load
     store = ApiDependencies.invoker.services.model_manager.store
     installer = ApiDependencies.invoker.services.model_manager.install
 
@@ -630,7 +615,13 @@ async def convert_model(
         raise HTTPException(400, f"The model with key {key} is not a main checkpoint model.")
 
     # loading the model will convert it into a cached diffusers file
-    model_manager.load.load_model(model_config, submodel_type=SubModelType.Scheduler)
+    try:
+        cc_size = loader.convert_cache.max_size
+        if cc_size == 0:  # temporary set the convert cache to a positive number so that cached model is written
+            loader._convert_cache.max_size = 1.0
+        loader.load_model(model_config, submodel_type=SubModelType.Scheduler)
+    finally:
+        loader._convert_cache.max_size = cc_size
 
     # Get the path of the converted model from the loader
     cache_path = loader.convert_cache.cache_path(key)

invokeai/app/invocations/custom_nodes/init.py

@@ -3,6 +3,7 @@ Invoke-managed custom node loader. See README.md for more information.
 """
 
 import sys
+import traceback
 from importlib.util import module_from_spec, spec_from_file_location
 from pathlib import Path
 
@@ -41,11 +42,15 @@ for d in Path(__file__).parent.iterdir():
 
     logger.info(f"Loading node pack {module_name}")
 
-    module = module_from_spec(spec)
-    sys.modules[spec.name] = module
-    spec.loader.exec_module(module)
+    try:
+        module = module_from_spec(spec)
+        sys.modules[spec.name] = module
+        spec.loader.exec_module(module)
 
-    loaded_count += 1
+        loaded_count += 1
+    except Exception:
+        full_error = traceback.format_exc()
+        logger.error(f"Failed to load node pack {module_name}:\n{full_error}")
 
     del init, module_name
 

invokeai/app/invocations/infill.py

@@ -1,154 +1,91 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
+from abc import abstractmethod
+from typing import Literal, get_args
 
-import math
-from typing import Literal, Optional, get_args
-
-import numpy as np
-from PIL import Image, ImageOps
+from PIL import Image
 
 from invokeai.app.invocations.fields import ColorField, ImageField
 from invokeai.app.invocations.primitives import ImageOutput
 from invokeai.app.services.shared.invocation_context import InvocationContext
-from invokeai.app.util.download_with_progress import download_with_progress_bar
 from invokeai.app.util.misc import SEED_MAX
-from invokeai.backend.image_util.cv2_inpaint import cv2_inpaint
-from invokeai.backend.image_util.lama import LaMA
-from invokeai.backend.image_util.patchmatch import PatchMatch
+from invokeai.backend.image_util.infill_methods.cv2_inpaint import cv2_inpaint
+from invokeai.backend.image_util.infill_methods.lama import LaMA
+from invokeai.backend.image_util.infill_methods.mosaic import infill_mosaic
+from invokeai.backend.image_util.infill_methods.patchmatch import PatchMatch, infill_patchmatch
+from invokeai.backend.image_util.infill_methods.tile import infill_tile
+from invokeai.backend.util.logging import InvokeAILogger
 
 from .baseinvocation import BaseInvocation, invocation
 from .fields import InputField, WithBoard, WithMetadata
 from .image import PIL_RESAMPLING_MAP, PIL_RESAMPLING_MODES
 
+logger = InvokeAILogger.get_logger()
 
-def infill_methods() -> list[str]:
-    methods = ["tile", "solid", "lama", "cv2"]
+
+def get_infill_methods():
+    methods = Literal["tile", "color", "lama", "cv2"]  # TODO: add mosaic back
     if PatchMatch.patchmatch_available():
-        methods.insert(0, "patchmatch")
+        methods = Literal["patchmatch", "tile", "color", "lama", "cv2"]  # TODO: add mosaic back
     return methods
 
 
-INFILL_METHODS = Literal[tuple(infill_methods())]
+INFILL_METHODS = get_infill_methods()
 DEFAULT_INFILL_METHOD = "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
 
 
-def infill_lama(im: Image.Image) -> Image.Image:
-    lama = LaMA()
-    return lama(im)
+class InfillImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Base class for invocations that preprocess images for Infilling"""
 
+    image: ImageField = InputField(description="The image to process")
 
-def infill_patchmatch(im: Image.Image) -> Image.Image:
-    if im.mode != "RGBA":
-        return im
+    @abstractmethod
+    def infill(self, image: Image.Image) -> Image.Image:
+        """Infill the image with the specified method"""
+        pass
 
-    # Skip patchmatch if patchmatch isn't available
-    if not PatchMatch.patchmatch_available():
-        return im
+    def load_image(self, context: InvocationContext) -> tuple[Image.Image, bool]:
+        """Process the image to have an alpha channel before being infilled"""
+        image = context.images.get_pil(self.image.image_name)
+        has_alpha = True if image.mode == "RGBA" else False
+        return image, has_alpha
 
-    # Patchmatch (note, we may want to expose patch_size? Increasing it significantly impacts performance though)
-    im_patched_np = PatchMatch.inpaint(im.convert("RGB"), ImageOps.invert(im.split()[-1]), patch_size=3)
-    im_patched = Image.fromarray(im_patched_np, mode="RGB")
-    return im_patched
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        # Retrieve and process image to be infilled
+        input_image, has_alpha = self.load_image(context)
 
+        # If the input image has no alpha channel, return it
+        if has_alpha is False:
+            return ImageOutput.build(context.images.get_dto(self.image.image_name))
 
-def infill_cv2(im: Image.Image) -> Image.Image:
-    return cv2_inpaint(im)
+        # Perform Infill action
+        infilled_image = self.infill(input_image)
 
+        # Create ImageDTO for Infilled Image
+        infilled_image_dto = context.images.save(image=infilled_image)
 
-def get_tile_images(image: np.ndarray, width=8, height=8):
-    _nrows, _ncols, depth = image.shape
-    _strides = image.strides
-
-    nrows, _m = divmod(_nrows, height)
-    ncols, _n = divmod(_ncols, width)
-    if _m != 0 or _n != 0:
-        return None
-
-    return np.lib.stride_tricks.as_strided(
-        np.ravel(image),
-        shape=(nrows, ncols, height, width, depth),
-        strides=(height * _strides[0], width * _strides[1], *_strides),
-        writeable=False,
-    )
-
-
-def tile_fill_missing(im: Image.Image, tile_size: int = 16, seed: Optional[int] = None) -> Image.Image:
-    # Only fill if there's an alpha layer
-    if im.mode != "RGBA":
-        return im
-
-    a = np.asarray(im, dtype=np.uint8)
-
-    tile_size_tuple = (tile_size, tile_size)
-
-    # Get the image as tiles of a specified size
-    tiles = get_tile_images(a, *tile_size_tuple).copy()
-
-    # Get the mask as tiles
-    tiles_mask = tiles[:, :, :, :, 3]
-
-    # Find any mask tiles with any fully transparent pixels (we will be replacing these later)
-    tmask_shape = tiles_mask.shape
-    tiles_mask = tiles_mask.reshape(math.prod(tiles_mask.shape))
-    n, ny = (math.prod(tmask_shape[0:2])), math.prod(tmask_shape[2:])
-    tiles_mask = tiles_mask > 0
-    tiles_mask = tiles_mask.reshape((n, ny)).all(axis=1)
-
-    # Get RGB tiles in single array and filter by the mask
-    tshape = tiles.shape
-    tiles_all = tiles.reshape((math.prod(tiles.shape[0:2]), *tiles.shape[2:]))
-    filtered_tiles = tiles_all[tiles_mask]
-
-    if len(filtered_tiles) == 0:
-        return im
-
-    # Find all invalid tiles and replace with a random valid tile
-    replace_count = (tiles_mask == False).sum()  # noqa: E712
-    rng = np.random.default_rng(seed=seed)
-    tiles_all[np.logical_not(tiles_mask)] = filtered_tiles[rng.choice(filtered_tiles.shape[0], replace_count), :, :, :]
-
-    # Convert back to an image
-    tiles_all = tiles_all.reshape(tshape)
-    tiles_all = tiles_all.swapaxes(1, 2)
-    st = tiles_all.reshape(
-        (
-            math.prod(tiles_all.shape[0:2]),
-            math.prod(tiles_all.shape[2:4]),
-            tiles_all.shape[4],
-        )
-    )
-    si = Image.fromarray(st, mode="RGBA")
-
-    return si
+        # Return Infilled Image
+        return ImageOutput.build(infilled_image_dto)
 
 
 @invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2")
-class InfillColorInvocation(BaseInvocation, WithMetadata, WithBoard):
+class InfillColorInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image with a solid color"""
 
-    image: ImageField = InputField(description="The image to infill")
     color: ColorField = InputField(
         default=ColorField(r=127, g=127, b=127, a=255),
         description="The color to use to infill",
     )
 
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.images.get_pil(self.image.image_name)
-
+    def infill(self, image: Image.Image):
         solid_bg = Image.new("RGBA", image.size, self.color.tuple())
         infilled = Image.alpha_composite(solid_bg, image.convert("RGBA"))
-
         infilled.paste(image, (0, 0), image.split()[-1])
-
-        image_dto = context.images.save(image=infilled)
-
-        return ImageOutput.build(image_dto)
+        return infilled
 
 
 @invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.3")
-class InfillTileInvocation(BaseInvocation, WithMetadata, WithBoard):
+class InfillTileInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image with tiles of the image"""
 
-    image: ImageField = InputField(description="The image to infill")
     tile_size: int = InputField(default=32, ge=1, description="The tile size (px)")
     seed: int = InputField(
         default=0,
@@ -157,92 +94,74 @@ class InfillTileInvocation(BaseInvocation, WithMetadata, WithBoard):
         description="The seed to use for tile generation (omit for random)",
     )
 
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.images.get_pil(self.image.image_name)
-
-        infilled = tile_fill_missing(image.copy(), seed=self.seed, tile_size=self.tile_size)
-        infilled.paste(image, (0, 0), image.split()[-1])
-
-        image_dto = context.images.save(image=infilled)
-
-        return ImageOutput.build(image_dto)
+    def infill(self, image: Image.Image):
+        output = infill_tile(image, seed=self.seed, tile_size=self.tile_size)
+        return output.infilled
 
 
 @invocation(
     "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2"
 )
-class InfillPatchMatchInvocation(BaseInvocation, WithMetadata, WithBoard):
+class InfillPatchMatchInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image using the PatchMatch algorithm"""
 
-    image: ImageField = InputField(description="The image to infill")
     downscale: float = InputField(default=2.0, gt=0, description="Run patchmatch on downscaled image to speedup infill")
     resample_mode: PIL_RESAMPLING_MODES = InputField(default="bicubic", description="The resampling mode")
 
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.images.get_pil(self.image.image_name).convert("RGBA")
-
+    def infill(self, image: Image.Image):
         resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
 
-        infill_image = image.copy()
         width = int(image.width / self.downscale)
         height = int(image.height / self.downscale)
-        infill_image = infill_image.resize(
+
+        infilled = image.resize(
             (width, height),
             resample=resample_mode,
         )
-
-        if PatchMatch.patchmatch_available():
-            infilled = infill_patchmatch(infill_image)
-        else:
-            raise ValueError("PatchMatch is not available on this system")
-
+        infilled = infill_patchmatch(image)
         infilled = infilled.resize(
             (image.width, image.height),
             resample=resample_mode,
         )
-
         infilled.paste(image, (0, 0), mask=image.split()[-1])
-        # image.paste(infilled, (0, 0), mask=image.split()[-1])
 
-        image_dto = context.images.save(image=infilled)
-
-        return ImageOutput.build(image_dto)
+        return infilled
 
 
 @invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2")
-class LaMaInfillInvocation(BaseInvocation, WithMetadata, WithBoard):
+class LaMaInfillInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image using the LaMa model"""
 
-    image: ImageField = InputField(description="The image to infill")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.images.get_pil(self.image.image_name)
-
-        # Downloads the LaMa model if it doesn't already exist
-        download_with_progress_bar(
-            name="LaMa Inpainting Model",
-            url="https://github.com/Sanster/models/releases/download/add_big_lama/big-lama.pt",
-            dest_path=context.config.get().models_path / "core/misc/lama/lama.pt",
-        )
-
-        infilled = infill_lama(image.copy())
-
-        image_dto = context.images.save(image=infilled)
-
-        return ImageOutput.build(image_dto)
+    def infill(self, image: Image.Image):
+        lama = LaMA()
+        return lama(image)
 
 
 @invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2")
-class CV2InfillInvocation(BaseInvocation, WithMetadata, WithBoard):
+class CV2InfillInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image using OpenCV Inpainting"""
 
+    def infill(self, image: Image.Image):
+        return cv2_inpaint(image)
+
+
+# @invocation(
+#     "infill_mosaic", title="Mosaic Infill", tags=["image", "inpaint", "outpaint"], category="inpaint", version="1.0.0"
+# )
+class MosaicInfillInvocation(InfillImageProcessorInvocation):
+    """Infills transparent areas of an image with a mosaic pattern drawing colors from the rest of the image"""
+
     image: ImageField = InputField(description="The image to infill")
+    tile_width: int = InputField(default=64, description="Width of the tile")
+    tile_height: int = InputField(default=64, description="Height of the tile")
+    min_color: ColorField = InputField(
+        default=ColorField(r=0, g=0, b=0, a=255),
+        description="The min threshold for color",
+    )
+    max_color: ColorField = InputField(
+        default=ColorField(r=255, g=255, b=255, a=255),
+        description="The max threshold for color",
+    )
 
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.images.get_pil(self.image.image_name)
-
-        infilled = infill_cv2(image.copy())
-
-        image_dto = context.images.save(image=infilled)
-
-        return ImageOutput.build(image_dto)
+    def infill(self, image: Image.Image):
+        return infill_mosaic(image, (self.tile_width, self.tile_height), self.min_color.tuple(), self.max_color.tuple())

invokeai/app/invocations/ip_adapter.py

@@ -1,21 +1,22 @@
 from builtins import float
-from typing import List, Union
+from typing import List, Literal, Union
 
 from pydantic import BaseModel, Field, field_validator, model_validator
 from typing_extensions import Self
 
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    invocation,
-    invocation_output,
-)
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
 from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIType
 from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
 from invokeai.app.services.shared.invocation_context import InvocationContext
-from invokeai.backend.model_manager.config import AnyModelConfig, BaseModelType, IPAdapterConfig, ModelType
+from invokeai.backend.model_manager.config import (
+    AnyModelConfig,
+    BaseModelType,
+    IPAdapterCheckpointConfig,
+    IPAdapterInvokeAIConfig,
+    ModelType,
+)
 
 
 class IPAdapterField(BaseModel):
@@ -48,12 +49,15 @@ class IPAdapterOutput(BaseInvocationOutput):
     ip_adapter: IPAdapterField = OutputField(description=FieldDescriptions.ip_adapter, title="IP-Adapter")
 
 
+CLIP_VISION_MODEL_MAP = {"ViT-H": "ip_adapter_sd_image_encoder", "ViT-G": "ip_adapter_sdxl_image_encoder"}
+
+
 @invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.2.2")
 class IPAdapterInvocation(BaseInvocation):
     """Collects IP-Adapter info to pass to other nodes."""
 
     # Inputs
-    image: Union[ImageField, List[ImageField]] = InputField(description="The IP-Adapter image prompt(s).")
+    image: Union[ImageField, List[ImageField]] = InputField(description="The IP-Adapter image prompt(s).", ui_order=1)
     ip_adapter_model: ModelIdentifierField = InputField(
         description="The IP-Adapter model.",
         title="IP-Adapter Model",
@@ -61,7 +65,11 @@ class IPAdapterInvocation(BaseInvocation):
         ui_order=-1,
         ui_type=UIType.IPAdapterModel,
     )
-
+    clip_vision_model: Literal["ViT-H", "ViT-G"] = InputField(
+        description="CLIP Vision model to use. Overrides model settings. Mandatory for checkpoint models.",
+        default="auto",
+        ui_order=2,
+    )
     weight: Union[float, List[float]] = InputField(
         default=1, description="The weight given to the IP-Adapter", title="Weight"
     )
@@ -86,10 +94,16 @@ class IPAdapterInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> IPAdapterOutput:
         # Lookup the CLIP Vision encoder that is intended to be used with the IP-Adapter model.
         ip_adapter_info = context.models.get_config(self.ip_adapter_model.key)
-        assert isinstance(ip_adapter_info, IPAdapterConfig)
-        image_encoder_model_id = ip_adapter_info.image_encoder_model_id
-        image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
+        assert isinstance(ip_adapter_info, (IPAdapterInvokeAIConfig, IPAdapterCheckpointConfig))
+
+        if isinstance(ip_adapter_info, IPAdapterInvokeAIConfig):
+            image_encoder_model_id = ip_adapter_info.image_encoder_model_id
+            image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
+        else:
+            image_encoder_model_name = CLIP_VISION_MODEL_MAP[self.clip_vision_model]
+
         image_encoder_model = self._get_image_encoder(context, image_encoder_model_name)
+
         return IPAdapterOutput(
             ip_adapter=IPAdapterField(
                 image=self.image,
@@ -102,19 +116,25 @@ class IPAdapterInvocation(BaseInvocation):
         )
 
     def _get_image_encoder(self, context: InvocationContext, image_encoder_model_name: str) -> AnyModelConfig:
-        found = False
-        while not found:
+        image_encoder_models = context.models.search_by_attrs(
+            name=image_encoder_model_name, base=BaseModelType.Any, type=ModelType.CLIPVision
+        )
+
+        if not len(image_encoder_models) > 0:
+            context.logger.warning(
+                f"The image encoder required by this IP Adapter ({image_encoder_model_name}) is not installed. \
+                    Downloading and installing now. This may take a while."
+            )
+
+            installer = context._services.model_manager.install
+            job = installer.heuristic_import(f"InvokeAI/{image_encoder_model_name}")
+            installer.wait_for_job(job, timeout=600)  # Wait for up to 10 minutes
             image_encoder_models = context.models.search_by_attrs(
                 name=image_encoder_model_name, base=BaseModelType.Any, type=ModelType.CLIPVision
             )
-            found = len(image_encoder_models) > 0
-            if not found:
-                context.logger.warning(
-                    f"The image encoder required by this IP Adapter ({image_encoder_model_name}) is not installed."
-                )
-                context.logger.warning("Downloading and installing now. This may take a while.")
-                installer = context._services.model_manager.install
-                job = installer.heuristic_import(f"InvokeAI/{image_encoder_model_name}")
-                installer.wait_for_job(job, timeout=600)  # wait up to 10 minutes - then raise a TimeoutException
-        assert len(image_encoder_models) == 1
+
+            if len(image_encoder_models) == 0:
+                context.logger.error("Error while fetching CLIP Vision Image Encoder")
+                assert len(image_encoder_models) == 1
+
         return image_encoder_models[0]

invokeai/app/invocations/latent.py

@@ -43,11 +43,7 @@ from invokeai.app.invocations.fields import (
     WithMetadata,
 )
 from invokeai.app.invocations.ip_adapter import IPAdapterField
-from invokeai.app.invocations.primitives import (
-    DenoiseMaskOutput,
-    ImageOutput,
-    LatentsOutput,
-)
+from invokeai.app.invocations.primitives import DenoiseMaskOutput, ImageOutput, LatentsOutput
 from invokeai.app.invocations.t2i_adapter import T2IAdapterField
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.controlnet_utils import prepare_control_image
@@ -68,12 +64,7 @@ from ...backend.stable_diffusion.diffusers_pipeline import (
 )
 from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
 from ...backend.util.devices import choose_precision, choose_torch_device
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    invocation,
-    invocation_output,
-)
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
 from .controlnet_image_processors import ControlField
 from .model import ModelIdentifierField, UNetField, VAEField
 
@@ -1263,7 +1254,7 @@ class IdealSizeInvocation(BaseInvocation):
         return tuple((x - x % multiple_of) for x in args)
 
     def invoke(self, context: InvocationContext) -> IdealSizeOutput:
-        unet_config = context.models.get_config(**self.unet.unet.model_dump())
+        unet_config = context.models.get_config(self.unet.unet.key)
         aspect = self.width / self.height
         dimension: float = 512
         if unet_config.base == BaseModelType.StableDiffusion2:

invokeai/app/invocations/metadata.py

@@ -2,16 +2,8 @@ from typing import Any, Literal, Optional, Union
 
 from pydantic import BaseModel, ConfigDict, Field
 
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    invocation,
-    invocation_output,
-)
-from invokeai.app.invocations.controlnet_image_processors import (
-    CONTROLNET_MODE_VALUES,
-    CONTROLNET_RESIZE_VALUES,
-)
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
+from invokeai.app.invocations.controlnet_image_processors import CONTROLNET_MODE_VALUES, CONTROLNET_RESIZE_VALUES
 from invokeai.app.invocations.fields import (
     FieldDescriptions,
     ImageField,
@@ -43,6 +35,7 @@ class IPAdapterMetadataField(BaseModel):
 
     image: ImageField = Field(description="The IP-Adapter image prompt.")
     ip_adapter_model: ModelIdentifierField = Field(description="The IP-Adapter model.")
+    clip_vision_model: Literal["ViT-H", "ViT-G"] = Field(description="The CLIP Vision model")
     weight: Union[float, list[float]] = Field(description="The weight given to the IP-Adapter")
     begin_step_percent: float = Field(description="When the IP-Adapter is first applied (% of total steps)")
     end_step_percent: float = Field(description="When the IP-Adapter is last applied (% of total steps)")

invokeai/app/services/config/config_default.py

@@ -3,6 +3,7 @@
 
 from __future__ import annotations
 
+import locale
 import os
 import re
 import shutil
@@ -317,11 +318,10 @@ class InvokeAIAppConfig(BaseSettings):
     @staticmethod
     def find_root() -> Path:
         """Choose the runtime root directory when not specified on command line or init file."""
-        venv = Path(os.environ.get("VIRTUAL_ENV") or ".")
         if os.environ.get("INVOKEAI_ROOT"):
             root = Path(os.environ["INVOKEAI_ROOT"])
-        elif any((venv.parent / x).exists() for x in [INIT_FILE, LEGACY_INIT_FILE]):
-            root = (venv.parent).resolve()
+        elif venv := os.environ.get("VIRTUAL_ENV", None):
+            root = Path(venv).parent.resolve()
         else:
             root = Path("~/invokeai").expanduser().resolve()
         return root
@@ -373,13 +373,16 @@ def migrate_v3_config_dict(config_dict: dict[str, Any]) -> InvokeAIAppConfig:
             if k == "conf_path":
                 parsed_config_dict["legacy_models_yaml_path"] = v
             if k == "legacy_conf_dir":
-                # The old default for this was "configs/stable-diffusion". If if the incoming config has that as the value, we won't set it.
-                # Else if the path ends in "stable-diffusion", we assume the parent is the new correct path.
-                # Else we do not attempt to migrate this setting
-                if v != "configs/stable-diffusion":
-                    parsed_config_dict["legacy_conf_dir"] = v
+                # The old default for this was "configs/stable-diffusion" ("configs\stable-diffusion" on Windows).
+                if v == "configs/stable-diffusion" or v == "configs\\stable-diffusion":
+                    # If if the incoming config has the default value, skip
+                    continue
                 elif Path(v).name == "stable-diffusion":
+                    # Else if the path ends in "stable-diffusion", we assume the parent is the new correct path.
                     parsed_config_dict["legacy_conf_dir"] = str(Path(v).parent)
+                else:
+                    # Else we do not attempt to migrate this setting
+                    parsed_config_dict["legacy_conf_dir"] = v
             elif k in InvokeAIAppConfig.model_fields:
                 # skip unknown fields
                 parsed_config_dict[k] = v
@@ -399,7 +402,7 @@ def load_and_migrate_config(config_path: Path) -> InvokeAIAppConfig:
         An instance of `InvokeAIAppConfig` with the loaded and migrated settings.
     """
     assert config_path.suffix == ".yaml"
-    with open(config_path) as file:
+    with open(config_path, "rt", encoding=locale.getpreferredencoding()) as file:
         loaded_config_dict = yaml.safe_load(file)
 
     assert isinstance(loaded_config_dict, dict)

invokeai/app/services/model_install/model_install_default.py

@@ -1,5 +1,6 @@
 """Model installation class."""
 
+import locale
 import os
 import re
 import signal
@@ -323,7 +324,8 @@ class ModelInstallService(ModelInstallServiceBase):
             legacy_models_yaml_path = Path(self._app_config.root_path, legacy_models_yaml_path)
 
         if legacy_models_yaml_path.exists():
-            legacy_models_yaml = yaml.safe_load(legacy_models_yaml_path.read_text())
+            with open(legacy_models_yaml_path, "rt", encoding=locale.getpreferredencoding()) as file:
+                legacy_models_yaml = yaml.safe_load(file)
 
             yaml_metadata = legacy_models_yaml.pop("__metadata__")
             yaml_version = yaml_metadata.get("version")
@@ -348,8 +350,13 @@ class ModelInstallService(ModelInstallServiceBase):
                     config: dict[str, Any] = {}
                     config["name"] = model_name
                     config["description"] = stanza.get("description")
-                    config["config_path"] = stanza.get("config")
-
+                    legacy_config_path = stanza.get("config")
+                    if legacy_config_path:
+                        # In v3, these paths were relative to the root. Migrate them to be relative to the legacy_conf_dir.
+                        legacy_config_path: Path = self._app_config.root_path / legacy_config_path
+                        if legacy_config_path.is_relative_to(self._app_config.legacy_conf_path):
+                            legacy_config_path = legacy_config_path.relative_to(self._app_config.legacy_conf_path)
+                        config["config_path"] = str(legacy_config_path)
                     try:
                         id = self.register_path(model_path=model_path, config=config)
                         self._logger.info(f"Migrated {model_name} with id {id}")
@@ -368,11 +375,13 @@ class ModelInstallService(ModelInstallServiceBase):
     def delete(self, key: str) -> None:  # noqa D102
         """Unregister the model. Delete its files only if they are within our models directory."""
         model = self.record_store.get_model(key)
-        models_dir = self.app_config.models_path
-        model_path = models_dir / Path(model.path)  # handle legacy relative model paths
-        if model_path.is_relative_to(models_dir):
+        model_path = self.app_config.models_path / model.path
+
+        if model_path.is_relative_to(self.app_config.models_path):
+            # If the models is in the Invoke-managed models dir, we delete it
             self.unconditionally_delete(key)
         else:
+            # Else we only unregister it, leaving the file in place
             self.unregister(key)
 
     def unconditionally_delete(self, key: str) -> None:  # noqa D102
@@ -500,9 +509,9 @@ class ModelInstallService(ModelInstallServiceBase):
     def _scan_for_missing_models(self) -> list[AnyModelConfig]:
         """Scan the models directory for missing models and return a list of them."""
         missing_models: list[AnyModelConfig] = []
-        for x in self.record_store.all_models():
-            if not Path(x.path).resolve().exists():
-                missing_models.append(x)
+        for model_config in self.record_store.all_models():
+            if not (self.app_config.models_path / model_config.path).resolve().exists():
+                missing_models.append(model_config)
         return missing_models
 
     def _register_orphaned_models(self) -> None:
@@ -512,7 +521,9 @@ class ModelInstallService(ModelInstallServiceBase):
         only situations in which we may have orphaned models in the models directory.
         """
 
-        installed_model_paths = {Path(x.path).resolve() for x in self.record_store.all_models()}
+        installed_model_paths = {
+            (self._app_config.models_path / x.path).resolve() for x in self.record_store.all_models()
+        }
 
         # The bool returned by this callback determines if the model is added to the list of models found by the search
         def on_model_found(model_path: Path) -> bool:
@@ -548,20 +559,21 @@ class ModelInstallService(ModelInstallServiceBase):
         May raise an UnknownModelException.
         """
         model = self.record_store.get_model(key)
-        old_path = Path(model.path).resolve()
-        models_dir = self.app_config.models_path.resolve()
+        models_dir = self.app_config.models_path
+        old_path = self.app_config.models_path / model.path
 
         if not old_path.is_relative_to(models_dir):
+            # The model is not in the models directory - we don't need to move it.
             return model
 
-        new_path = (models_dir / model.base.value / model.type.value / model.name).with_suffix(old_path.suffix)
+        new_path = models_dir / model.base.value / model.type.value / old_path.name
 
         if old_path == new_path or new_path.exists() and old_path == new_path.resolve():
             return model
 
         self._logger.info(f"Moving {model.name} to {new_path}.")
         new_path = self._move_model(old_path, new_path)
-        model.path = new_path.as_posix()
+        model.path = new_path.relative_to(models_dir).as_posix()
         self.record_store.update_model(key, ModelRecordChanges(path=model.path))
         return model
 
@@ -600,12 +612,19 @@ class ModelInstallService(ModelInstallServiceBase):
 
         model_path = model_path.resolve()
 
+        # Models in the Invoke-managed models dir should use relative paths.
+        if model_path.is_relative_to(self.app_config.models_path):
+            model_path = model_path.relative_to(self.app_config.models_path)
+
         info.path = model_path.as_posix()
 
-        # Checkpoints have a config file needed for conversion - resolve this to an absolute path
         if isinstance(info, CheckpointConfigBase):
-            legacy_conf = (self.app_config.legacy_conf_path / info.config_path).resolve()
-            info.config_path = legacy_conf.as_posix()
+            # Checkpoints have a config file needed for conversion. Same handling as the model weights - if it's in the
+            # invoke-managed legacy config dir, we use a relative path.
+            legacy_config_path = self.app_config.legacy_conf_path / info.config_path
+            if legacy_config_path.is_relative_to(self.app_config.legacy_conf_path):
+                legacy_config_path = legacy_config_path.relative_to(self.app_config.legacy_conf_path)
+            info.config_path = legacy_config_path.as_posix()
         self.record_store.add_model(info)
         return info.key
 

invokeai/app/services/model_manager/model_manager_default.py

@@ -80,6 +80,7 @@ class ModelManagerService(ModelManagerServiceBase):
         ram_cache = ModelCache(
             max_cache_size=app_config.ram,
             max_vram_cache_size=app_config.vram,
+            lazy_offloading=app_config.lazy_offload,
             logger=logger,
             execution_device=execution_device,
         )

invokeai/app/services/session_processor/session_processor_default.py

@@ -70,8 +70,18 @@ class DefaultSessionProcessor(SessionProcessorBase):
     async def _on_queue_event(self, event: FastAPIEvent) -> None:
         event_name = event[1]["event"]
 
-        if event_name == "session_canceled" or event_name == "queue_cleared":
-            # These both mean we should cancel the current session.
+        if (
+            event_name == "session_canceled"
+            and self._queue_item
+            and self._queue_item.item_id == event[1]["data"]["queue_item_id"]
+        ):
+            self._cancel_event.set()
+            self._poll_now()
+        elif (
+            event_name == "queue_cleared"
+            and self._queue_item
+            and self._queue_item.queue_id == event[1]["data"]["queue_id"]
+        ):
             self._cancel_event.set()
             self._poll_now()
         elif event_name == "batch_enqueued":
@@ -111,141 +121,146 @@ class DefaultSessionProcessor(SessionProcessorBase):
                 poll_now_event.clear()
                 # Middle processor try block; any unhandled exception is a non-fatal processor error
                 try:
+                    # If we are paused, wait for resume event
+                    resume_event.wait()
+
                     # Get the next session to process
                     self._queue_item = self._invoker.services.session_queue.dequeue()
-                    if self._queue_item is not None and resume_event.is_set():
-                        self._invoker.services.logger.debug(f"Executing queue item {self._queue_item.item_id}")
-                        cancel_event.clear()
 
-                        # If profiling is enabled, start the profiler
-                        if self._profiler is not None:
-                            self._profiler.start(profile_id=self._queue_item.session_id)
+                    if self._queue_item is None:
+                        # The queue was empty, wait for next polling interval or event to try again
+                        self._invoker.services.logger.debug("Waiting for next polling interval or event")
+                        poll_now_event.wait(self._polling_interval)
+                        continue
 
-                        # Prepare invocations and take the first
-                        self._invocation = self._queue_item.session.next()
+                    self._invoker.services.logger.debug(f"Executing queue item {self._queue_item.item_id}")
+                    cancel_event.clear()
 
-                        # Loop over invocations until the session is complete or canceled
-                        while self._invocation is not None and not cancel_event.is_set():
-                            # get the source node id to provide to clients (the prepared node id is not as useful)
-                            source_invocation_id = self._queue_item.session.prepared_source_mapping[self._invocation.id]
+                    # If profiling is enabled, start the profiler
+                    if self._profiler is not None:
+                        self._profiler.start(profile_id=self._queue_item.session_id)
 
-                            # Send starting event
-                            self._invoker.services.events.emit_invocation_started(
-                                queue_batch_id=self._queue_item.batch_id,
-                                queue_item_id=self._queue_item.item_id,
-                                queue_id=self._queue_item.queue_id,
-                                graph_execution_state_id=self._queue_item.session_id,
-                                node=self._invocation.model_dump(),
-                                source_node_id=source_invocation_id,
-                            )
+                    # Prepare invocations and take the first
+                    self._invocation = self._queue_item.session.next()
 
-                            # Innermost processor try block; any unhandled exception is an invocation error & will fail the graph
-                            try:
-                                with self._invoker.services.performance_statistics.collect_stats(
-                                    self._invocation, self._queue_item.session.id
-                                ):
-                                    # Build invocation context (the node-facing API)
-                                    data = InvocationContextData(
-                                        invocation=self._invocation,
-                                        source_invocation_id=source_invocation_id,
-                                        queue_item=self._queue_item,
-                                    )
-                                    context = build_invocation_context(
-                                        data=data,
-                                        services=self._invoker.services,
-                                        cancel_event=self._cancel_event,
-                                    )
+                    # Loop over invocations until the session is complete or canceled
+                    while self._invocation is not None and not cancel_event.is_set():
+                        # get the source node id to provide to clients (the prepared node id is not as useful)
+                        source_invocation_id = self._queue_item.session.prepared_source_mapping[self._invocation.id]
 
-                                    # Invoke the node
-                                    outputs = self._invocation.invoke_internal(
-                                        context=context, services=self._invoker.services
-                                    )
+                        # Send starting event
+                        self._invoker.services.events.emit_invocation_started(
+                            queue_batch_id=self._queue_item.batch_id,
+                            queue_item_id=self._queue_item.item_id,
+                            queue_id=self._queue_item.queue_id,
+                            graph_execution_state_id=self._queue_item.session_id,
+                            node=self._invocation.model_dump(),
+                            source_node_id=source_invocation_id,
+                        )
 
-                                    # Save outputs and history
-                                    self._queue_item.session.complete(self._invocation.id, outputs)
-
-                                    # Send complete event
-                                    self._invoker.services.events.emit_invocation_complete(
-                                        queue_batch_id=self._queue_item.batch_id,
-                                        queue_item_id=self._queue_item.item_id,
-                                        queue_id=self._queue_item.queue_id,
-                                        graph_execution_state_id=self._queue_item.session.id,
-                                        node=self._invocation.model_dump(),
-                                        source_node_id=source_invocation_id,
-                                        result=outputs.model_dump(),
-                                    )
-
-                            except KeyboardInterrupt:
-                                # TODO(MM2): Create an event for this
-                                pass
-
-                            except CanceledException:
-                                # When the user cancels the graph, we first set the cancel event. The event is checked
-                                # between invocations, in this loop. Some invocations are long-running, and we need to
-                                # be able to cancel them mid-execution.
-                                #
-                                # For example, denoising is a long-running invocation with many steps. A step callback
-                                # is executed after each step. This step callback checks if the canceled event is set,
-                                # then raises a CanceledException to stop execution immediately.
-                                #
-                                # When we get a CanceledException, we don't need to do anything - just pass and let the
-                                # loop go to its next iteration, and the cancel event will be handled correctly.
-                                pass
-
-                            except Exception as e:
-                                error = traceback.format_exc()
-
-                                # Save error
-                                self._queue_item.session.set_node_error(self._invocation.id, error)
-                                self._invoker.services.logger.error(
-                                    f"Error while invoking session {self._queue_item.session_id}, invocation {self._invocation.id} ({self._invocation.get_type()}):\n{e}"
+                        # Innermost processor try block; any unhandled exception is an invocation error & will fail the graph
+                        try:
+                            with self._invoker.services.performance_statistics.collect_stats(
+                                self._invocation, self._queue_item.session.id
+                            ):
+                                # Build invocation context (the node-facing API)
+                                data = InvocationContextData(
+                                    invocation=self._invocation,
+                                    source_invocation_id=source_invocation_id,
+                                    queue_item=self._queue_item,
+                                )
+                                context = build_invocation_context(
+                                    data=data,
+                                    services=self._invoker.services,
+                                    cancel_event=self._cancel_event,
                                 )
-                                self._invoker.services.logger.error(error)
 
-                                # Send error event
-                                self._invoker.services.events.emit_invocation_error(
-                                    queue_batch_id=self._queue_item.session_id,
+                                # Invoke the node
+                                outputs = self._invocation.invoke_internal(
+                                    context=context, services=self._invoker.services
+                                )
+
+                                # Save outputs and history
+                                self._queue_item.session.complete(self._invocation.id, outputs)
+
+                                # Send complete event
+                                self._invoker.services.events.emit_invocation_complete(
+                                    queue_batch_id=self._queue_item.batch_id,
                                     queue_item_id=self._queue_item.item_id,
                                     queue_id=self._queue_item.queue_id,
                                     graph_execution_state_id=self._queue_item.session.id,
                                     node=self._invocation.model_dump(),
                                     source_node_id=source_invocation_id,
-                                    error_type=e.__class__.__name__,
-                                    error=error,
+                                    result=outputs.model_dump(),
                                 )
-                                pass
 
-                            # The session is complete if the all invocations are complete or there was an error
-                            if self._queue_item.session.is_complete() or cancel_event.is_set():
-                                # Send complete event
-                                self._invoker.services.events.emit_graph_execution_complete(
-                                    queue_batch_id=self._queue_item.batch_id,
-                                    queue_item_id=self._queue_item.item_id,
-                                    queue_id=self._queue_item.queue_id,
-                                    graph_execution_state_id=self._queue_item.session.id,
+                        except KeyboardInterrupt:
+                            # TODO(MM2): Create an event for this
+                            pass
+
+                        except CanceledException:
+                            # When the user cancels the graph, we first set the cancel event. The event is checked
+                            # between invocations, in this loop. Some invocations are long-running, and we need to
+                            # be able to cancel them mid-execution.
+                            #
+                            # For example, denoising is a long-running invocation with many steps. A step callback
+                            # is executed after each step. This step callback checks if the canceled event is set,
+                            # then raises a CanceledException to stop execution immediately.
+                            #
+                            # When we get a CanceledException, we don't need to do anything - just pass and let the
+                            # loop go to its next iteration, and the cancel event will be handled correctly.
+                            pass
+
+                        except Exception as e:
+                            error = traceback.format_exc()
+
+                            # Save error
+                            self._queue_item.session.set_node_error(self._invocation.id, error)
+                            self._invoker.services.logger.error(
+                                f"Error while invoking session {self._queue_item.session_id}, invocation {self._invocation.id} ({self._invocation.get_type()}):\n{e}"
+                            )
+                            self._invoker.services.logger.error(error)
+
+                            # Send error event
+                            self._invoker.services.events.emit_invocation_error(
+                                queue_batch_id=self._queue_item.session_id,
+                                queue_item_id=self._queue_item.item_id,
+                                queue_id=self._queue_item.queue_id,
+                                graph_execution_state_id=self._queue_item.session.id,
+                                node=self._invocation.model_dump(),
+                                source_node_id=source_invocation_id,
+                                error_type=e.__class__.__name__,
+                                error=error,
+                            )
+                            pass
+
+                        # The session is complete if the all invocations are complete or there was an error
+                        if self._queue_item.session.is_complete() or cancel_event.is_set():
+                            # Send complete event
+                            self._invoker.services.events.emit_graph_execution_complete(
+                                queue_batch_id=self._queue_item.batch_id,
+                                queue_item_id=self._queue_item.item_id,
+                                queue_id=self._queue_item.queue_id,
+                                graph_execution_state_id=self._queue_item.session.id,
+                            )
+                            # If we are profiling, stop the profiler and dump the profile & stats
+                            if self._profiler:
+                                profile_path = self._profiler.stop()
+                                stats_path = profile_path.with_suffix(".json")
+                                self._invoker.services.performance_statistics.dump_stats(
+                                    graph_execution_state_id=self._queue_item.session.id, output_path=stats_path
                                 )
-                                # If we are profiling, stop the profiler and dump the profile & stats
-                                if self._profiler:
-                                    profile_path = self._profiler.stop()
-                                    stats_path = profile_path.with_suffix(".json")
-                                    self._invoker.services.performance_statistics.dump_stats(
-                                        graph_execution_state_id=self._queue_item.session.id, output_path=stats_path
-                                    )
-                                # We'll get a GESStatsNotFoundError if we try to log stats for an untracked graph, but in the processor
-                                # we don't care about that - suppress the error.
-                                with suppress(GESStatsNotFoundError):
-                                    self._invoker.services.performance_statistics.log_stats(self._queue_item.session.id)
-                                    self._invoker.services.performance_statistics.reset_stats()
+                            # We'll get a GESStatsNotFoundError if we try to log stats for an untracked graph, but in the processor
+                            # we don't care about that - suppress the error.
+                            with suppress(GESStatsNotFoundError):
+                                self._invoker.services.performance_statistics.log_stats(self._queue_item.session.id)
+                                self._invoker.services.performance_statistics.reset_stats()
 
-                                # Set the invocation to None to prepare for the next session
-                                self._invocation = None
-                            else:
-                                # Prepare the next invocation
-                                self._invocation = self._queue_item.session.next()
-
-                        # The session is complete, immediately poll for next session
-                        self._queue_item = None
-                        poll_now_event.set()
+                            # Set the invocation to None to prepare for the next session
+                            self._invocation = None
+                        else:
+                            # Prepare the next invocation
+                            self._invocation = self._queue_item.session.next()
                     else:
                         # The queue was empty, wait for next polling interval or event to try again
                         self._invoker.services.logger.debug("Waiting for next polling interval or event")

invokeai/app/services/shared/sqlite/sqlite_util.py

@@ -10,6 +10,8 @@ from invokeai.app.services.shared.sqlite_migrator.migrations.migration_4 import
 from invokeai.app.services.shared.sqlite_migrator.migrations.migration_5 import build_migration_5
 from invokeai.app.services.shared.sqlite_migrator.migrations.migration_6 import build_migration_6
 from invokeai.app.services.shared.sqlite_migrator.migrations.migration_7 import build_migration_7
+from invokeai.app.services.shared.sqlite_migrator.migrations.migration_8 import build_migration_8
+from invokeai.app.services.shared.sqlite_migrator.migrations.migration_9 import build_migration_9
 from invokeai.app.services.shared.sqlite_migrator.sqlite_migrator_impl import SqliteMigrator
 
 
@@ -37,6 +39,8 @@ def init_db(config: InvokeAIAppConfig, logger: Logger, image_files: ImageFileSto
     migrator.register_migration(build_migration_5())
     migrator.register_migration(build_migration_6())
     migrator.register_migration(build_migration_7())
+    migrator.register_migration(build_migration_8(app_config=config))
+    migrator.register_migration(build_migration_9())
     migrator.run_migrations()
 
     return db

invokeai/app/services/shared/sqlite_migrator/migrations/migration_7.py

@@ -11,7 +11,7 @@ class Migration7Callback:
     def _drop_old_models_tables(self, cursor: sqlite3.Cursor) -> None:
         """Drops the old model_records, model_metadata, model_tags and tags tables."""
 
-        tables = ["model_records", "model_metadata", "model_tags", "tags"]
+        tables = ["model_config", "model_metadata", "model_tags", "tags"]
 
         for table in tables:
             cursor.execute(f"DROP TABLE IF EXISTS {table};")

invokeai/app/services/shared/sqlite_migrator/migrations/migration_8.py

@@ -0,0 +1,91 @@
+import sqlite3
+from pathlib import Path
+
+from invokeai.app.services.config.config_default import InvokeAIAppConfig
+from invokeai.app.services.shared.sqlite_migrator.sqlite_migrator_common import Migration
+
+
+class Migration8Callback:
+    def __init__(self, app_config: InvokeAIAppConfig) -> None:
+        self._app_config = app_config
+
+    def __call__(self, cursor: sqlite3.Cursor) -> None:
+        self._drop_model_config_table(cursor)
+        self._migrate_abs_models_to_rel(cursor)
+
+    def _drop_model_config_table(self, cursor: sqlite3.Cursor) -> None:
+        """Drops the old model_config table. This was missed in a previous migration."""
+
+        cursor.execute("DROP TABLE IF EXISTS model_config;")
+
+    def _migrate_abs_models_to_rel(self, cursor: sqlite3.Cursor) -> None:
+        """Check all model paths & legacy config paths to determine if they are inside Invoke-managed directories. If
+        they are, update the paths to be relative to the managed directories.
+
+        This migration is a no-op for normal users (their paths will already be relative), but is necessary for users
+        who have been testing the RCs with their live databases. The paths were made absolute in the initial RC, but this
+        change was reverted. To smooth over the revert for our tests, we can migrate the paths back to relative.
+        """
+
+        models_path = self._app_config.models_path
+        legacy_conf_path = self._app_config.legacy_conf_path
+        legacy_conf_dir = self._app_config.legacy_conf_dir
+
+        stmt = """---sql
+        SELECT
+            id,
+            path,
+            json_extract(config, '$.config_path') as config_path
+        FROM models;
+        """
+
+        all_models = cursor.execute(stmt).fetchall()
+
+        for model_id, model_path, model_config_path in all_models:
+            # If the model path is inside the models directory, update it to be relative to the models directory.
+            if Path(model_path).is_relative_to(models_path):
+                new_path = Path(model_path).relative_to(models_path)
+                cursor.execute(
+                    """--sql
+                    UPDATE models
+                    SET config = json_set(config, '$.path', ?)
+                    WHERE id = ?;
+                    """,
+                    (str(new_path), model_id),
+                )
+            # If the model has a legacy config path and it is inside the legacy conf directory, update it to be
+            # relative to the legacy conf directory. This also fixes up cases in which the config path was
+            # incorrectly relativized to the root directory. It will now be relativized to the legacy conf directory.
+            if model_config_path:
+                if Path(model_config_path).is_relative_to(legacy_conf_path):
+                    new_config_path = Path(model_config_path).relative_to(legacy_conf_path)
+                elif Path(model_config_path).is_relative_to(legacy_conf_dir):
+                    new_config_path = Path(*Path(model_config_path).parts[1:])
+                else:
+                    new_config_path = None
+                if new_config_path:
+                    cursor.execute(
+                        """--sql
+                        UPDATE models
+                        SET config = json_set(config, '$.config_path', ?)
+                        WHERE id = ?;
+                        """,
+                        (str(new_config_path), model_id),
+                    )
+
+
+def build_migration_8(app_config: InvokeAIAppConfig) -> Migration:
+    """
+    Build the migration from database version 7 to 8.
+
+    This migration does the following:
+    - Removes the `model_config` table.
+    - Migrates absolute model & legacy config paths to be relative to the models directory.
+    """
+    migration_8 = Migration(
+        from_version=7,
+        to_version=8,
+        callback=Migration8Callback(app_config),
+    )
+
+    return migration_8

invokeai/app/services/shared/sqlite_migrator/migrations/migration_9.py

@@ -0,0 +1,29 @@
+import sqlite3
+
+from invokeai.app.services.shared.sqlite_migrator.sqlite_migrator_common import Migration
+
+
+class Migration9Callback:
+    def __call__(self, cursor: sqlite3.Cursor) -> None:
+        self._empty_session_queue(cursor)
+
+    def _empty_session_queue(self, cursor: sqlite3.Cursor) -> None:
+        """Empties the session queue. This is done to prevent any lingering session queue items from causing pydantic errors due to changed schemas."""
+
+        cursor.execute("DELETE FROM session_queue;")
+
+
+def build_migration_9() -> Migration:
+    """
+    Build the migration from database version 8 to 9.
+
+    This migration does the following:
+    - Empties the session queue. This is done to prevent any lingering session queue items from causing pydantic errors due to changed schemas.
+    """
+    migration_9 = Migration(
+        from_version=8,
+        to_version=9,
+        callback=Migration9Callback(),
+    )
+
+    return migration_9

invokeai/app/services/shared/sqlite_migrator/sqlite_migrator_impl.py

@@ -1,4 +1,6 @@
 import sqlite3
+from contextlib import closing
+from datetime import datetime
 from pathlib import Path
 from typing import Optional
 
@@ -32,6 +34,7 @@ class SqliteMigrator:
         self._db = db
         self._logger = db.logger
         self._migration_set = MigrationSet()
+        self._backup_path: Optional[Path] = None
 
     def register_migration(self, migration: Migration) -> None:
         """Registers a migration."""
@@ -55,6 +58,18 @@ class SqliteMigrator:
                 return False
 
             self._logger.info("Database update needed")
+
+            # Make a backup of the db if it needs to be updated and is a file db
+            if self._db.db_path is not None:
+                timestamp = datetime.now().strftime("%Y%m%d-%H%M%S")
+                self._backup_path = self._db.db_path.parent / f"{self._db.db_path.stem}_backup_{timestamp}.db"
+                self._logger.info(f"Backing up database to {str(self._backup_path)}")
+                # Use SQLite to do the backup
+                with closing(sqlite3.connect(self._backup_path)) as backup_conn:
+                    self._db.conn.backup(backup_conn)
+            else:
+                self._logger.info("Using in-memory database, no backup needed")
+
             next_migration = self._migration_set.get(from_version=self._get_current_version(cursor))
             while next_migration is not None:
                 self._run_migration(next_migration)

invokeai/backend/image_util/__init__.py

@@ -2,7 +2,7 @@
 Initialization file for invokeai.backend.image_util methods.
 """
 
-from .patchmatch import PatchMatch  # noqa: F401
+from .infill_methods.patchmatch import PatchMatch  # noqa: F401
 from .pngwriter import PngWriter, PromptFormatter, retrieve_metadata, write_metadata  # noqa: F401
 from .seamless import configure_model_padding  # noqa: F401
 from .util import InitImageResizer, make_grid  # noqa: F401

invokeai/backend/image_util/infill_methods/lama.py

@@ -7,6 +7,7 @@ from PIL import Image
 
 import invokeai.backend.util.logging as logger
 from invokeai.app.services.config.config_default import get_config
+from invokeai.app.util.download_with_progress import download_with_progress_bar
 from invokeai.backend.util.devices import choose_torch_device
 
 
@@ -30,6 +31,14 @@ class LaMA:
     def __call__(self, input_image: Image.Image, *args: Any, **kwds: Any) -> Any:
         device = choose_torch_device()
         model_location = get_config().models_path / "core/misc/lama/lama.pt"
+
+        if not model_location.exists():
+            download_with_progress_bar(
+                name="LaMa Inpainting Model",
+                url="https://github.com/Sanster/models/releases/download/add_big_lama/big-lama.pt",
+                dest_path=model_location,
+            )
+
         model = load_jit_model(model_location, device)
 
         image = np.asarray(input_image.convert("RGB"))

invokeai/backend/image_util/infill_methods/mosaic.py

@@ -0,0 +1,60 @@
+from typing import Tuple
+
+import numpy as np
+from PIL import Image
+
+
+def infill_mosaic(
+    image: Image.Image,
+    tile_shape: Tuple[int, int] = (64, 64),
+    min_color: Tuple[int, int, int, int] = (0, 0, 0, 0),
+    max_color: Tuple[int, int, int, int] = (255, 255, 255, 0),
+) -> Image.Image:
+    """
+    image:PIL - A PIL Image
+    tile_shape: Tuple[int,int] - Tile width & Tile Height
+    min_color: Tuple[int,int,int] - RGB values for the lowest color to clip to (0-255)
+    max_color: Tuple[int,int,int] - RGB values for the highest color to clip to (0-255)
+    """
+
+    np_image = np.array(image)  # Convert image to np array
+    alpha = np_image[:, :, 3]  # Get the mask from the alpha channel of the image
+    non_transparent_pixels = np_image[alpha != 0, :3]  # List of non-transparent pixels
+
+    # Create color tiles to paste in the empty areas of the image
+    tile_width, tile_height = tile_shape
+
+    # Clip the range of colors in the image to a particular spectrum only
+    r_min, g_min, b_min, _ = min_color
+    r_max, g_max, b_max, _ = max_color
+    non_transparent_pixels[:, 0] = np.clip(non_transparent_pixels[:, 0], r_min, r_max)
+    non_transparent_pixels[:, 1] = np.clip(non_transparent_pixels[:, 1], g_min, g_max)
+    non_transparent_pixels[:, 2] = np.clip(non_transparent_pixels[:, 2], b_min, b_max)
+
+    tiles = []
+    for _ in range(256):
+        color = non_transparent_pixels[np.random.randint(len(non_transparent_pixels))]
+        tile = np.zeros((tile_height, tile_width, 3), dtype=np.uint8)
+        tile[:, :] = color
+        tiles.append(tile)
+
+    # Fill the transparent area with tiles
+    filled_image = np.zeros((image.height, image.width, 3), dtype=np.uint8)
+
+    for x in range(image.width):
+        for y in range(image.height):
+            tile = tiles[np.random.randint(len(tiles))]
+            try:
+                filled_image[
+                    y - (y % tile_height) : y - (y % tile_height) + tile_height,
+                    x - (x % tile_width) : x - (x % tile_width) + tile_width,
+                ] = tile
+            except ValueError:
+                # Need to handle edge cases - literally
+                pass
+
+    filled_image = Image.fromarray(filled_image)  # Convert the filled tiles image to PIL
+    image = Image.composite(
+        image, filled_image, image.split()[-1]
+    )  # Composite the original image on top of the filled tiles
+    return image

invokeai/backend/image_util/infill_methods/patchmatch.py

@@ -0,0 +1,67 @@
+"""
+This module defines a singleton object, "patchmatch" that
+wraps the actual patchmatch object. It respects the global
+"try_patchmatch" attribute, so that patchmatch loading can
+be suppressed or deferred
+"""
+
+import numpy as np
+from PIL import Image
+
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.config.config_default import get_config
+
+
+class PatchMatch:
+    """
+    Thin class wrapper around the patchmatch function.
+    """
+
+    patch_match = None
+    tried_load: bool = False
+
+    def __init__(self):
+        super().__init__()
+
+    @classmethod
+    def _load_patch_match(cls):
+        if cls.tried_load:
+            return
+        if get_config().patchmatch:
+            from patchmatch import patch_match as pm
+
+            if pm.patchmatch_available:
+                logger.info("Patchmatch initialized")
+                cls.patch_match = pm
+            else:
+                logger.info("Patchmatch not loaded (nonfatal)")
+        else:
+            logger.info("Patchmatch loading disabled")
+        cls.tried_load = True
+
+    @classmethod
+    def patchmatch_available(cls) -> bool:
+        cls._load_patch_match()
+        if not cls.patch_match:
+            return False
+        return cls.patch_match.patchmatch_available
+
+    @classmethod
+    def inpaint(cls, image: Image.Image) -> Image.Image:
+        if cls.patch_match is None or not cls.patchmatch_available():
+            return image
+
+        np_image = np.array(image)
+        mask = 255 - np_image[:, :, 3]
+        infilled = cls.patch_match.inpaint(np_image[:, :, :3], mask, patch_size=3)
+        return Image.fromarray(infilled, mode="RGB")
+
+
+def infill_patchmatch(image: Image.Image) -> Image.Image:
+    IS_PATCHMATCH_AVAILABLE = PatchMatch.patchmatch_available()
+
+    if not IS_PATCHMATCH_AVAILABLE:
+        logger.warning("PatchMatch is not available on this system")
+        return image
+
+    return PatchMatch.inpaint(image)

invokeai/backend/image_util/infill_methods/tile.ipynb

@@ -0,0 +1,95 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\"\"\"Smoke test for the tile infill\"\"\"\n",
+    "\n",
+    "from pathlib import Path\n",
+    "from typing import Optional\n",
+    "from PIL import Image\n",
+    "from invokeai.backend.image_util.infill_methods.tile import infill_tile\n",
+    "\n",
+    "images: list[tuple[str, Image.Image]] = []\n",
+    "\n",
+    "for i in sorted(Path(\"./test_images/\").glob(\"*.webp\")):\n",
+    "    images.append((i.name, Image.open(i)))\n",
+    "    images.append((i.name, Image.open(i).transpose(Image.FLIP_LEFT_RIGHT)))\n",
+    "    images.append((i.name, Image.open(i).transpose(Image.FLIP_TOP_BOTTOM)))\n",
+    "    images.append((i.name, Image.open(i).resize((512, 512))))\n",
+    "    images.append((i.name, Image.open(i).resize((1234, 461))))\n",
+    "\n",
+    "outputs: list[tuple[str, Image.Image, Image.Image, Optional[Image.Image]]] = []\n",
+    "\n",
+    "for name, image in images:\n",
+    "    try:\n",
+    "        output = infill_tile(image, seed=0, tile_size=32)\n",
+    "        outputs.append((name, image, output.infilled, output.tile_image))\n",
+    "    except ValueError as e:\n",
+    "        print(f\"Skipping image {name}: {e}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Display the images in jupyter notebook\n",
+    "import matplotlib.pyplot as plt\n",
+    "from PIL import ImageOps\n",
+    "\n",
+    "fig, axes = plt.subplots(len(outputs), 3, figsize=(10, 3 * len(outputs)))\n",
+    "plt.subplots_adjust(hspace=0)\n",
+    "\n",
+    "for i, (name, original, infilled, tile_image) in enumerate(outputs):\n",
+    "    # Add a border to each image, helps to see the edges\n",
+    "    size = original.size\n",
+    "    original = ImageOps.expand(original, border=5, fill=\"red\")\n",
+    "    filled = ImageOps.expand(infilled, border=5, fill=\"red\")\n",
+    "    if tile_image:\n",
+    "        tile_image = ImageOps.expand(tile_image, border=5, fill=\"red\")\n",
+    "\n",
+    "    axes[i, 0].imshow(original)\n",
+    "    axes[i, 0].axis(\"off\")\n",
+    "    axes[i, 0].set_title(f\"Original ({name} - {size})\")\n",
+    "\n",
+    "    if tile_image:\n",
+    "        axes[i, 1].imshow(tile_image)\n",
+    "        axes[i, 1].axis(\"off\")\n",
+    "        axes[i, 1].set_title(\"Tile Image\")\n",
+    "    else:\n",
+    "        axes[i, 1].axis(\"off\")\n",
+    "        axes[i, 1].set_title(\"NO TILES GENERATED (NO TRANSPARENCY)\")\n",
+    "\n",
+    "    axes[i, 2].imshow(filled)\n",
+    "    axes[i, 2].axis(\"off\")\n",
+    "    axes[i, 2].set_title(\"Filled\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".invokeai",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

invokeai/backend/image_util/infill_methods/tile.py

@@ -0,0 +1,122 @@
+from dataclasses import dataclass
+from typing import Optional
+
+import numpy as np
+from PIL import Image
+
+
+def create_tile_pool(img_array: np.ndarray, tile_size: tuple[int, int]) -> list[np.ndarray]:
+    """
+    Create a pool of tiles from non-transparent areas of the image by systematically walking through the image.
+
+    Args:
+        img_array: numpy array of the image.
+        tile_size: tuple (tile_width, tile_height) specifying the size of each tile.
+
+    Returns:
+        A list of numpy arrays, each representing a tile.
+    """
+    tiles: list[np.ndarray] = []
+    rows, cols = img_array.shape[:2]
+    tile_width, tile_height = tile_size
+
+    for y in range(0, rows - tile_height + 1, tile_height):
+        for x in range(0, cols - tile_width + 1, tile_width):
+            tile = img_array[y : y + tile_height, x : x + tile_width]
+            # Check if the image has an alpha channel and the tile is completely opaque
+            if img_array.shape[2] == 4 and np.all(tile[:, :, 3] == 255):
+                tiles.append(tile)
+            elif img_array.shape[2] == 3:  # If no alpha channel, append the tile
+                tiles.append(tile)
+
+    if not tiles:
+        raise ValueError(
+            "Not enough opaque pixels to generate any tiles. Use a smaller tile size or a different image."
+        )
+
+    return tiles
+
+
+def create_filled_image(
+    img_array: np.ndarray, tile_pool: list[np.ndarray], tile_size: tuple[int, int], seed: int
+) -> np.ndarray:
+    """
+    Create an image of the same dimensions as the original, filled entirely with tiles from the pool.
+
+    Args:
+        img_array: numpy array of the original image.
+        tile_pool: A list of numpy arrays, each representing a tile.
+        tile_size: tuple (tile_width, tile_height) specifying the size of each tile.
+
+    Returns:
+        A numpy array representing the filled image.
+    """
+
+    rows, cols, _ = img_array.shape
+    tile_width, tile_height = tile_size
+
+    # Prep an empty RGB image
+    filled_img_array = np.zeros((rows, cols, 3), dtype=img_array.dtype)
+
+    # Make the random tile selection reproducible
+    rng = np.random.default_rng(seed)
+
+    for y in range(0, rows, tile_height):
+        for x in range(0, cols, tile_width):
+            # Pick a random tile from the pool
+            tile = tile_pool[rng.integers(len(tile_pool))]
+
+            # Calculate the space available (may be less than tile size near the edges)
+            space_y = min(tile_height, rows - y)
+            space_x = min(tile_width, cols - x)
+
+            # Crop the tile if necessary to fit into the available space
+            cropped_tile = tile[:space_y, :space_x, :3]
+
+            # Fill the available space with the (possibly cropped) tile
+            filled_img_array[y : y + space_y, x : x + space_x, :3] = cropped_tile
+
+    return filled_img_array
+
+
+@dataclass
+class InfillTileOutput:
+    infilled: Image.Image
+    tile_image: Optional[Image.Image] = None
+
+
+def infill_tile(image_to_infill: Image.Image, seed: int, tile_size: int) -> InfillTileOutput:
+    """Infills an image with random tiles from the image itself.
+
+    If the image is not an RGBA image, it is returned untouched.
+
+    Args:
+        image: The image to infill.
+        tile_size: The size of the tiles to use for infilling.
+
+    Raises:
+        ValueError: If there are not enough opaque pixels to generate any tiles.
+    """
+
+    if image_to_infill.mode != "RGBA":
+        return InfillTileOutput(infilled=image_to_infill)
+
+    # Internally, we want a tuple of (tile_width, tile_height). In the future, the tile size can be any rectangle.
+    _tile_size = (tile_size, tile_size)
+    np_image = np.array(image_to_infill, dtype=np.uint8)
+
+    # Create the pool of tiles that we will use to infill
+    tile_pool = create_tile_pool(np_image, _tile_size)
+
+    # Create an image from the tiles, same size as the original
+    tile_np_image = create_filled_image(np_image, tile_pool, _tile_size, seed)
+
+    # Paste the OG image over the tile image, effectively infilling the area
+    tile_image = Image.fromarray(tile_np_image, "RGB")
+    infilled = tile_image.copy()
+    infilled.paste(image_to_infill, (0, 0), image_to_infill.split()[-1])
+
+    # I think we want this to be "RGBA"?
+    infilled.convert("RGBA")
+
+    return InfillTileOutput(infilled=infilled, tile_image=tile_image)

invokeai/backend/image_util/patchmatch.py

@@ -1,49 +0,0 @@
-"""
-This module defines a singleton object, "patchmatch" that
-wraps the actual patchmatch object. It respects the global
-"try_patchmatch" attribute, so that patchmatch loading can
-be suppressed or deferred
-"""
-
-import numpy as np
-
-import invokeai.backend.util.logging as logger
-from invokeai.app.services.config.config_default import get_config
-
-
-class PatchMatch:
-    """
-    Thin class wrapper around the patchmatch function.
-    """
-
-    patch_match = None
-    tried_load: bool = False
-
-    def __init__(self):
-        super().__init__()
-
-    @classmethod
-    def _load_patch_match(self):
-        if self.tried_load:
-            return
-        if get_config().patchmatch:
-            from patchmatch import patch_match as pm
-
-            if pm.patchmatch_available:
-                logger.info("Patchmatch initialized")
-            else:
-                logger.info("Patchmatch not loaded (nonfatal)")
-            self.patch_match = pm
-        else:
-            logger.info("Patchmatch loading disabled")
-        self.tried_load = True
-
-    @classmethod
-    def patchmatch_available(self) -> bool:
-        self._load_patch_match()
-        return self.patch_match and self.patch_match.patchmatch_available
-
-    @classmethod
-    def inpaint(self, *args, **kwargs) -> np.ndarray:
-        if self.patchmatch_available():
-            return self.patch_match.inpaint(*args, **kwargs)

invokeai/backend/ip_adapter/ip_adapter.py

@@ -1,8 +1,11 @@
 # copied from https://github.com/tencent-ailab/IP-Adapter (Apache License 2.0)
 #   and modified as needed
 
-from typing import Optional, Union
+import pathlib
+from typing import List, Optional, TypedDict, Union
 
+import safetensors
+import safetensors.torch
 import torch
 from PIL import Image
 from transformers import CLIPImageProcessor, CLIPVisionModelWithProjection
@@ -13,10 +16,17 @@ from ..raw_model import RawModel
 from .resampler import Resampler
 
 
+class IPAdapterStateDict(TypedDict):
+    ip_adapter: dict[str, torch.Tensor]
+    image_proj: dict[str, torch.Tensor]
+
+
 class ImageProjModel(torch.nn.Module):
     """Image Projection Model"""
 
-    def __init__(self, cross_attention_dim=1024, clip_embeddings_dim=1024, clip_extra_context_tokens=4):
+    def __init__(
+        self, cross_attention_dim: int = 1024, clip_embeddings_dim: int = 1024, clip_extra_context_tokens: int = 4
+    ):
         super().__init__()
 
         self.cross_attention_dim = cross_attention_dim
@@ -25,7 +35,7 @@ class ImageProjModel(torch.nn.Module):
         self.norm = torch.nn.LayerNorm(cross_attention_dim)
 
     @classmethod
-    def from_state_dict(cls, state_dict: dict[torch.Tensor], clip_extra_context_tokens=4):
+    def from_state_dict(cls, state_dict: dict[str, torch.Tensor], clip_extra_context_tokens: int = 4):
         """Initialize an ImageProjModel from a state_dict.
 
         The cross_attention_dim and clip_embeddings_dim are inferred from the shape of the tensors in the state_dict.
@@ -45,7 +55,7 @@ class ImageProjModel(torch.nn.Module):
         model.load_state_dict(state_dict)
         return model
 
-    def forward(self, image_embeds):
+    def forward(self, image_embeds: torch.Tensor):
         embeds = image_embeds
         clip_extra_context_tokens = self.proj(embeds).reshape(
             -1, self.clip_extra_context_tokens, self.cross_attention_dim
@@ -57,7 +67,7 @@ class ImageProjModel(torch.nn.Module):
 class MLPProjModel(torch.nn.Module):
     """SD model with image prompt"""
 
-    def __init__(self, cross_attention_dim=1024, clip_embeddings_dim=1024):
+    def __init__(self, cross_attention_dim: int = 1024, clip_embeddings_dim: int = 1024):
         super().__init__()
 
         self.proj = torch.nn.Sequential(
@@ -68,7 +78,7 @@ class MLPProjModel(torch.nn.Module):
         )
 
     @classmethod
-    def from_state_dict(cls, state_dict: dict[torch.Tensor]):
+    def from_state_dict(cls, state_dict: dict[str, torch.Tensor]):
         """Initialize an MLPProjModel from a state_dict.
 
         The cross_attention_dim and clip_embeddings_dim are inferred from the shape of the tensors in the state_dict.
@@ -87,7 +97,7 @@ class MLPProjModel(torch.nn.Module):
         model.load_state_dict(state_dict)
         return model
 
-    def forward(self, image_embeds):
+    def forward(self, image_embeds: torch.Tensor):
         clip_extra_context_tokens = self.proj(image_embeds)
         return clip_extra_context_tokens
 
@@ -97,7 +107,7 @@ class IPAdapter(RawModel):
 
     def __init__(
         self,
-        state_dict: dict[str, torch.Tensor],
+        state_dict: IPAdapterStateDict,
         device: torch.device,
         dtype: torch.dtype = torch.float16,
         num_tokens: int = 4,
@@ -129,24 +139,27 @@ class IPAdapter(RawModel):
 
         return calc_model_size_by_data(self._image_proj_model) + calc_model_size_by_data(self.attn_weights)
 
-    def _init_image_proj_model(self, state_dict):
+    def _init_image_proj_model(
+        self, state_dict: dict[str, torch.Tensor]
+    ) -> Union[ImageProjModel, Resampler, MLPProjModel]:
         return ImageProjModel.from_state_dict(state_dict, self._num_tokens).to(self.device, dtype=self.dtype)
 
     @torch.inference_mode()
-    def get_image_embeds(self, pil_image, image_encoder: CLIPVisionModelWithProjection):
-        if isinstance(pil_image, Image.Image):
-            pil_image = [pil_image]
+    def get_image_embeds(self, pil_image: List[Image.Image], image_encoder: CLIPVisionModelWithProjection):
         clip_image = self._clip_image_processor(images=pil_image, return_tensors="pt").pixel_values
         clip_image_embeds = image_encoder(clip_image.to(self.device, dtype=self.dtype)).image_embeds
-        image_prompt_embeds = self._image_proj_model(clip_image_embeds)
-        uncond_image_prompt_embeds = self._image_proj_model(torch.zeros_like(clip_image_embeds))
-        return image_prompt_embeds, uncond_image_prompt_embeds
+        try:
+            image_prompt_embeds = self._image_proj_model(clip_image_embeds)
+            uncond_image_prompt_embeds = self._image_proj_model(torch.zeros_like(clip_image_embeds))
+            return image_prompt_embeds, uncond_image_prompt_embeds
+        except RuntimeError as e:
+            raise RuntimeError("Selected CLIP Vision Model is incompatible with the current IP Adapter") from e
 
 
 class IPAdapterPlus(IPAdapter):
     """IP-Adapter with fine-grained features"""
 
-    def _init_image_proj_model(self, state_dict):
+    def _init_image_proj_model(self, state_dict: dict[str, torch.Tensor]) -> Union[Resampler, MLPProjModel]:
         return Resampler.from_state_dict(
             state_dict=state_dict,
             depth=4,
@@ -157,31 +170,32 @@ class IPAdapterPlus(IPAdapter):
         ).to(self.device, dtype=self.dtype)
 
     @torch.inference_mode()
-    def get_image_embeds(self, pil_image, image_encoder: CLIPVisionModelWithProjection):
-        if isinstance(pil_image, Image.Image):
-            pil_image = [pil_image]
+    def get_image_embeds(self, pil_image: List[Image.Image], image_encoder: CLIPVisionModelWithProjection):
         clip_image = self._clip_image_processor(images=pil_image, return_tensors="pt").pixel_values
         clip_image = clip_image.to(self.device, dtype=self.dtype)
         clip_image_embeds = image_encoder(clip_image, output_hidden_states=True).hidden_states[-2]
-        image_prompt_embeds = self._image_proj_model(clip_image_embeds)
         uncond_clip_image_embeds = image_encoder(torch.zeros_like(clip_image), output_hidden_states=True).hidden_states[
             -2
         ]
-        uncond_image_prompt_embeds = self._image_proj_model(uncond_clip_image_embeds)
-        return image_prompt_embeds, uncond_image_prompt_embeds
+        try:
+            image_prompt_embeds = self._image_proj_model(clip_image_embeds)
+            uncond_image_prompt_embeds = self._image_proj_model(uncond_clip_image_embeds)
+            return image_prompt_embeds, uncond_image_prompt_embeds
+        except RuntimeError as e:
+            raise RuntimeError("Selected CLIP Vision Model is incompatible with the current IP Adapter") from e
 
 
 class IPAdapterFull(IPAdapterPlus):
     """IP-Adapter Plus with full features."""
 
-    def _init_image_proj_model(self, state_dict: dict[torch.Tensor]):
+    def _init_image_proj_model(self, state_dict: dict[str, torch.Tensor]):
         return MLPProjModel.from_state_dict(state_dict).to(self.device, dtype=self.dtype)
 
 
 class IPAdapterPlusXL(IPAdapterPlus):
     """IP-Adapter Plus for SDXL."""
 
-    def _init_image_proj_model(self, state_dict):
+    def _init_image_proj_model(self, state_dict: dict[str, torch.Tensor]):
         return Resampler.from_state_dict(
             state_dict=state_dict,
             depth=4,
@@ -192,24 +206,48 @@ class IPAdapterPlusXL(IPAdapterPlus):
         ).to(self.device, dtype=self.dtype)
 
 
-def build_ip_adapter(
-    ip_adapter_ckpt_path: str, device: torch.device, dtype: torch.dtype = torch.float16
-) -> Union[IPAdapter, IPAdapterPlus]:
-    state_dict = torch.load(ip_adapter_ckpt_path, map_location="cpu")
+def load_ip_adapter_tensors(ip_adapter_ckpt_path: pathlib.Path, device: str) -> IPAdapterStateDict:
+    state_dict: IPAdapterStateDict = {"ip_adapter": {}, "image_proj": {}}
 
-    if "proj.weight" in state_dict["image_proj"]:  # IPAdapter (with ImageProjModel).
+    if ip_adapter_ckpt_path.suffix == ".safetensors":
+        model = safetensors.torch.load_file(ip_adapter_ckpt_path, device=device)
+        for key in model.keys():
+            if key.startswith("image_proj."):
+                state_dict["image_proj"][key.replace("image_proj.", "")] = model[key]
+            elif key.startswith("ip_adapter."):
+                state_dict["ip_adapter"][key.replace("ip_adapter.", "")] = model[key]
+            else:
+                raise RuntimeError(f"Encountered unexpected IP Adapter state dict key: '{key}'.")
+    else:
+        ip_adapter_diffusers_checkpoint_path = ip_adapter_ckpt_path / "ip_adapter.bin"
+        state_dict = torch.load(ip_adapter_diffusers_checkpoint_path, map_location="cpu")
+
+    return state_dict
+
+
+def build_ip_adapter(
+    ip_adapter_ckpt_path: pathlib.Path, device: torch.device, dtype: torch.dtype = torch.float16
+) -> Union[IPAdapter, IPAdapterPlus, IPAdapterPlusXL, IPAdapterPlus]:
+    state_dict = load_ip_adapter_tensors(ip_adapter_ckpt_path, device.type)
+
+    # IPAdapter (with ImageProjModel)
+    if "proj.weight" in state_dict["image_proj"]:
         return IPAdapter(state_dict, device=device, dtype=dtype)
-    elif "proj_in.weight" in state_dict["image_proj"]:  # IPAdaterPlus or IPAdapterPlusXL (with Resampler).
+
+    # IPAdaterPlus or IPAdapterPlusXL (with Resampler)
+    elif "proj_in.weight" in state_dict["image_proj"]:
         cross_attention_dim = state_dict["ip_adapter"]["1.to_k_ip.weight"].shape[-1]
         if cross_attention_dim == 768:
-            # SD1 IP-Adapter Plus
-            return IPAdapterPlus(state_dict, device=device, dtype=dtype)
+            return IPAdapterPlus(state_dict, device=device, dtype=dtype)  # SD1 IP-Adapter Plus
         elif cross_attention_dim == 2048:
-            # SDXL IP-Adapter Plus
-            return IPAdapterPlusXL(state_dict, device=device, dtype=dtype)
+            return IPAdapterPlusXL(state_dict, device=device, dtype=dtype)  # SDXL IP-Adapter Plus
         else:
             raise Exception(f"Unsupported IP-Adapter Plus cross-attention dimension: {cross_attention_dim}.")
-    elif "proj.0.weight" in state_dict["image_proj"]:  # IPAdapterFull (with MLPProjModel).
+
+    # IPAdapterFull (with MLPProjModel)
+    elif "proj.0.weight" in state_dict["image_proj"]:
         return IPAdapterFull(state_dict, device=device, dtype=dtype)
+
+    # Unrecognized IP Adapter Architectures
     else:
         raise ValueError(f"'{ip_adapter_ckpt_path}' has an unrecognized IP-Adapter model architecture.")

invokeai/backend/ip_adapter/resampler.py

@@ -9,8 +9,8 @@ import torch.nn as nn
 
 
 # FFN
-def FeedForward(dim, mult=4):
-    inner_dim = int(dim * mult)
+def FeedForward(dim: int, mult: int = 4):
+    inner_dim = dim * mult
     return nn.Sequential(
         nn.LayerNorm(dim),
         nn.Linear(dim, inner_dim, bias=False),
@@ -19,8 +19,8 @@ def FeedForward(dim, mult=4):
     )
 
 
-def reshape_tensor(x, heads):
-    bs, length, width = x.shape
+def reshape_tensor(x: torch.Tensor, heads: int):
+    bs, length, _ = x.shape
     # (bs, length, width) --> (bs, length, n_heads, dim_per_head)
     x = x.view(bs, length, heads, -1)
     # (bs, length, n_heads, dim_per_head) --> (bs, n_heads, length, dim_per_head)
@@ -31,7 +31,7 @@ def reshape_tensor(x, heads):
 
 
 class PerceiverAttention(nn.Module):
-    def __init__(self, *, dim, dim_head=64, heads=8):
+    def __init__(self, *, dim: int, dim_head: int = 64, heads: int = 8):
         super().__init__()
         self.scale = dim_head**-0.5
         self.dim_head = dim_head
@@ -45,7 +45,7 @@ class PerceiverAttention(nn.Module):
         self.to_kv = nn.Linear(dim, inner_dim * 2, bias=False)
         self.to_out = nn.Linear(inner_dim, dim, bias=False)
 
-    def forward(self, x, latents):
+    def forward(self, x: torch.Tensor, latents: torch.Tensor):
         """
         Args:
             x (torch.Tensor): image features
@@ -80,14 +80,14 @@ class PerceiverAttention(nn.Module):
 class Resampler(nn.Module):
     def __init__(
         self,
-        dim=1024,
-        depth=8,
-        dim_head=64,
-        heads=16,
-        num_queries=8,
-        embedding_dim=768,
-        output_dim=1024,
-        ff_mult=4,
+        dim: int = 1024,
+        depth: int = 8,
+        dim_head: int = 64,
+        heads: int = 16,
+        num_queries: int = 8,
+        embedding_dim: int = 768,
+        output_dim: int = 1024,
+        ff_mult: int = 4,
     ):
         super().__init__()
 
@@ -110,7 +110,15 @@ class Resampler(nn.Module):
             )
 
     @classmethod
-    def from_state_dict(cls, state_dict: dict[torch.Tensor], depth=8, dim_head=64, heads=16, num_queries=8, ff_mult=4):
+    def from_state_dict(
+        cls,
+        state_dict: dict[str, torch.Tensor],
+        depth: int = 8,
+        dim_head: int = 64,
+        heads: int = 16,
+        num_queries: int = 8,
+        ff_mult: int = 4,
+    ):
         """A convenience function that initializes a Resampler from a state_dict.
 
         Some of the shape parameters are inferred from the state_dict (e.g. dim, embedding_dim, etc.). At the time of
@@ -145,7 +153,7 @@ class Resampler(nn.Module):
         model.load_state_dict(state_dict)
         return model
 
-    def forward(self, x):
+    def forward(self, x: torch.Tensor):
         latents = self.latents.repeat(x.size(0), 1, 1)
 
         x = self.proj_in(x)

invokeai/backend/model_manager/__init__.py

@@ -33,42 +33,3 @@ __all__ = [
     "SchedulerPredictionType",
     "SubModelType",
 ]
-
-########## to help populate the openapi_schema with format enums for each config ###########
-# This code is no longer necessary?
-# leave it here just in case
-#
-# import inspect
-# from enum import Enum
-# from typing import Any, Iterable, Dict, get_args, Set
-# def _expand(something: Any) -> Iterable[type]:
-#     if isinstance(something, type):
-#         yield something
-#     else:
-#         for x in get_args(something):
-#             for y in _expand(x):
-#                 yield y
-
-# def _find_format(cls: type) -> Iterable[Enum]:
-#     if hasattr(inspect, "get_annotations"):
-#         fields = inspect.get_annotations(cls)
-#     else:
-#         fields = cls.__annotations__
-#     if "format" in fields:
-#         for x in get_args(fields["format"]):
-#             yield x
-#     for parent_class in cls.__bases__:
-#         for x in _find_format(parent_class):
-#             yield x
-#     return None
-
-# def get_model_config_formats() -> Dict[str, Set[Enum]]:
-#     result: Dict[str, Set[Enum]] = {}
-#     for model_config in _expand(AnyModelConfig):
-#         for field in _find_format(model_config):
-#             if field is None:
-#                 continue
-#             if not result.get(model_config.__qualname__):
-#                 result[model_config.__qualname__] = set()
-#             result[model_config.__qualname__].add(field)
-#     return result

invokeai/backend/model_manager/config.py

@@ -323,10 +323,13 @@ class MainDiffusersConfig(DiffusersConfigBase, MainConfigBase):
         return Tag(f"{ModelType.Main.value}.{ModelFormat.Diffusers.value}")
 
 
-class IPAdapterConfig(ModelConfigBase):
-    """Model config for IP Adaptor format models."""
-
+class IPAdapterBaseConfig(ModelConfigBase):
     type: Literal[ModelType.IPAdapter] = ModelType.IPAdapter
+
+
+class IPAdapterInvokeAIConfig(IPAdapterBaseConfig):
+    """Model config for IP Adapter diffusers format models."""
+
     image_encoder_model_id: str
     format: Literal[ModelFormat.InvokeAI]
 
@@ -335,6 +338,16 @@ class IPAdapterConfig(ModelConfigBase):
         return Tag(f"{ModelType.IPAdapter.value}.{ModelFormat.InvokeAI.value}")
 
 
+class IPAdapterCheckpointConfig(IPAdapterBaseConfig):
+    """Model config for IP Adapter checkpoint format models."""
+
+    format: Literal[ModelFormat.Checkpoint]
+
+    @staticmethod
+    def get_tag() -> Tag:
+        return Tag(f"{ModelType.IPAdapter.value}.{ModelFormat.Checkpoint.value}")
+
+
 class CLIPVisionDiffusersConfig(DiffusersConfigBase):
     """Model config for CLIPVision."""
 
@@ -390,7 +403,8 @@ AnyModelConfig = Annotated[
         Annotated[LoRADiffusersConfig, LoRADiffusersConfig.get_tag()],
         Annotated[TextualInversionFileConfig, TextualInversionFileConfig.get_tag()],
         Annotated[TextualInversionFolderConfig, TextualInversionFolderConfig.get_tag()],
-        Annotated[IPAdapterConfig, IPAdapterConfig.get_tag()],
+        Annotated[IPAdapterInvokeAIConfig, IPAdapterInvokeAIConfig.get_tag()],
+        Annotated[IPAdapterCheckpointConfig, IPAdapterCheckpointConfig.get_tag()],
         Annotated[T2IAdapterConfig, T2IAdapterConfig.get_tag()],
         Annotated[CLIPVisionDiffusersConfig, CLIPVisionDiffusersConfig.get_tag()],
     ],

invokeai/backend/model_manager/convert_ckpt_to_diffusers.py

@@ -3,10 +3,10 @@
 """Conversion script for the Stable Diffusion checkpoints."""
 
 from pathlib import Path
-from typing import Dict
+from typing import Optional
 
 import torch
-from diffusers import AutoencoderKL
+from diffusers.models.autoencoders.autoencoder_kl import AutoencoderKL
 from diffusers.pipelines.stable_diffusion.convert_from_ckpt import (
     convert_ldm_vae_checkpoint,
     create_vae_diffusers_config,
@@ -15,11 +15,14 @@ from diffusers.pipelines.stable_diffusion.convert_from_ckpt import (
 )
 from omegaconf import DictConfig
 
+from . import AnyModel
+
 
 def convert_ldm_vae_to_diffusers(
-    checkpoint: Dict[str, torch.Tensor],
+    checkpoint: torch.Tensor | dict[str, torch.Tensor],
     vae_config: DictConfig,
     image_size: int,
+    dump_path: Optional[Path] = None,
     precision: torch.dtype = torch.float16,
 ) -> AutoencoderKL:
     """Convert a checkpoint-style VAE into a Diffusers VAE"""
@@ -28,16 +31,21 @@ def convert_ldm_vae_to_diffusers(
 
     vae = AutoencoderKL(**vae_config)
     vae.load_state_dict(converted_vae_checkpoint)
-    return vae.to(precision)
+    vae.to(precision)
+
+    if dump_path:
+        vae.save_pretrained(dump_path, safe_serialization=True)
+
+    return vae
 
 
 def convert_ckpt_to_diffusers(
     checkpoint_path: str | Path,
-    dump_path: str | Path,
+    dump_path: Optional[str | Path] = None,
     precision: torch.dtype = torch.float16,
     use_safetensors: bool = True,
     **kwargs,
-):
+) -> AnyModel:
     """
     Takes all the arguments of download_from_original_stable_diffusion_ckpt(),
     and in addition a path-like object indicating the location of the desired diffusers
@@ -47,18 +55,20 @@ def convert_ckpt_to_diffusers(
     pipe = pipe.to(precision)
 
     # TO DO: save correct repo variant
-    pipe.save_pretrained(
-        dump_path,
-        safe_serialization=use_safetensors,
-    )
+    if dump_path:
+        pipe.save_pretrained(
+            dump_path,
+            safe_serialization=use_safetensors,
+        )
+    return pipe
 
 
 def convert_controlnet_to_diffusers(
     checkpoint_path: Path,
-    dump_path: Path,
+    dump_path: Optional[Path] = None,
     precision: torch.dtype = torch.float16,
     **kwargs,
-):
+) -> AnyModel:
     """
     Takes all the arguments of download_controlnet_from_original_ckpt(),
     and in addition a path-like object indicating the location of the desired diffusers
@@ -68,4 +78,6 @@ def convert_controlnet_to_diffusers(
     pipe = pipe.to(precision)
 
     # TO DO: save correct repo variant
-    pipe.save_pretrained(dump_path, safe_serialization=True)
+    if dump_path:
+        pipe.save_pretrained(dump_path, safe_serialization=True)
+    return pipe

invokeai/backend/model_manager/load/convert_cache/convert_cache_default.py

@@ -19,11 +19,20 @@ class ModelConvertCache(ModelConvertCacheBase):
         self._cache_path = cache_path
         self._max_size = max_size
 
+        # adjust cache size at startup in case it has been changed
+        if self._cache_path.exists():
+            self.make_room(0.0)
+
     @property
     def max_size(self) -> float:
         """Return the maximum size of this cache directory (GB)."""
         return self._max_size
 
+    @max_size.setter
+    def max_size(self, value: float) -> None:
+        """Set the maximum size of this cache directory (GB)."""
+        self._max_size = value
+
     def cache_path(self, key: str) -> Path:
         """Return the path for a model with the indicated key."""
         return self._cache_path / key

invokeai/backend/model_manager/load/load_base.py

@@ -83,3 +83,15 @@ class ModelLoaderBase(ABC):
     ) -> int:
         """Return size in bytes of the model, calculated before loading."""
         pass
+
+    @property
+    @abstractmethod
+    def convert_cache(self) -> ModelConvertCacheBase:
+        """Return the convert cache associated with this loader."""
+        pass
+
+    @property
+    @abstractmethod
+    def ram_cache(self) -> ModelCacheBase[AnyModel]:
+        """Return the ram cache associated with this loader."""
+        pass

invokeai/backend/model_manager/load/load_default.py

@@ -3,14 +3,13 @@
 
 from logging import Logger
 from pathlib import Path
-from typing import Optional, Tuple
+from typing import Optional
 
 from invokeai.app.services.config import InvokeAIAppConfig
 from invokeai.backend.model_manager import (
     AnyModel,
     AnyModelConfig,
     InvalidModelConfigException,
-    ModelRepoVariant,
     SubModelType,
 )
 from invokeai.backend.model_manager.config import DiffusersConfigBase, ModelType
@@ -54,51 +53,43 @@ class ModelLoader(ModelLoaderBase):
         if model_config.type is ModelType.Main and not submodel_type:
             raise InvalidModelConfigException("submodel_type is required when loading a main model")
 
-        model_path, model_config, submodel_type = self._get_model_path(model_config, submodel_type)
+        model_path = self._get_model_path(model_config)
 
         if not model_path.exists():
             raise InvalidModelConfigException(f"Files for model '{model_config.name}' not found at {model_path}")
 
-        model_path = self._convert_if_needed(model_config, model_path, submodel_type)
-        locker = self._load_if_needed(model_config, model_path, submodel_type)
+        with skip_torch_weight_init():
+            locker = self._convert_and_load(model_config, model_path, submodel_type)
         return LoadedModel(config=model_config, _locker=locker)
 
-    def _get_model_path(
-        self, config: AnyModelConfig, submodel_type: Optional[SubModelType] = None
-    ) -> Tuple[Path, AnyModelConfig, Optional[SubModelType]]:
+    @property
+    def convert_cache(self) -> ModelConvertCacheBase:
+        """Return the convert cache associated with this loader."""
+        return self._convert_cache
+
+    @property
+    def ram_cache(self) -> ModelCacheBase[AnyModel]:
+        """Return the ram cache associated with this loader."""
+        return self._ram_cache
+
+    def _get_model_path(self, config: AnyModelConfig) -> Path:
         model_base = self._app_config.models_path
-        result = (model_base / config.path).resolve(), config, submodel_type
-        return result
+        return (model_base / config.path).resolve()
 
-    def _convert_if_needed(
-        self, config: AnyModelConfig, model_path: Path, submodel_type: Optional[SubModelType] = None
-    ) -> Path:
-        cache_path: Path = self._convert_cache.cache_path(config.key)
-
-        if not self._needs_conversion(config, model_path, cache_path):
-            return cache_path if cache_path.exists() else model_path
-
-        self._convert_cache.make_room(self.get_size_fs(config, model_path, submodel_type))
-        return self._convert_model(config, model_path, cache_path)
-
-    def _needs_conversion(self, config: AnyModelConfig, model_path: Path, dest_path: Path) -> bool:
-        return False
-
-    def _load_if_needed(
+    def _convert_and_load(
         self, config: AnyModelConfig, model_path: Path, submodel_type: Optional[SubModelType] = None
     ) -> ModelLockerBase:
-        # TO DO: This is not thread safe!
         try:
             return self._ram_cache.get(config.key, submodel_type)
         except IndexError:
             pass
 
-        model_variant = getattr(config, "repo_variant", None)
-        self._ram_cache.make_room(self.get_size_fs(config, model_path, submodel_type))
-
-        # This is where the model is actually loaded!
-        with skip_torch_weight_init():
-            loaded_model = self._load_model(model_path, model_variant=model_variant, submodel_type=submodel_type)
+        cache_path: Path = self._convert_cache.cache_path(config.key)
+        if self._needs_conversion(config, model_path, cache_path):
+            loaded_model = self._do_convert(config, model_path, cache_path, submodel_type)
+        else:
+            config.path = str(cache_path) if cache_path.exists() else str(self._get_model_path(config))
+            loaded_model = self._load_model(config, submodel_type)
 
         self._ram_cache.put(
             config.key,
@@ -123,15 +114,34 @@ class ModelLoader(ModelLoaderBase):
             variant=config.repo_variant if isinstance(config, DiffusersConfigBase) else None,
         )
 
+    def _do_convert(
+        self, config: AnyModelConfig, model_path: Path, cache_path: Path, submodel_type: Optional[SubModelType] = None
+    ) -> AnyModel:
+        self.convert_cache.make_room(calc_model_size_by_fs(model_path))
+        pipeline = self._convert_model(config, model_path, cache_path if self.convert_cache.max_size > 0 else None)
+        if submodel_type:
+            # Proactively load the various submodels into the RAM cache so that we don't have to re-convert
+            # the entire pipeline every time a new submodel is needed.
+            for subtype in SubModelType:
+                if subtype == submodel_type:
+                    continue
+                if submodel := getattr(pipeline, subtype.value, None):
+                    self._ram_cache.put(
+                        config.key, submodel_type=subtype, model=submodel, size=calc_model_size_by_data(submodel)
+                    )
+        return getattr(pipeline, submodel_type.value) if submodel_type else pipeline
+
+    def _needs_conversion(self, config: AnyModelConfig, model_path: Path, dest_path: Path) -> bool:
+        return False
+
     # This needs to be implemented in subclasses that handle checkpoints
-    def _convert_model(self, config: AnyModelConfig, model_path: Path, output_path: Path) -> Path:
+    def _convert_model(self, config: AnyModelConfig, model_path: Path, output_path: Optional[Path] = None) -> AnyModel:
         raise NotImplementedError
 
     # This needs to be implemented in the subclass
     def _load_model(
         self,
-        model_path: Path,
-        model_variant: Optional[ModelRepoVariant] = None,
+        config: AnyModelConfig,
         submodel_type: Optional[SubModelType] = None,
     ) -> AnyModel:
         raise NotImplementedError

invokeai/backend/model_manager/load/model_cache/model_cache_default.py

@@ -122,6 +122,11 @@ class ModelCache(ModelCacheBase[AnyModel]):
         """Return the cap on cache size."""
         return self._max_cache_size
 
+    @max_cache_size.setter
+    def max_cache_size(self, value: float) -> None:
+        """Set the cap on cache size."""
+        self._max_cache_size = value
+
     @property
     def stats(self) -> Optional[CacheStats]:
         """Return collected CacheStats object."""
@@ -157,8 +162,9 @@ class ModelCache(ModelCacheBase[AnyModel]):
     ) -> None:
         """Store model under key and optional submodel_type."""
         key = self._make_cache_key(key, submodel_type)
-        assert key not in self._cached_models
-
+        if key in self._cached_models:
+            return
+        self.make_room(size)
         cache_record = CacheRecord(key, model, size)
         self._cached_models[key] = cache_record
         self._cache_stack.append(key)
@@ -405,6 +411,8 @@ class ModelCache(ModelCacheBase[AnyModel]):
             #
             # Keep in mind that gc is only responsible for handling reference cycles. Most objects should be cleaned up
             # immediately when their reference count hits 0.
+            if self.stats:
+                self.stats.cleared = models_cleared
             gc.collect()
 
         torch.cuda.empty_cache()
@@ -413,12 +421,23 @@ class ModelCache(ModelCacheBase[AnyModel]):
 
         self.logger.debug(f"After making room: cached_models={len(self._cached_models)}")
 
+    def _free_vram(self, device: torch.device) -> int:
+        vram_device = (  # mem_get_info() needs an indexed device
+            device if device.index is not None else torch.device(str(device), index=0)
+        )
+        free_mem, _ = torch.cuda.mem_get_info(vram_device)
+        for _, cache_entry in self._cached_models.items():
+            if cache_entry.loaded and not cache_entry.locked:
+                free_mem += cache_entry.size
+        return free_mem
+
     def _check_free_vram(self, target_device: torch.device, needed_size: int) -> None:
         if target_device.type != "cuda":
             return
-        vram_device = (  # mem_get_info() needs an indexed device
-            target_device if target_device.index is not None else torch.device(str(target_device), index=0)
-        )
-        free_mem, _ = torch.cuda.mem_get_info(torch.device(vram_device))
+        free_mem = self._free_vram(target_device)
         if needed_size > free_mem:
-            raise torch.cuda.OutOfMemoryError
+            needed_gb = round(needed_size / GIG, 2)
+            free_gb = round(free_mem / GIG, 2)
+            raise torch.cuda.OutOfMemoryError(
+                f"Insufficient VRAM to load model, requested {needed_gb}GB but only had {free_gb}GB free"
+            )

invokeai/backend/model_manager/load/model_cache/model_locker.py

@@ -34,7 +34,6 @@ class ModelLocker(ModelLockerBase):
 
         # NOTE that the model has to have the to() method in order for this code to move it into GPU!
         self._cache_entry.lock()
-
         try:
             if self._cache.lazy_offloading:
                 self._cache.offload_unlocked_models(self._cache_entry.size)
@@ -51,6 +50,7 @@ class ModelLocker(ModelLockerBase):
         except Exception:
             self._cache_entry.unlock()
             raise
+
         return self.model
 
     def unlock(self) -> None:

invokeai/backend/model_manager/load/model_loaders/controlnet.py

@@ -2,8 +2,10 @@
 """Class for ControlNet model loading in InvokeAI."""
 
 from pathlib import Path
+from typing import Optional
 
 from invokeai.backend.model_manager import (
+    AnyModel,
     AnyModelConfig,
     BaseModelType,
     ModelFormat,
@@ -33,7 +35,7 @@ class ControlNetLoader(GenericDiffusersLoader):
         else:
             return True
 
-    def _convert_model(self, config: AnyModelConfig, model_path: Path, output_path: Path) -> Path:
+    def _convert_model(self, config: AnyModelConfig, model_path: Path, output_path: Optional[Path] = None) -> AnyModel:
         assert isinstance(config, CheckpointConfigBase)
         image_size = (
             512
@@ -44,8 +46,8 @@ class ControlNetLoader(GenericDiffusersLoader):
         )
 
         self._logger.info(f"Converting {model_path} to diffusers format")
-        with open(self._app_config.root_path / config.config_path, "r") as config_stream:
-            convert_controlnet_to_diffusers(
+        with open(self._app_config.legacy_conf_path / config.config_path, "r") as config_stream:
+            result = convert_controlnet_to_diffusers(
                 model_path,
                 output_path,
                 original_config_file=config_stream,
@@ -53,4 +55,4 @@ class ControlNetLoader(GenericDiffusersLoader):
                 precision=self._torch_dtype,
                 from_safetensors=model_path.suffix == ".safetensors",
             )
-        return output_path
+        return result

invokeai/backend/model_manager/load/model_loaders/generic_diffusers.py

@@ -10,13 +10,14 @@ from diffusers.models.modeling_utils import ModelMixin
 
 from invokeai.backend.model_manager import (
     AnyModel,
+    AnyModelConfig,
     BaseModelType,
     InvalidModelConfigException,
     ModelFormat,
-    ModelRepoVariant,
     ModelType,
     SubModelType,
 )
+from invokeai.backend.model_manager.config import DiffusersConfigBase
 
 from .. import ModelLoader, ModelLoaderRegistry
 
@@ -28,14 +29,15 @@ class GenericDiffusersLoader(ModelLoader):
 
     def _load_model(
         self,
-        model_path: Path,
-        model_variant: Optional[ModelRepoVariant] = None,
+        config: AnyModelConfig,
         submodel_type: Optional[SubModelType] = None,
     ) -> AnyModel:
+        model_path = Path(config.path)
         model_class = self.get_hf_load_class(model_path)
         if submodel_type is not None:
             raise Exception(f"There are no submodels in models of type {model_class}")
-        variant = model_variant.value if model_variant else None
+        repo_variant = config.repo_variant if isinstance(config, DiffusersConfigBase) else None
+        variant = repo_variant.value if repo_variant else None
         try:
             result: AnyModel = model_class.from_pretrained(model_path, torch_dtype=self._torch_dtype, variant=variant)
         except OSError as e:

invokeai/backend/model_manager/load/model_loaders/ip_adapter.py

@@ -7,31 +7,26 @@ from typing import Optional
 import torch
 
 from invokeai.backend.ip_adapter.ip_adapter import build_ip_adapter
-from invokeai.backend.model_manager import (
-    AnyModel,
-    BaseModelType,
-    ModelFormat,
-    ModelRepoVariant,
-    ModelType,
-    SubModelType,
-)
+from invokeai.backend.model_manager import AnyModel, AnyModelConfig, BaseModelType, ModelFormat, ModelType, SubModelType
 from invokeai.backend.model_manager.load import ModelLoader, ModelLoaderRegistry
+from invokeai.backend.raw_model import RawModel
 
 
 @ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.IPAdapter, format=ModelFormat.InvokeAI)
+@ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.IPAdapter, format=ModelFormat.Checkpoint)
 class IPAdapterInvokeAILoader(ModelLoader):
     """Class to load IP Adapter diffusers models."""
 
     def _load_model(
         self,
-        model_path: Path,
-        model_variant: Optional[ModelRepoVariant] = None,
+        config: AnyModelConfig,
         submodel_type: Optional[SubModelType] = None,
     ) -> AnyModel:
         if submodel_type is not None:
             raise ValueError("There are no submodels in an IP-Adapter model.")
-        model = build_ip_adapter(
-            ip_adapter_ckpt_path=str(model_path / "ip_adapter.bin"),
+        model_path = Path(config.path)
+        model: RawModel = build_ip_adapter(
+            ip_adapter_ckpt_path=model_path,
             device=torch.device("cpu"),
             dtype=self._torch_dtype,
         )

invokeai/backend/model_manager/load/model_loaders/lora.py

@@ -3,7 +3,7 @@
 
 from logging import Logger
 from pathlib import Path
-from typing import Optional, Tuple
+from typing import Optional
 
 from invokeai.app.services.config import InvokeAIAppConfig
 from invokeai.backend.lora import LoRAModelRaw
@@ -12,7 +12,6 @@ from invokeai.backend.model_manager import (
     AnyModelConfig,
     BaseModelType,
     ModelFormat,
-    ModelRepoVariant,
     ModelType,
     SubModelType,
 )
@@ -41,12 +40,12 @@ class LoRALoader(ModelLoader):
 
     def _load_model(
         self,
-        model_path: Path,
-        model_variant: Optional[ModelRepoVariant] = None,
+        config: AnyModelConfig,
         submodel_type: Optional[SubModelType] = None,
     ) -> AnyModel:
         if submodel_type is not None:
             raise ValueError("There are no submodels in a LoRA model.")
+        model_path = Path(config.path)
         assert self._model_base is not None
         model = LoRAModelRaw.from_checkpoint(
             file_path=model_path,
@@ -56,12 +55,9 @@ class LoRALoader(ModelLoader):
         return model
 
     # override
-    def _get_model_path(
-        self, config: AnyModelConfig, submodel_type: Optional[SubModelType] = None
-    ) -> Tuple[Path, AnyModelConfig, Optional[SubModelType]]:
-        self._model_base = (
-            config.base
-        )  # cheating a little - we remember this variable for using in the subsequent call to _load_model()
+    def _get_model_path(self, config: AnyModelConfig) -> Path:
+        # cheating a little - we remember this variable for using in the subsequent call to _load_model()
+        self._model_base = config.base
 
         model_base_path = self._app_config.models_path
         model_path = model_base_path / config.path
@@ -73,5 +69,4 @@ class LoRALoader(ModelLoader):
                     model_path = path
                     break
 
-        result = model_path.resolve(), config, submodel_type
-        return result
+        return model_path.resolve()

invokeai/backend/model_manager/load/model_loaders/onnx.py

@@ -7,9 +7,9 @@ from typing import Optional
 
 from invokeai.backend.model_manager import (
     AnyModel,
+    AnyModelConfig,
     BaseModelType,
     ModelFormat,
-    ModelRepoVariant,
     ModelType,
     SubModelType,
 )
@@ -25,18 +25,19 @@ class OnnyxDiffusersModel(GenericDiffusersLoader):
 
     def _load_model(
         self,
-        model_path: Path,
-        model_variant: Optional[ModelRepoVariant] = None,
+        config: AnyModelConfig,
         submodel_type: Optional[SubModelType] = None,
     ) -> AnyModel:
         if not submodel_type is not None:
             raise Exception("A submodel type must be provided when loading onnx pipelines.")
+        model_path = Path(config.path)
         load_class = self.get_hf_load_class(model_path, submodel_type)
-        variant = model_variant.value if model_variant else None
+        repo_variant = getattr(config, "repo_variant", None)
+        variant = repo_variant.value if repo_variant else None
         model_path = model_path / submodel_type.value
         result: AnyModel = load_class.from_pretrained(
             model_path,
             torch_dtype=self._torch_dtype,
             variant=variant,
-        )  # type: ignore
+        )
         return result

invokeai/backend/model_manager/load/model_loaders/stable_diffusion.py

@@ -9,12 +9,16 @@ from invokeai.backend.model_manager import (
     AnyModelConfig,
     BaseModelType,
     ModelFormat,
-    ModelRepoVariant,
     ModelType,
     SchedulerPredictionType,
     SubModelType,
 )
-from invokeai.backend.model_manager.config import CheckpointConfigBase, MainCheckpointConfig, ModelVariantType
+from invokeai.backend.model_manager.config import (
+    CheckpointConfigBase,
+    DiffusersConfigBase,
+    MainCheckpointConfig,
+    ModelVariantType,
+)
 from invokeai.backend.model_manager.convert_ckpt_to_diffusers import convert_ckpt_to_diffusers
 
 from .. import ModelLoaderRegistry
@@ -41,14 +45,15 @@ class StableDiffusionDiffusersModel(GenericDiffusersLoader):
 
     def _load_model(
         self,
-        model_path: Path,
-        model_variant: Optional[ModelRepoVariant] = None,
+        config: AnyModelConfig,
         submodel_type: Optional[SubModelType] = None,
     ) -> AnyModel:
         if not submodel_type is not None:
             raise Exception("A submodel type must be provided when loading main pipelines.")
+        model_path = Path(config.path)
         load_class = self.get_hf_load_class(model_path, submodel_type)
-        variant = model_variant.value if model_variant else None
+        repo_variant = config.repo_variant if isinstance(config, DiffusersConfigBase) else None
+        variant = repo_variant.value if repo_variant else None
         model_path = model_path / submodel_type.value
         try:
             result: AnyModel = load_class.from_pretrained(
@@ -78,7 +83,7 @@ class StableDiffusionDiffusersModel(GenericDiffusersLoader):
         else:
             return True
 
-    def _convert_model(self, config: AnyModelConfig, model_path: Path, output_path: Path) -> Path:
+    def _convert_model(self, config: AnyModelConfig, model_path: Path, output_path: Optional[Path] = None) -> AnyModel:
         assert isinstance(config, MainCheckpointConfig)
         base = config.base
 
@@ -94,11 +99,11 @@ class StableDiffusionDiffusersModel(GenericDiffusersLoader):
 
         self._logger.info(f"Converting {model_path} to diffusers format")
 
-        convert_ckpt_to_diffusers(
+        loaded_model = convert_ckpt_to_diffusers(
             model_path,
             output_path,
             model_type=self.model_base_to_model_type[base],
-            original_config_file=self._app_config.root_path / config.config_path,
+            original_config_file=self._app_config.legacy_conf_path / config.config_path,
             extract_ema=True,
             from_safetensors=model_path.suffix == ".safetensors",
             precision=self._torch_dtype,
@@ -108,4 +113,4 @@ class StableDiffusionDiffusersModel(GenericDiffusersLoader):
             load_safety_checker=False,
             num_in_channels=VARIANT_TO_IN_CHANNEL_MAP[config.variant],
         )
-        return output_path
+        return loaded_model

invokeai/backend/model_manager/load/model_loaders/textual_inversion.py

@@ -2,14 +2,13 @@
 """Class for TI model loading in InvokeAI."""
 
 from pathlib import Path
-from typing import Optional, Tuple
+from typing import Optional
 
 from invokeai.backend.model_manager import (
     AnyModel,
     AnyModelConfig,
     BaseModelType,
     ModelFormat,
-    ModelRepoVariant,
     ModelType,
     SubModelType,
 )
@@ -27,22 +26,19 @@ class TextualInversionLoader(ModelLoader):
 
     def _load_model(
         self,
-        model_path: Path,
-        model_variant: Optional[ModelRepoVariant] = None,
+        config: AnyModelConfig,
         submodel_type: Optional[SubModelType] = None,
     ) -> AnyModel:
         if submodel_type is not None:
             raise ValueError("There are no submodels in a TI model.")
         model = TextualInversionModelRaw.from_checkpoint(
-            file_path=model_path,
+            file_path=config.path,
             dtype=self._torch_dtype,
         )
         return model
 
     # override
-    def _get_model_path(
-        self, config: AnyModelConfig, submodel_type: Optional[SubModelType] = None
-    ) -> Tuple[Path, AnyModelConfig, Optional[SubModelType]]:
+    def _get_model_path(self, config: AnyModelConfig) -> Path:
         model_path = self._app_config.models_path / config.path
 
         if config.format == ModelFormat.EmbeddingFolder:
@@ -53,4 +49,4 @@ class TextualInversionLoader(ModelLoader):
         if not path.exists():
             raise OSError(f"The embedding file at {path} was not found")
 
-        return path, config, submodel_type
+        return path

invokeai/backend/model_manager/load/model_loaders/vae.py

@@ -2,6 +2,7 @@
 """Class for VAE model loading in InvokeAI."""
 
 from pathlib import Path
+from typing import Optional
 
 import torch
 from omegaconf import DictConfig, OmegaConf
@@ -13,7 +14,7 @@ from invokeai.backend.model_manager import (
     ModelFormat,
     ModelType,
 )
-from invokeai.backend.model_manager.config import CheckpointConfigBase
+from invokeai.backend.model_manager.config import AnyModel, CheckpointConfigBase
 from invokeai.backend.model_manager.convert_ckpt_to_diffusers import convert_ldm_vae_to_diffusers
 
 from .. import ModelLoaderRegistry
@@ -38,13 +39,13 @@ class VAELoader(GenericDiffusersLoader):
         else:
             return True
 
-    def _convert_model(self, config: AnyModelConfig, model_path: Path, output_path: Path) -> Path:
+    def _convert_model(self, config: AnyModelConfig, model_path: Path, output_path: Optional[Path] = None) -> AnyModel:
         # TODO(MM2): check whether sdxl VAE models convert.
         if config.base not in {BaseModelType.StableDiffusion1, BaseModelType.StableDiffusion2}:
             raise Exception(f"VAE conversion not supported for model type: {config.base}")
         else:
             assert isinstance(config, CheckpointConfigBase)
-            config_file = self._app_config.root_path / config.config_path
+            config_file = self._app_config.legacy_conf_path / config.config_path
 
         if model_path.suffix == ".safetensors":
             checkpoint = safetensors_load_file(model_path, device="cpu")
@@ -63,6 +64,6 @@ class VAELoader(GenericDiffusersLoader):
             vae_config=ckpt_config,
             image_size=512,
             precision=self._torch_dtype,
+            dump_path=output_path,
         )
-        vae_model.save_pretrained(output_path, safe_serialization=True)
-        return output_path
+        return vae_model

invokeai/backend/model_manager/probe.py

@@ -230,9 +230,10 @@ class ModelProbe(object):
                 return ModelType.LoRA
             elif any(key.startswith(v) for v in {"controlnet", "control_model", "input_blocks"}):
                 return ModelType.ControlNet
+            elif any(key.startswith(v) for v in {"image_proj.", "ip_adapter."}):
+                return ModelType.IPAdapter
             elif key in {"emb_params", "string_to_param"}:
                 return ModelType.TextualInversion
-
         else:
             # diffusers-ti
             if len(ckpt) < 10 and all(isinstance(v, torch.Tensor) for v in ckpt.values()):
@@ -323,7 +324,7 @@ class ModelProbe(object):
         with SilenceWarnings():
             if model_path.suffix.endswith((".ckpt", ".pt", ".pth", ".bin")):
                 cls._scan_model(model_path.name, model_path)
-                model = torch.load(model_path)
+                model = torch.load(model_path, map_location="cpu")
                 assert isinstance(model, dict)
                 return model
             else:
@@ -527,8 +528,25 @@ class ControlNetCheckpointProbe(CheckpointProbeBase):
 
 
 class IPAdapterCheckpointProbe(CheckpointProbeBase):
+    """Class for probing IP Adapters"""
+
     def get_base_type(self) -> BaseModelType:
-        raise NotImplementedError()
+        checkpoint = self.checkpoint
+        for key in checkpoint.keys():
+            if not key.startswith(("image_proj.", "ip_adapter.")):
+                continue
+            cross_attention_dim = checkpoint["ip_adapter.1.to_k_ip.weight"].shape[-1]
+            if cross_attention_dim == 768:
+                return BaseModelType.StableDiffusion1
+            elif cross_attention_dim == 1024:
+                return BaseModelType.StableDiffusion2
+            elif cross_attention_dim == 2048:
+                return BaseModelType.StableDiffusionXL
+            else:
+                raise InvalidModelConfigException(
+                    f"IP-Adapter had unexpected cross-attention dimension: {cross_attention_dim}."
+                )
+        raise InvalidModelConfigException(f"{self.model_path}: Unable to determine base type")
 
 
 class CLIPVisionCheckpointProbe(CheckpointProbeBase):
@@ -768,7 +786,7 @@ class T2IAdapterFolderProbe(FolderProbeBase):
             )
 
 
-############## register probe classes ######
+# Register probe classes
 ModelProbe.register_probe("diffusers", ModelType.Main, PipelineFolderProbe)
 ModelProbe.register_probe("diffusers", ModelType.VAE, VaeFolderProbe)
 ModelProbe.register_probe("diffusers", ModelType.LoRA, LoRAFolderProbe)

invokeai/backend/stable_diffusion/seamless.py

@@ -28,6 +28,10 @@ def _conv_forward_asymmetric(self, input, weight, bias):
 
 @contextmanager
 def set_seamless(model: Union[UNet2DConditionModel, AutoencoderKL, AutoencoderTiny], seamless_axes: List[str]):
+    if not seamless_axes:
+        yield
+        return
+
     # Callable: (input: Tensor, weight: Tensor, bias: Optional[Tensor]) -> Tensor
     to_restore: list[tuple[nn.Conv2d | nn.ConvTranspose2d, Callable]] = []
     try:

invokeai/backend/util/db_maintenance.py

@@ -31,6 +31,9 @@ class ConfigMapper:
     YAML_FILENAME = "invokeai.yaml"
     DATABASE_FILENAME = "invokeai.db"
 
+    DEFAULT_OUTDIR = "outputs"
+    DEFAULT_DB_DIR = "databases"
+
     database_path = None
     database_backup_dir = None
     outputs_path = None
@@ -50,12 +53,18 @@ class ConfigMapper:
     def __load_from_root_config(self, invoke_root):
         """Validate a yaml path exists, confirm the user wants to use it and load config."""
         yaml_path = os.path.join(invoke_root, self.YAML_FILENAME)
+        if not os.path.exists(yaml_path):
+            print(f"Unable to find invokeai.yaml at {yaml_path}!")
+            return False
         if os.path.exists(yaml_path):
             db_dir, outdir = self.__load_paths_from_yaml_file(yaml_path)
 
-            if db_dir is None or outdir is None:
-                print("The invokeai.yaml file was found but is missing the db_dir and/or outdir setting!")
-                return False
+            if db_dir is None:
+                db_dir = self.DEFAULT_DB_DIR
+                print(f"The invokeai.yaml file was found but is missing the db_dir setting! Defaulting to {db_dir}")
+            if outdir is None:
+                outdir = self.DEFAULT_OUTDIR
+                print(f"The invokeai.yaml file was found but is missing the outdir setting! Defaulting to {outdir}")
 
             if os.path.isabs(db_dir):
                 self.database_path = os.path.join(db_dir, self.DATABASE_FILENAME)

invokeai/frontend/web/package.json

@@ -94,6 +94,7 @@
     "reactflow": "^11.10.4",
     "redux-dynamic-middlewares": "^2.2.0",
     "redux-remember": "^5.1.0",
+    "rfdc": "^1.3.1",
     "roarr": "^7.21.1",
     "serialize-error": "^11.0.3",
     "socket.io-client": "^4.7.5",

invokeai/frontend/web/pnpm-lock.yaml

@@ -137,6 +137,9 @@ dependencies:
   redux-remember:
     specifier: ^5.1.0
     version: 5.1.0(redux@5.0.1)
+  rfdc:
+    specifier: ^1.3.1
+    version: 1.3.1
   roarr:
     specifier: ^7.21.1
     version: 7.21.1
@@ -12128,6 +12131,10 @@ packages:
     resolution: {integrity: sha512-/x8uIPdTafBqakK0TmPNJzgkLP+3H+yxpUJhCQHsLBg1rYEVNR2D8BRYNWQhVBjyOd7oo1dZRVzIkwMY2oqfYQ==}
     dev: true
 
+  /rfdc@1.3.1:
+    resolution: {integrity: sha512-r5a3l5HzYlIC68TpmYKlxWjmOP6wiPJ1vWv2HeLhNsRZMrCkxeqxiHlQ21oXmQ4F3SiryXBHhAD7JZqvOJjFmg==}
+    dev: false
+
   /rimraf@2.6.3:
     resolution: {integrity: sha512-mwqeW5XsA2qAejG46gYdENaxXjx9onRNCfn7L0duuP4hCuTIi/QO7PDK07KJfp1d+izWPrzEJDcSqBa0OZQriA==}
     hasBin: true

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

@@ -4,7 +4,7 @@
         "reportBugLabel": "Fehler melden",
         "settingsLabel": "Einstellungen",
         "img2img": "Bild zu Bild",
-        "nodes": "Knoten Editor",
+        "nodes": "Arbeitsabläufe",
         "upload": "Hochladen",
         "load": "Laden",
         "statusDisconnected": "Getrennt",
@@ -74,7 +74,9 @@
         "updated": "Aktualisiert",
         "copy": "Kopieren",
         "aboutHeading": "Nutzen Sie Ihre kreative Energie",
-        "toResolve": "Lösen"
+        "toResolve": "Lösen",
+        "add": "Hinzufügen",
+        "loglevel": "Protokoll Stufe"
     },
     "gallery": {
         "galleryImageSize": "Bildgröße",
@@ -104,11 +106,16 @@
         "dropToUpload": "$t(gallery.drop) zum hochladen",
         "dropOrUpload": "$t(gallery.drop) oder hochladen",
         "drop": "Ablegen",
-        "problemDeletingImages": "Problem beim Löschen der Bilder"
+        "problemDeletingImages": "Problem beim Löschen der Bilder",
+        "bulkDownloadRequested": "Download vorbereiten",
+        "bulkDownloadRequestedDesc": "Dein Download wird vorbereitet. Dies kann ein paar Momente dauern.",
+        "bulkDownloadRequestFailed": "Problem beim Download vorbereiten",
+        "bulkDownloadFailed": "Download fehlgeschlagen",
+        "alwaysShowImageSizeBadge": "Zeige immer Bilder Größe Abzeichen"
     },
     "hotkeys": {
         "keyboardShortcuts": "Tastenkürzel",
-        "appHotkeys": "App-Tastenkombinationen",
+        "appHotkeys": "App",
         "generalHotkeys": "Allgemein",
         "galleryHotkeys": "Galerie",
         "unifiedCanvasHotkeys": "Leinwand",
@@ -382,7 +389,14 @@
         "vaePrecision": "VAE-Präzision",
         "variant": "Variante",
         "modelDeleteFailed": "Modell konnte nicht gelöscht werden",
-        "noModelSelected": "Kein Modell ausgewählt"
+        "noModelSelected": "Kein Modell ausgewählt",
+        "huggingFace": "HuggingFace",
+        "defaultSettings": "Standardeinstellungen",
+        "edit": "Bearbeiten",
+        "cancel": "Stornieren",
+        "defaultSettingsSaved": "Standardeinstellungen gespeichert",
+        "addModels": "Model hinzufügen",
+        "deleteModelImage": "Lösche Model Bild"
     },
     "parameters": {
         "images": "Bilder",
@@ -671,7 +685,8 @@
         "body": "Körper",
         "hands": "Hände",
         "dwOpenpose": "DW Openpose",
-        "dwOpenposeDescription": "Posenschätzung mit DW Openpose"
+        "dwOpenposeDescription": "Posenschätzung mit DW Openpose",
+        "selectCLIPVisionModel": "Wähle ein CLIP Vision Model aus"
     },
     "queue": {
         "status": "Status",
@@ -757,7 +772,12 @@
         "scheduler": "Planer",
         "noRecallParameters": "Es wurden keine Parameter zum Abrufen gefunden",
         "recallParameters": "Parameter wiederherstellen",
-        "cfgRescaleMultiplier": "$t(parameters.cfgRescaleMultiplier)"
+        "cfgRescaleMultiplier": "$t(parameters.cfgRescaleMultiplier)",
+        "allPrompts": "Alle Prompts",
+        "imageDimensions": "Bilder Auslösungen",
+        "parameterSet": "Parameter {{parameter}} setzen",
+        "recallParameter": "{{label}} Abrufen",
+        "parsingFailed": "Parsing Fehlgeschlagen"
     },
     "popovers": {
         "noiseUseCPU": {
@@ -1022,7 +1042,8 @@
             "title": "Bild"
         },
         "advanced": {
-            "title": "Erweitert"
+            "title": "Erweitert",
+            "options": "$t(accordions.advanced.title) Optionen"
         },
         "control": {
             "title": "Kontrolle"
@@ -1068,5 +1089,10 @@
     },
     "dynamicPrompts": {
         "showDynamicPrompts": "Dynamische Prompts anzeigen"
+    },
+    "prompt": {
+        "noMatchingTriggers": "Keine passenden Auslöser",
+        "addPromptTrigger": "Auslöse Text hinzufügen",
+        "compatibleEmbeddings": "Kompatible Einbettungen"
     }
 }

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

@@ -217,6 +217,7 @@
         "saveControlImage": "Save Control Image",
         "scribble": "scribble",
         "selectModel": "Select a model",
+        "selectCLIPVisionModel": "Select a CLIP Vision model",
         "setControlImageDimensions": "Set Control Image Dimensions To W/H",
         "showAdvanced": "Show Advanced",
         "small": "Small",
@@ -655,6 +656,7 @@
         "install": "Install",
         "installAll": "Install All",
         "installRepo": "Install Repo",
+        "ipAdapters": "IP Adapters",
         "load": "Load",
         "localOnly": "local only",
         "manual": "Manual",
@@ -682,6 +684,7 @@
         "noModelsInstalled": "No Models Installed",
         "noModelsInstalledDesc1": "Install models with the",
         "noModelSelected": "No Model Selected",
+        "noMatchingModels": "No matching Models",
         "none": "none",
         "path": "Path",
         "pathToConfig": "Path To Config",
@@ -885,6 +888,11 @@
         "imageFit": "Fit Initial Image To Output Size",
         "images": "Images",
         "infillMethod": "Infill Method",
+        "infillMosaicTileWidth": "Tile Width",
+        "infillMosaicTileHeight": "Tile Height",
+        "infillMosaicMinColor": "Min Color",
+        "infillMosaicMaxColor": "Max Color",
+        "infillColorValue": "Fill Color",
         "info": "Info",
         "invoke": {
             "addingImagesTo": "Adding images to",
@@ -1415,6 +1423,7 @@
         "eraseBoundingBox": "Erase Bounding Box",
         "eraser": "Eraser",
         "fillBoundingBox": "Fill Bounding Box",
+        "initialFitImageSize": "Fit Image Size on Drop",
         "invertBrushSizeScrollDirection": "Invert Scroll for Brush Size",
         "layer": "Layer",
         "limitStrokesToBox": "Limit Strokes to Box",

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

@@ -73,7 +73,8 @@
         "ai": "ia",
         "file": "File",
         "toResolve": "Da risolvere",
-        "add": "Aggiungi"
+        "add": "Aggiungi",
+        "loglevel": "Livello di log"
     },
     "gallery": {
         "galleryImageSize": "Dimensione dell'immagine",
@@ -365,7 +366,7 @@
         "modelConverted": "Modello convertito",
         "alpha": "Alpha",
         "convertToDiffusersHelpText1": "Questo modello verrà convertito nel formato 🧨 Diffusori.",
-        "convertToDiffusersHelpText3": "Il file Checkpoint su disco verrà eliminato se si trova nella cartella principale di InvokeAI. Se si trova invece in una posizione personalizzata, NON verrà eliminato.",
+        "convertToDiffusersHelpText3": "Il file del modello su disco verrà eliminato se si trova nella cartella principale di InvokeAI. Se si trova invece in una posizione personalizzata, NON verrà eliminato.",
         "v2_base": "v2 (512px)",
         "v2_768": "v2 (768px)",
         "none": "nessuno",
@@ -442,7 +443,8 @@
         "noModelsInstalled": "Nessun modello installato",
         "hfTokenInvalidErrorMessage2": "Aggiornalo in ",
         "main": "Principali",
-        "noModelsInstalledDesc1": "Installa i modelli con"
+        "noModelsInstalledDesc1": "Installa i modelli con",
+        "ipAdapters": "Adattatori IP"
     },
     "parameters": {
         "images": "Immagini",
@@ -934,7 +936,10 @@
         "base": "Base",
         "lineart": "Linea",
         "controlnet": "$t(controlnet.controlAdapter_one) #{{number}} ($t(common.controlNet))",
-        "mediapipeFace": "Mediapipe Volto"
+        "mediapipeFace": "Mediapipe Volto",
+        "ip_adapter": "$t(controlnet.controlAdapter_one) #{{number}} ($t(common.ipAdapter))",
+        "t2i_adapter": "$t(controlnet.controlAdapter_one) #{{number}} ($t(common.t2iAdapter))",
+        "selectCLIPVisionModel": "Seleziona un modello CLIP Vision"
     },
     "queue": {
         "queueFront": "Aggiungi all'inizio della coda",
@@ -1490,7 +1495,8 @@
             "title": "Generazione"
         },
         "advanced": {
-            "title": "Avanzate"
+            "title": "Avanzate",
+            "options": "Opzioni $t(accordions.advanced.title)"
         },
         "image": {
             "title": "Immagine"

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

@@ -75,7 +75,8 @@
         "copy": "Копировать",
         "localSystem": "Локальная система",
         "aboutDesc": "Используя Invoke для работы? Проверьте это:",
-        "add": "Добавить"
+        "add": "Добавить",
+        "loglevel": "Уровень логов"
     },
     "gallery": {
         "galleryImageSize": "Размер изображений",
@@ -1505,7 +1506,8 @@
             "title": "Генерация"
         },
         "advanced": {
-            "title": "Расширенные"
+            "title": "Расширенные",
+            "options": "Опции $t(accordions.advanced.title)"
         },
         "image": {
             "title": "Изображение"

invokeai/frontend/web/src/app/store/middleware/devtools/actionSanitizer.ts

@@ -1,7 +1,7 @@
 import type { UnknownAction } from '@reduxjs/toolkit';
+import { deepClone } from 'common/util/deepClone';
 import { isAnyGraphBuilt } from 'features/nodes/store/actions';
 import { nodeTemplatesBuilt } from 'features/nodes/store/nodesSlice';
-import { cloneDeep } from 'lodash-es';
 import { appInfoApi } from 'services/api/endpoints/appInfo';
 import type { Graph } from 'services/api/types';
 import { socketGeneratorProgress } from 'services/events/actions';
@@ -33,7 +33,7 @@ export const actionSanitizer = <A extends UnknownAction>(action: A): A => {
   }
 
   if (socketGeneratorProgress.match(action)) {
-    const sanitized = cloneDeep(action);
+    const sanitized = deepClone(action);
     if (sanitized.payload.data.progress_image) {
       sanitized.payload.data.progress_image.dataURL = '<Progress image omitted>';
     }

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/socketio/socketModelInstall.ts

@@ -43,6 +43,7 @@ export const addModelInstallEventListener = (startAppListening: AppStartListenin
         })
       );
       dispatch(api.util.invalidateTags([{ type: 'ModelConfig', id: LIST_TAG }]));
+      dispatch(api.util.invalidateTags([{ type: 'ModelScanFolderResults', id: LIST_TAG }]));
     },
   });
 

invokeai/frontend/web/src/common/components/OverlayScrollbars/constants.ts

@@ -1,4 +1,5 @@
-import { cloneDeep, merge } from 'lodash-es';
+import { deepClone } from 'common/util/deepClone';
+import { merge } from 'lodash-es';
 import { ClickScrollPlugin, OverlayScrollbars } from 'overlayscrollbars';
 import type { UseOverlayScrollbarsParams } from 'overlayscrollbars-react';
 
@@ -22,7 +23,7 @@ export const getOverlayScrollbarsParams = (
   overflowX: 'hidden' | 'scroll' = 'hidden',
   overflowY: 'hidden' | 'scroll' = 'scroll'
 ) => {
-  const params = cloneDeep(overlayScrollbarsParams);
+  const params = deepClone(overlayScrollbarsParams);
   merge(params, { options: { overflow: { y: overflowY, x: overflowX } } });
   return params;
 };

invokeai/frontend/web/src/common/util/deepClone.ts

@@ -0,0 +1,15 @@
+import rfdc from 'rfdc';
+const _rfdc = rfdc();
+
+/**
+ * Deep-clones an object using Really Fast Deep Clone.
+ * This is the fastest deep clone library on Chrome, but not the fastest on FF. Still, it's much faster than lodash
+ * and structuredClone, so it's the best all-around choice.
+ *
+ * Simple Benchmark: https://www.measurethat.net/Benchmarks/Show/30358/0/lodash-clonedeep-vs-jsonparsejsonstringify-vs-recursive
+ * Repo: https://github.com/davidmarkclements/rfdc
+ *
+ * @param obj The object to deep-clone
+ * @returns The cloned object
+ */
+export const deepClone = <T>(obj: T): T => _rfdc(obj);

invokeai/frontend/web/src/features/canvas/components/IAICanvasToolbar/IAICanvasSettingsButtonPopover.tsx

@@ -18,6 +18,7 @@ import {
   setShouldAutoSave,
   setShouldCropToBoundingBoxOnSave,
   setShouldDarkenOutsideBoundingBox,
+  setShouldFitImageSize,
   setShouldInvertBrushSizeScrollDirection,
   setShouldRestrictStrokesToBox,
   setShouldShowCanvasDebugInfo,
@@ -48,6 +49,7 @@ const IAICanvasSettingsButtonPopover = () => {
   const shouldSnapToGrid = useAppSelector((s) => s.canvas.shouldSnapToGrid);
   const shouldRestrictStrokesToBox = useAppSelector((s) => s.canvas.shouldRestrictStrokesToBox);
   const shouldAntialias = useAppSelector((s) => s.canvas.shouldAntialias);
+  const shouldFitImageSize = useAppSelector((s) => s.canvas.shouldFitImageSize);
 
   useHotkeys(
     ['n'],
@@ -102,6 +104,10 @@ const IAICanvasSettingsButtonPopover = () => {
     (e: ChangeEvent<HTMLInputElement>) => dispatch(setShouldAntialias(e.target.checked)),
     [dispatch]
   );
+  const handleChangeShouldFitImageSize = useCallback(
+    (e: ChangeEvent<HTMLInputElement>) => dispatch(setShouldFitImageSize(e.target.checked)),
+    [dispatch]
+  );
 
   return (
     <Popover>
@@ -165,6 +171,10 @@ const IAICanvasSettingsButtonPopover = () => {
                 <FormLabel>{t('unifiedCanvas.antialiasing')}</FormLabel>
                 <Checkbox isChecked={shouldAntialias} onChange={handleChangeShouldAntialias} />
               </FormControl>
+              <FormControl>
+                <FormLabel>{t('unifiedCanvas.initialFitImageSize')}</FormLabel>
+                <Checkbox isChecked={shouldFitImageSize} onChange={handleChangeShouldFitImageSize} />
+              </FormControl>
             </FormControlGroup>
             <ClearCanvasHistoryButtonModal />
           </Flex>

invokeai/frontend/web/src/features/canvas/store/canvasSlice.ts

@@ -1,6 +1,7 @@
 import type { PayloadAction } from '@reduxjs/toolkit';
 import { createSlice } from '@reduxjs/toolkit';
 import type { PersistConfig, RootState } from 'app/store/store';
+import { deepClone } from 'common/util/deepClone';
 import { roundDownToMultiple, roundToMultiple } from 'common/util/roundDownToMultiple';
 import calculateCoordinates from 'features/canvas/util/calculateCoordinates';
 import calculateScale from 'features/canvas/util/calculateScale';
@@ -13,7 +14,7 @@ import { modelChanged } from 'features/parameters/store/generationSlice';
 import type { PayloadActionWithOptimalDimension } from 'features/parameters/store/types';
 import { getIsSizeOptimal, getOptimalDimension } from 'features/parameters/util/optimalDimension';
 import type { IRect, Vector2d } from 'konva/lib/types';
-import { clamp, cloneDeep } from 'lodash-es';
+import { clamp } from 'lodash-es';
 import type { RgbaColor } from 'react-colorful';
 import { queueApi } from 'services/api/endpoints/queue';
 import type { ImageDTO } from 'services/api/types';
@@ -36,7 +37,7 @@ import { CANVAS_GRID_SIZE_FINE } from './constants';
 /**
  * The maximum history length to keep in the past/future layer states.
  */
-const MAX_HISTORY = 128;
+const MAX_HISTORY = 100;
 
 const initialLayerState: CanvasLayerState = {
   objects: [],
@@ -65,6 +66,7 @@ const initialCanvasState: CanvasState = {
   shouldAutoSave: false,
   shouldCropToBoundingBoxOnSave: false,
   shouldDarkenOutsideBoundingBox: false,
+  shouldFitImageSize: true,
   shouldInvertBrushSizeScrollDirection: false,
   shouldLockBoundingBox: false,
   shouldPreserveMaskedArea: false,
@@ -121,7 +123,7 @@ export const canvasSlice = createSlice({
       state.brushSize = action.payload;
     },
     clearMask: (state) => {
-      state.pastLayerStates.push(cloneDeep(state.layerState));
+      pushToPrevLayerStates(state);
       state.layerState.objects = state.layerState.objects.filter((obj) => !isCanvasMaskLine(obj));
       state.futureLayerStates = [];
       state.shouldPreserveMaskedArea = false;
@@ -143,12 +145,20 @@ export const canvasSlice = createSlice({
       reducer: (state, action: PayloadActionWithOptimalDimension<ImageDTO>) => {
         const { width, height, image_name } = action.payload;
         const { optimalDimension } = action.meta;
-        const { stageDimensions } = state;
+        const { stageDimensions, shouldFitImageSize } = state;
 
-        const newBoundingBoxDimensions = {
-          width: roundDownToMultiple(clamp(width, CANVAS_GRID_SIZE_FINE, optimalDimension), CANVAS_GRID_SIZE_FINE),
-          height: roundDownToMultiple(clamp(height, CANVAS_GRID_SIZE_FINE, optimalDimension), CANVAS_GRID_SIZE_FINE),
-        };
+        const newBoundingBoxDimensions = shouldFitImageSize
+          ? {
+              width: roundDownToMultiple(width, CANVAS_GRID_SIZE_FINE),
+              height: roundDownToMultiple(height, CANVAS_GRID_SIZE_FINE),
+            }
+          : {
+              width: roundDownToMultiple(clamp(width, CANVAS_GRID_SIZE_FINE, optimalDimension), CANVAS_GRID_SIZE_FINE),
+              height: roundDownToMultiple(
+                clamp(height, CANVAS_GRID_SIZE_FINE, optimalDimension),
+                CANVAS_GRID_SIZE_FINE
+              ),
+            };
 
         const newBoundingBoxCoordinates = {
           x: roundToMultiple(width / 2 - newBoundingBoxDimensions.width / 2, CANVAS_GRID_SIZE_FINE),
@@ -163,10 +173,10 @@ export const canvasSlice = createSlice({
         state.boundingBoxDimensions = newBoundingBoxDimensions;
         state.boundingBoxCoordinates = newBoundingBoxCoordinates;
 
-        state.pastLayerStates.push(cloneDeep(state.layerState));
+        pushToPrevLayerStates(state);
 
         state.layerState = {
-          ...cloneDeep(initialLayerState),
+          ...deepClone(initialLayerState),
           objects: [
             {
               kind: 'image',
@@ -261,11 +271,7 @@ export const canvasSlice = createSlice({
         return;
       }
 
-      state.pastLayerStates.push(cloneDeep(state.layerState));
-
-      if (state.pastLayerStates.length > MAX_HISTORY) {
-        state.pastLayerStates.shift();
-      }
+      pushToPrevLayerStates(state);
 
       state.layerState.stagingArea.images.push({
         kind: 'image',
@@ -279,13 +285,9 @@ export const canvasSlice = createSlice({
       state.futureLayerStates = [];
     },
     discardStagedImages: (state) => {
-      state.pastLayerStates.push(cloneDeep(state.layerState));
+      pushToPrevLayerStates(state);
 
-      if (state.pastLayerStates.length > MAX_HISTORY) {
-        state.pastLayerStates.shift();
-      }
-
-      state.layerState.stagingArea = cloneDeep(cloneDeep(initialLayerState)).stagingArea;
+      state.layerState.stagingArea = deepClone(initialLayerState.stagingArea);
 
       state.futureLayerStates = [];
       state.shouldShowStagingOutline = true;
@@ -294,18 +296,21 @@ export const canvasSlice = createSlice({
     },
     discardStagedImage: (state) => {
       const { images, selectedImageIndex } = state.layerState.stagingArea;
-      state.pastLayerStates.push(cloneDeep(state.layerState));
-
-      if (state.pastLayerStates.length > MAX_HISTORY) {
-        state.pastLayerStates.shift();
-      }
-
-      if (!images.length) {
-        return;
-      }
+      pushToPrevLayerStates(state);
 
       images.splice(selectedImageIndex, 1);
 
+      if (images.length === 0) {
+        pushToPrevLayerStates(state);
+
+        state.layerState.stagingArea = deepClone(initialLayerState.stagingArea);
+
+        state.futureLayerStates = [];
+        state.shouldShowStagingOutline = true;
+        state.shouldShowStagingImage = true;
+        state.batchIds = [];
+      }
+
       if (selectedImageIndex >= images.length) {
         state.layerState.stagingArea.selectedImageIndex = images.length - 1;
       }
@@ -320,11 +325,7 @@ export const canvasSlice = createSlice({
     addFillRect: (state) => {
       const { boundingBoxCoordinates, boundingBoxDimensions, brushColor } = state;
 
-      state.pastLayerStates.push(cloneDeep(state.layerState));
-
-      if (state.pastLayerStates.length > MAX_HISTORY) {
-        state.pastLayerStates.shift();
-      }
+      pushToPrevLayerStates(state);
 
       state.layerState.objects.push({
         kind: 'fillRect',
@@ -339,11 +340,7 @@ export const canvasSlice = createSlice({
     addEraseRect: (state) => {
       const { boundingBoxCoordinates, boundingBoxDimensions } = state;
 
-      state.pastLayerStates.push(cloneDeep(state.layerState));
-
-      if (state.pastLayerStates.length > MAX_HISTORY) {
-        state.pastLayerStates.shift();
-      }
+      pushToPrevLayerStates(state);
 
       state.layerState.objects.push({
         kind: 'eraseRect',
@@ -367,11 +364,7 @@ export const canvasSlice = createSlice({
       // set & then spread this to only conditionally add the "color" key
       const newColor = layer === 'base' && tool === 'brush' ? { color: brushColor } : {};
 
-      state.pastLayerStates.push(cloneDeep(state.layerState));
-
-      if (state.pastLayerStates.length > MAX_HISTORY) {
-        state.pastLayerStates.shift();
-      }
+      pushToPrevLayerStates(state);
 
       const newLine: CanvasMaskLine | CanvasBaseLine = {
         kind: 'line',
@@ -409,11 +402,7 @@ export const canvasSlice = createSlice({
         return;
       }
 
-      state.futureLayerStates.unshift(cloneDeep(state.layerState));
-
-      if (state.futureLayerStates.length > MAX_HISTORY) {
-        state.futureLayerStates.pop();
-      }
+      pushToFutureLayerStates(state);
 
       state.layerState = targetState;
     },
@@ -424,11 +413,7 @@ export const canvasSlice = createSlice({
         return;
       }
 
-      state.pastLayerStates.push(cloneDeep(state.layerState));
-
-      if (state.pastLayerStates.length > MAX_HISTORY) {
-        state.pastLayerStates.shift();
-      }
+      pushToPrevLayerStates(state);
 
       state.layerState = targetState;
     },
@@ -445,8 +430,8 @@ export const canvasSlice = createSlice({
       state.shouldShowIntermediates = action.payload;
     },
     resetCanvas: (state) => {
-      state.pastLayerStates.push(cloneDeep(state.layerState));
-      state.layerState = cloneDeep(initialLayerState);
+      pushToPrevLayerStates(state);
+      state.layerState = deepClone(initialLayerState);
       state.futureLayerStates = [];
       state.batchIds = [];
       state.boundingBoxCoordinates = {
@@ -540,11 +525,7 @@ export const canvasSlice = createSlice({
 
       const { images, selectedImageIndex } = state.layerState.stagingArea;
 
-      state.pastLayerStates.push(cloneDeep(state.layerState));
-
-      if (state.pastLayerStates.length > MAX_HISTORY) {
-        state.pastLayerStates.shift();
-      }
+      pushToPrevLayerStates(state);
 
       const imageToCommit = images[selectedImageIndex];
 
@@ -553,7 +534,7 @@ export const canvasSlice = createSlice({
           ...imageToCommit,
         });
       }
-      state.layerState.stagingArea = cloneDeep(initialLayerState).stagingArea;
+      state.layerState.stagingArea = deepClone(initialLayerState.stagingArea);
 
       state.futureLayerStates = [];
       state.shouldShowStagingOutline = true;
@@ -610,6 +591,9 @@ export const canvasSlice = createSlice({
     setShouldAntialias: (state, action: PayloadAction<boolean>) => {
       state.shouldAntialias = action.payload;
     },
+    setShouldFitImageSize: (state, action: PayloadAction<boolean>) => {
+      state.shouldFitImageSize = action.payload;
+    },
     setShouldCropToBoundingBoxOnSave: (state, action: PayloadAction<boolean>) => {
       state.shouldCropToBoundingBoxOnSave = action.payload;
     },
@@ -623,7 +607,7 @@ export const canvasSlice = createSlice({
       };
     },
     setMergedCanvas: (state, action: PayloadAction<CanvasImage>) => {
-      state.pastLayerStates.push(cloneDeep(state.layerState));
+      pushToPrevLayerStates(state);
 
       state.futureLayerStates = [];
 
@@ -720,6 +704,7 @@ export const {
   setShouldRestrictStrokesToBox,
   stagingAreaInitialized,
   setShouldAntialias,
+  setShouldFitImageSize,
   canvasResized,
   canvasBatchIdAdded,
   canvasBatchIdsReset,
@@ -743,3 +728,17 @@ export const canvasPersistConfig: PersistConfig<CanvasState> = {
   migrate: migrateCanvasState,
   persistDenylist: [],
 };
+
+const pushToPrevLayerStates = (state: CanvasState) => {
+  state.pastLayerStates.push(deepClone(state.layerState));
+  if (state.pastLayerStates.length > MAX_HISTORY) {
+    state.pastLayerStates = state.pastLayerStates.slice(-MAX_HISTORY);
+  }
+};
+
+const pushToFutureLayerStates = (state: CanvasState) => {
+  state.futureLayerStates.unshift(deepClone(state.layerState));
+  if (state.futureLayerStates.length > MAX_HISTORY) {
+    state.futureLayerStates = state.futureLayerStates.slice(0, MAX_HISTORY);
+  }
+};

invokeai/frontend/web/src/features/canvas/store/canvasTypes.ts

@@ -120,6 +120,7 @@ export interface CanvasState {
   shouldAutoSave: boolean;
   shouldCropToBoundingBoxOnSave: boolean;
   shouldDarkenOutsideBoundingBox: boolean;
+  shouldFitImageSize: boolean;
   shouldInvertBrushSizeScrollDirection: boolean;
   shouldLockBoundingBox: boolean;
   shouldPreserveMaskedArea: boolean;

invokeai/frontend/web/src/features/controlAdapters/components/parameters/ParamControlAdapterModel.tsx

@@ -1,12 +1,18 @@
-import { Combobox, FormControl, Tooltip } from '@invoke-ai/ui-library';
+import type { ComboboxOnChange, ComboboxOption } from '@invoke-ai/ui-library';
+import { Combobox, Flex, FormControl, Tooltip } from '@invoke-ai/ui-library';
 import { createMemoizedSelector } from 'app/store/createMemoizedSelector';
 import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
 import { useGroupedModelCombobox } from 'common/hooks/useGroupedModelCombobox';
+import { useControlAdapterCLIPVisionModel } from 'features/controlAdapters/hooks/useControlAdapterCLIPVisionModel';
 import { useControlAdapterIsEnabled } from 'features/controlAdapters/hooks/useControlAdapterIsEnabled';
 import { useControlAdapterModel } from 'features/controlAdapters/hooks/useControlAdapterModel';
 import { useControlAdapterModels } from 'features/controlAdapters/hooks/useControlAdapterModels';
 import { useControlAdapterType } from 'features/controlAdapters/hooks/useControlAdapterType';
-import { controlAdapterModelChanged } from 'features/controlAdapters/store/controlAdaptersSlice';
+import {
+  controlAdapterCLIPVisionModelChanged,
+  controlAdapterModelChanged,
+} from 'features/controlAdapters/store/controlAdaptersSlice';
+import type { CLIPVisionModel } from 'features/controlAdapters/store/types';
 import { selectGenerationSlice } from 'features/parameters/store/generationSlice';
 import { memo, useCallback, useMemo } from 'react';
 import { useTranslation } from 'react-i18next';
@@ -29,6 +35,7 @@ const ParamControlAdapterModel = ({ id }: ParamControlAdapterModelProps) => {
   const { modelConfig } = useControlAdapterModel(id);
   const dispatch = useAppDispatch();
   const currentBaseModel = useAppSelector((s) => s.generation.model?.base);
+  const currentCLIPVisionModel = useControlAdapterCLIPVisionModel(id);
   const mainModel = useAppSelector(selectMainModel);
   const { t } = useTranslation();
 
@@ -49,6 +56,16 @@ const ParamControlAdapterModel = ({ id }: ParamControlAdapterModelProps) => {
     [dispatch, id]
   );
 
+  const onCLIPVisionModelChange = useCallback<ComboboxOnChange>(
+    (v) => {
+      if (!v?.value) {
+        return;
+      }
+      dispatch(controlAdapterCLIPVisionModelChanged({ id, clipVisionModel: v.value as CLIPVisionModel }));
+    },
+    [dispatch, id]
+  );
+
   const selectedModel = useMemo(
     () => (modelConfig && controlAdapterType ? { ...modelConfig, model_type: controlAdapterType } : null),
     [controlAdapterType, modelConfig]
@@ -71,18 +88,51 @@ const ParamControlAdapterModel = ({ id }: ParamControlAdapterModelProps) => {
     isLoading,
   });
 
+  const clipVisionOptions = useMemo<ComboboxOption[]>(
+    () => [
+      { label: 'ViT-H', value: 'ViT-H' },
+      { label: 'ViT-G', value: 'ViT-G' },
+    ],
+    []
+  );
+
+  const clipVisionModel = useMemo(
+    () => clipVisionOptions.find((o) => o.value === currentCLIPVisionModel),
+    [clipVisionOptions, currentCLIPVisionModel]
+  );
+
   return (
-    <Tooltip label={value?.description}>
-      <FormControl isDisabled={!isEnabled} isInvalid={!value || mainModel?.base !== modelConfig?.base}>
-        <Combobox
-          options={options}
-          placeholder={t('controlnet.selectModel')}
-          value={value}
-          onChange={onChange}
-          noOptionsMessage={noOptionsMessage}
-        />
-      </FormControl>
-    </Tooltip>
+    <Flex sx={{ gap: 2 }}>
+      <Tooltip label={value?.description}>
+        <FormControl
+          isDisabled={!isEnabled}
+          isInvalid={!value || mainModel?.base !== modelConfig?.base}
+          sx={{ width: '100%' }}
+        >
+          <Combobox
+            options={options}
+            placeholder={t('controlnet.selectModel')}
+            value={value}
+            onChange={onChange}
+            noOptionsMessage={noOptionsMessage}
+          />
+        </FormControl>
+      </Tooltip>
+      {modelConfig?.type === 'ip_adapter' && modelConfig.format === 'checkpoint' && (
+        <FormControl
+          isDisabled={!isEnabled}
+          isInvalid={!value || mainModel?.base !== modelConfig?.base}
+          sx={{ width: 'max-content', minWidth: 28 }}
+        >
+          <Combobox
+            options={clipVisionOptions}
+            placeholder={t('controlnet.selectCLIPVisionModel')}
+            value={clipVisionModel}
+            onChange={onCLIPVisionModelChange}
+          />
+        </FormControl>
+      )}
+    </Flex>
   );
 };
 

invokeai/frontend/web/src/features/controlAdapters/hooks/useControlAdapterCLIPVisionModel.ts

@@ -0,0 +1,24 @@
+import { createMemoizedSelector } from 'app/store/createMemoizedSelector';
+import { useAppSelector } from 'app/store/storeHooks';
+import {
+  selectControlAdapterById,
+  selectControlAdaptersSlice,
+} from 'features/controlAdapters/store/controlAdaptersSlice';
+import { useMemo } from 'react';
+
+export const useControlAdapterCLIPVisionModel = (id: string) => {
+  const selector = useMemo(
+    () =>
+      createMemoizedSelector(selectControlAdaptersSlice, (controlAdapters) => {
+        const cn = selectControlAdapterById(controlAdapters, id);
+        if (cn && cn?.type === 'ip_adapter') {
+          return cn.clipVisionModel;
+        }
+      }),
+    [id]
+  );
+
+  const clipVisionModel = useAppSelector(selector);
+
+  return clipVisionModel;
+};

invokeai/frontend/web/src/features/controlAdapters/store/controlAdaptersSlice.ts

@@ -2,10 +2,11 @@ import type { PayloadAction, Update } from '@reduxjs/toolkit';
 import { createEntityAdapter, createSlice, isAnyOf } from '@reduxjs/toolkit';
 import { getSelectorsOptions } from 'app/store/createMemoizedSelector';
 import type { PersistConfig, RootState } from 'app/store/store';
+import { deepClone } from 'common/util/deepClone';
 import { buildControlAdapter } from 'features/controlAdapters/util/buildControlAdapter';
 import { buildControlAdapterProcessor } from 'features/controlAdapters/util/buildControlAdapterProcessor';
 import { zModelIdentifierField } from 'features/nodes/types/common';
-import { cloneDeep, merge, uniq } from 'lodash-es';
+import { merge, uniq } from 'lodash-es';
 import type { ControlNetModelConfig, IPAdapterModelConfig, T2IAdapterModelConfig } from 'services/api/types';
 import { socketInvocationError } from 'services/events/actions';
 import { v4 as uuidv4 } from 'uuid';
@@ -13,6 +14,7 @@ import { v4 as uuidv4 } from 'uuid';
 import { controlAdapterImageProcessed } from './actions';
 import { CONTROLNET_PROCESSORS } from './constants';
 import type {
+  CLIPVisionModel,
   ControlAdapterConfig,
   ControlAdapterProcessorType,
   ControlAdaptersState,
@@ -114,7 +116,7 @@ export const controlAdaptersSlice = createSlice({
         if (!controlAdapter) {
           return;
         }
-        const newControlAdapter = merge(cloneDeep(controlAdapter), {
+        const newControlAdapter = merge(deepClone(controlAdapter), {
           id: newId,
           isEnabled: true,
         });
@@ -243,6 +245,13 @@ export const controlAdaptersSlice = createSlice({
       }
       caAdapter.updateOne(state, { id, changes: { controlMode } });
     },
+    controlAdapterCLIPVisionModelChanged: (
+      state,
+      action: PayloadAction<{ id: string; clipVisionModel: CLIPVisionModel }>
+    ) => {
+      const { id, clipVisionModel } = action.payload;
+      caAdapter.updateOne(state, { id, changes: { clipVisionModel } });
+    },
     controlAdapterResizeModeChanged: (
       state,
       action: PayloadAction<{
@@ -270,7 +279,7 @@ export const controlAdaptersSlice = createSlice({
         return;
       }
 
-      const processorNode = merge(cloneDeep(cn.processorNode), params);
+      const processorNode = merge(deepClone(cn.processorNode), params);
 
       caAdapter.updateOne(state, {
         id,
@@ -293,7 +302,7 @@ export const controlAdaptersSlice = createSlice({
         return;
       }
 
-      const processorNode = cloneDeep(
+      const processorNode = deepClone(
         CONTROLNET_PROCESSORS[processorType].buildDefaults(cn.model?.base)
       ) as RequiredControlAdapterProcessorNode;
 
@@ -333,7 +342,7 @@ export const controlAdaptersSlice = createSlice({
       caAdapter.updateOne(state, update);
     },
     controlAdaptersReset: () => {
-      return cloneDeep(initialControlAdaptersState);
+      return deepClone(initialControlAdaptersState);
     },
     pendingControlImagesCleared: (state) => {
       state.pendingControlImages = [];
@@ -380,6 +389,7 @@ export const {
   controlAdapterProcessedImageChanged,
   controlAdapterIsEnabledChanged,
   controlAdapterModelChanged,
+  controlAdapterCLIPVisionModelChanged,
   controlAdapterWeightChanged,
   controlAdapterBeginStepPctChanged,
   controlAdapterEndStepPctChanged,
@@ -406,7 +416,7 @@ const migrateControlAdaptersState = (state: any): any => {
     state._version = 1;
   }
   if (state._version === 1) {
-    state = cloneDeep(initialControlAdaptersState);
+    state = deepClone(initialControlAdaptersState);
   }
   return state;
 };

invokeai/frontend/web/src/features/controlAdapters/store/types.ts

@@ -243,12 +243,15 @@ export type T2IAdapterConfig = {
   shouldAutoConfig: boolean;
 };
 
+export type CLIPVisionModel = 'ViT-H' | 'ViT-G';
+
 export type IPAdapterConfig = {
   type: 'ip_adapter';
   id: string;
   isEnabled: boolean;
   controlImage: string | null;
   model: ParameterIPAdapterModel | null;
+  clipVisionModel: CLIPVisionModel;
   weight: number;
   beginStepPct: number;
   endStepPct: number;

invokeai/frontend/web/src/features/controlAdapters/util/buildControlAdapter.ts

@@ -1,3 +1,4 @@
+import { deepClone } from 'common/util/deepClone';
 import { CONTROLNET_PROCESSORS } from 'features/controlAdapters/store/constants';
 import type {
   ControlAdapterConfig,
@@ -7,7 +8,7 @@ import type {
   RequiredCannyImageProcessorInvocation,
   T2IAdapterConfig,
 } from 'features/controlAdapters/store/types';
-import { cloneDeep, merge } from 'lodash-es';
+import { merge } from 'lodash-es';
 
 export const initialControlNet: Omit<ControlNetConfig, 'id'> = {
   type: 'controlnet',
@@ -45,6 +46,7 @@ export const initialIPAdapter: Omit<IPAdapterConfig, 'id'> = {
   isEnabled: true,
   controlImage: null,
   model: null,
+  clipVisionModel: 'ViT-H',
   weight: 1,
   beginStepPct: 0,
   endStepPct: 1,
@@ -57,11 +59,11 @@ export const buildControlAdapter = (
 ): ControlAdapterConfig => {
   switch (type) {
     case 'controlnet':
-      return merge(cloneDeep(initialControlNet), { id, ...overrides });
+      return merge(deepClone(initialControlNet), { id, ...overrides });
     case 't2i_adapter':
-      return merge(cloneDeep(initialT2IAdapter), { id, ...overrides });
+      return merge(deepClone(initialT2IAdapter), { id, ...overrides });
     case 'ip_adapter':
-      return merge(cloneDeep(initialIPAdapter), { id, ...overrides });
+      return merge(deepClone(initialIPAdapter), { id, ...overrides });
     default:
       throw new Error(`Unknown control adapter type: ${type}`);
   }

invokeai/frontend/web/src/features/lora/store/loraSlice.ts

@@ -1,9 +1,9 @@
 import type { PayloadAction } from '@reduxjs/toolkit';
 import { createSlice } from '@reduxjs/toolkit';
 import type { PersistConfig, RootState } from 'app/store/store';
+import { deepClone } from 'common/util/deepClone';
 import { zModelIdentifierField } from 'features/nodes/types/common';
 import type { ParameterLoRAModel } from 'features/parameters/types/parameterSchemas';
-import { cloneDeep } from 'lodash-es';
 import type { LoRAModelConfig } from 'services/api/types';
 
 export type LoRA = {
@@ -58,7 +58,7 @@ export const loraSlice = createSlice({
       }
       lora.isEnabled = isEnabled;
     },
-    lorasReset: () => cloneDeep(initialLoraState),
+    lorasReset: () => deepClone(initialLoraState),
   },
 });
 
@@ -74,7 +74,7 @@ const migrateLoRAState = (state: any): any => {
   }
   if (state._version === 1) {
     // Model type has changed, so we need to reset the state - too risky to migrate
-    state = cloneDeep(initialLoraState);
+    state = deepClone(initialLoraState);
   }
   return state;
 };

invokeai/frontend/web/src/features/metadata/util/parsers.ts

@@ -372,6 +372,7 @@ const parseIPAdapter: MetadataParseFunc<IPAdapterConfigMetadata> = async (metada
     type: 'ip_adapter',
     isEnabled: true,
     model: zModelIdentifierField.parse(ipAdapterModel),
+    clipVisionModel: 'ViT-H',
     controlImage: image?.image_name ?? null,
     weight: weight ?? initialIPAdapter.weight,
     beginStepPct: begin_step_percent ?? initialIPAdapter.beginStepPct,

invokeai/frontend/web/src/features/modelManagerV2/store/modelManagerV2Slice.ts

@@ -3,7 +3,7 @@ import { createSlice } from '@reduxjs/toolkit';
 import type { PersistConfig } from 'app/store/store';
 import type { ModelType } from 'services/api/types';
 
-export type FilterableModelType = Exclude<ModelType, 'onnx' | 'clip_vision'>;
+export type FilterableModelType = Exclude<ModelType, 'onnx' | 'clip_vision'> | 'refiner';
 
 type ModelManagerState = {
   _version: 1;

invokeai/frontend/web/src/features/modelManagerV2/subpanels/AddModelPanel/ModelInstallQueue/ModelInstallQueueItem.tsx

@@ -87,6 +87,10 @@ export const ModelInstallQueueItem = (props: ModelListItemProps) => {
   }, [installJob.source]);
 
   const progressValue = useMemo(() => {
+    if (installJob.status === 'completed' || installJob.status === 'error' || installJob.status === 'cancelled') {
+      return 100;
+    }
+
     if (isNil(installJob.bytes) || isNil(installJob.total_bytes)) {
       return null;
     }
@@ -96,7 +100,7 @@ export const ModelInstallQueueItem = (props: ModelListItemProps) => {
     }
 
     return (installJob.bytes / installJob.total_bytes) * 100;
-  }, [installJob.bytes, installJob.total_bytes]);
+  }, [installJob.bytes, installJob.status, installJob.total_bytes]);
 
   return (
     <Flex gap={3} w="full" alignItems="center">

invokeai/frontend/web/src/features/modelManagerV2/subpanels/AddModelPanel/ScanFolder/ScanFolderResultItem.tsx

@@ -1,48 +1,19 @@
 import { Badge, Box, Flex, IconButton, Text } from '@invoke-ai/ui-library';
-import { useAppDispatch } from 'app/store/storeHooks';
-import { addToast } from 'features/system/store/systemSlice';
-import { makeToast } from 'features/system/util/makeToast';
 import { useCallback } from 'react';
 import { useTranslation } from 'react-i18next';
 import { PiPlusBold } from 'react-icons/pi';
 import type { ScanFolderResponse } from 'services/api/endpoints/models';
-import { useInstallModelMutation } from 'services/api/endpoints/models';
 
 type Props = {
   result: ScanFolderResponse[number];
+  installModel: (source: string) => void;
 };
-export const ScanModelResultItem = ({ result }: Props) => {
+export const ScanModelResultItem = ({ result, installModel }: Props) => {
   const { t } = useTranslation();
-  const dispatch = useAppDispatch();
 
-  const [installModel] = useInstallModelMutation();
-
-  const handleQuickAdd = useCallback(() => {
-    installModel({ source: result.path })
-      .unwrap()
-      .then((_) => {
-        dispatch(
-          addToast(
-            makeToast({
-              title: t('toast.modelAddedSimple'),
-              status: 'success',
-            })
-          )
-        );
-      })
-      .catch((error) => {
-        if (error) {
-          dispatch(
-            addToast(
-              makeToast({
-                title: `${error.data.detail} `,
-                status: 'error',
-              })
-            )
-          );
-        }
-      });
-  }, [installModel, result, dispatch, t]);
+  const handleInstall = useCallback(() => {
+    installModel(result.path);
+  }, [installModel, result]);
 
   return (
     <Flex alignItems="center" justifyContent="space-between" w="100%" gap={3}>
@@ -54,7 +25,7 @@ export const ScanModelResultItem = ({ result }: Props) => {
         {result.is_installed ? (
           <Badge>{t('common.installed')}</Badge>
         ) : (
-          <IconButton aria-label={t('modelManager.install')} icon={<PiPlusBold />} onClick={handleQuickAdd} size="sm" />
+          <IconButton aria-label={t('modelManager.install')} icon={<PiPlusBold />} onClick={handleInstall} size="sm" />
         )}
       </Box>
     </Flex>

invokeai/frontend/web/src/features/modelManagerV2/subpanels/AddModelPanel/ScanFolder/ScanFolderResults.tsx

@@ -1,7 +1,10 @@
 import {
   Button,
+  Checkbox,
   Divider,
   Flex,
+  FormControl,
+  FormLabel,
   Heading,
   IconButton,
   Input,
@@ -12,7 +15,7 @@ import { useAppDispatch } from 'app/store/storeHooks';
 import ScrollableContent from 'common/components/OverlayScrollbars/ScrollableContent';
 import { addToast } from 'features/system/store/systemSlice';
 import { makeToast } from 'features/system/util/makeToast';
-import type { ChangeEventHandler } from 'react';
+import type { ChangeEvent, ChangeEventHandler } from 'react';
 import { useCallback, useMemo, useState } from 'react';
 import { useTranslation } from 'react-i18next';
 import { PiXBold } from 'react-icons/pi';
@@ -28,7 +31,7 @@ export const ScanModelsResults = ({ results }: ScanModelResultsProps) => {
   const { t } = useTranslation();
   const [searchTerm, setSearchTerm] = useState('');
   const dispatch = useAppDispatch();
-
+  const [inplace, setInplace] = useState(true);
   const [installModel] = useInstallModelMutation();
 
   const filteredResults = useMemo(() => {
@@ -42,6 +45,10 @@ export const ScanModelsResults = ({ results }: ScanModelResultsProps) => {
     setSearchTerm(e.target.value.trim());
   }, []);
 
+  const onChangeInplace = useCallback((e: ChangeEvent<HTMLInputElement>) => {
+    setInplace(e.target.checked);
+  }, []);
+
   const clearSearch = useCallback(() => {
     setSearchTerm('');
   }, []);
@@ -51,7 +58,7 @@ export const ScanModelsResults = ({ results }: ScanModelResultsProps) => {
       if (result.is_installed) {
         continue;
       }
-      installModel({ source: result.path })
+      installModel({ source: result.path, inplace })
         .unwrap()
         .then((_) => {
           dispatch(
@@ -76,7 +83,37 @@ export const ScanModelsResults = ({ results }: ScanModelResultsProps) => {
           }
         });
     }
-  }, [installModel, filteredResults, dispatch, t]);
+  }, [filteredResults, installModel, inplace, dispatch, t]);
+
+  const handleInstallOne = useCallback(
+    (source: string) => {
+      installModel({ source, inplace })
+        .unwrap()
+        .then((_) => {
+          dispatch(
+            addToast(
+              makeToast({
+                title: t('toast.modelAddedSimple'),
+                status: 'success',
+              })
+            )
+          );
+        })
+        .catch((error) => {
+          if (error) {
+            dispatch(
+              addToast(
+                makeToast({
+                  title: `${error.data.detail} `,
+                  status: 'error',
+                })
+              )
+            );
+          }
+        });
+    },
+    [installModel, inplace, dispatch, t]
+  );
 
   return (
     <>
@@ -85,6 +122,10 @@ export const ScanModelsResults = ({ results }: ScanModelResultsProps) => {
         <Flex justifyContent="space-between" alignItems="center">
           <Heading size="sm">{t('modelManager.scanResults')}</Heading>
           <Flex alignItems="center" gap={3}>
+            <FormControl w="min-content">
+              <FormLabel m={0}>{t('modelManager.inplaceInstall')}</FormLabel>
+              <Checkbox isChecked={inplace} onChange={onChangeInplace} size="md" />
+            </FormControl>
             <Button size="sm" onClick={handleAddAll} isDisabled={filteredResults.length === 0}>
               {t('modelManager.installAll')}
             </Button>
@@ -116,7 +157,7 @@ export const ScanModelsResults = ({ results }: ScanModelResultsProps) => {
           <ScrollableContent>
             <Flex flexDir="column" gap={3}>
               {filteredResults.map((result) => (
-                <ScanModelResultItem key={result.path} result={result} />
+                <ScanModelResultItem key={result.path} result={result} installModel={handleInstallOne} />
               ))}
             </Flex>
           </ScrollableContent>

invokeai/frontend/web/src/features/modelManagerV2/subpanels/ModelManagerPanel/ModelList.tsx

@@ -1,6 +1,7 @@
-import { Flex } from '@invoke-ai/ui-library';
+import { Flex, Text } from '@invoke-ai/ui-library';
 import { useAppSelector } from 'app/store/storeHooks';
 import ScrollableContent from 'common/components/OverlayScrollbars/ScrollableContent';
+import type { FilterableModelType } from 'features/modelManagerV2/store/modelManagerV2Slice';
 import { memo, useMemo } from 'react';
 import { useTranslation } from 'react-i18next';
 import {
@@ -9,10 +10,11 @@ import {
   useIPAdapterModels,
   useLoRAModels,
   useMainModels,
+  useRefinerModels,
   useT2IAdapterModels,
   useVAEModels,
 } from 'services/api/hooks/modelsByType';
-import type { AnyModelConfig, ModelType } from 'services/api/types';
+import type { AnyModelConfig } from 'services/api/types';
 
 import { FetchingModelsLoader } from './FetchingModelsLoader';
 import { ModelListWrapper } from './ModelListWrapper';
@@ -27,6 +29,12 @@ const ModelList = () => {
     [mainModels, searchTerm, filteredModelType]
   );
 
+  const [refinerModels, { isLoading: isLoadingRefinerModels }] = useRefinerModels();
+  const filteredRefinerModels = useMemo(
+    () => modelsFilter(refinerModels, searchTerm, filteredModelType),
+    [refinerModels, searchTerm, filteredModelType]
+  );
+
   const [loraModels, { isLoading: isLoadingLoRAModels }] = useLoRAModels();
   const filteredLoRAModels = useMemo(
     () => modelsFilter(loraModels, searchTerm, filteredModelType),
@@ -63,6 +71,28 @@ const ModelList = () => {
     [vaeModels, searchTerm, filteredModelType]
   );
 
+  const totalFilteredModels = useMemo(() => {
+    return (
+      filteredMainModels.length +
+      filteredRefinerModels.length +
+      filteredLoRAModels.length +
+      filteredEmbeddingModels.length +
+      filteredControlNetModels.length +
+      filteredT2IAdapterModels.length +
+      filteredIPAdapterModels.length +
+      filteredVAEModels.length
+    );
+  }, [
+    filteredControlNetModels.length,
+    filteredEmbeddingModels.length,
+    filteredIPAdapterModels.length,
+    filteredLoRAModels.length,
+    filteredMainModels.length,
+    filteredRefinerModels.length,
+    filteredT2IAdapterModels.length,
+    filteredVAEModels.length,
+  ]);
+
   return (
     <ScrollableContent>
       <Flex flexDirection="column" w="full" h="full" gap={4}>
@@ -71,6 +101,11 @@ const ModelList = () => {
         {!isLoadingMainModels && filteredMainModels.length > 0 && (
           <ModelListWrapper title={t('modelManager.main')} modelList={filteredMainModels} key="main" />
         )}
+        {/* Refiner Model List */}
+        {isLoadingRefinerModels && <FetchingModelsLoader loadingMessage="Loading Refiner Models..." />}
+        {!isLoadingRefinerModels && filteredRefinerModels.length > 0 && (
+          <ModelListWrapper title={t('sdxl.refiner')} modelList={filteredRefinerModels} key="refiner" />
+        )}
         {/* LoRAs List */}
         {isLoadingLoRAModels && <FetchingModelsLoader loadingMessage="Loading LoRAs..." />}
         {!isLoadingLoRAModels && filteredLoRAModels.length > 0 && (
@@ -108,6 +143,11 @@ const ModelList = () => {
         {!isLoadingT2IAdapterModels && filteredT2IAdapterModels.length > 0 && (
           <ModelListWrapper title={t('common.t2iAdapter')} modelList={filteredT2IAdapterModels} key="t2i-adapters" />
         )}
+        {totalFilteredModels === 0 && (
+          <Flex w="full" h="full" alignItems="center" justifyContent="center">
+            <Text>{t('modelManager.noMatchingModels')}</Text>
+          </Flex>
+        )}
       </Flex>
     </ScrollableContent>
   );
@@ -118,12 +158,24 @@ export default memo(ModelList);
 const modelsFilter = <T extends AnyModelConfig>(
   data: T[],
   nameFilter: string,
-  filteredModelType: ModelType | null
+  filteredModelType: FilterableModelType | null
 ): T[] => {
   return data.filter((model) => {
     const matchesFilter = model.name.toLowerCase().includes(nameFilter.toLowerCase());
-    const matchesType = filteredModelType ? model.type === filteredModelType : true;
+    const matchesType = getMatchesType(model, filteredModelType);
 
     return matchesFilter && matchesType;
   });
 };
+
+const getMatchesType = (modelConfig: AnyModelConfig, filteredModelType: FilterableModelType | null): boolean => {
+  if (filteredModelType === 'refiner') {
+    return modelConfig.base === 'sdxl-refiner';
+  }
+
+  if (filteredModelType === 'main' && modelConfig.base === 'sdxl-refiner') {
+    return false;
+  }
+
+  return filteredModelType ? modelConfig.type === filteredModelType : true;
+};

invokeai/frontend/web/src/features/modelManagerV2/subpanels/ModelManagerPanel/ModelListItem.tsx

@@ -90,11 +90,13 @@ const ModelListItem = (props: ModelListItemProps) => {
       cursor="pointer"
       onClick={handleSelectModel}
     >
-      <Flex gap={2} w="full" h="full">
+      <Flex gap={2} w="full" h="full" minW={0}>
         <ModelImage image_url={model.cover_image} />
-        <Flex gap={1} alignItems="flex-start" flexDir="column" w="full">
+        <Flex gap={1} alignItems="flex-start" flexDir="column" w="full" minW={0}>
           <Flex gap={2} w="full" alignItems="flex-start">
-            <Text fontWeight="semibold">{model.name}</Text>
+            <Text fontWeight="semibold" noOfLines={1} wordBreak="break-all">
+              {model.name}
+            </Text>
             <Spacer />
           </Flex>
           <Text variant="subtext" noOfLines={1}>

invokeai/frontend/web/src/features/modelManagerV2/subpanels/ModelManagerPanel/ModelTypeFilter.tsx

@@ -13,6 +13,7 @@ export const ModelTypeFilter = () => {
   const MODEL_TYPE_LABELS: Record<FilterableModelType, string> = useMemo(
     () => ({
       main: t('modelManager.main'),
+      refiner: t('sdxl.refiner'),
       lora: 'LoRA',
       embedding: t('modelManager.textualInversions'),
       controlnet: 'ControlNet',

invokeai/frontend/web/src/features/modelManagerV2/subpanels/ModelPanel/Model.tsx

@@ -87,9 +87,9 @@ export const Model = () => {
     <Flex flexDir="column" gap={4}>
       <Flex alignItems="flex-start" gap={4}>
         <ModelImageUpload model_key={selectedModelKey} model_image={data.cover_image} />
-        <Flex flexDir="column" gap={1} flexGrow={1}>
+        <Flex flexDir="column" gap={1} flexGrow={1} minW={0}>
           <Flex gap={2}>
-            <Heading as="h2" fontSize="lg">
+            <Heading as="h2" fontSize="lg" noOfLines={1} wordBreak="break-all">
               {data.name}
             </Heading>
             <Spacer />
@@ -114,7 +114,7 @@ export const Model = () => {
             )}
           </Flex>
           {data.source && (
-            <Text variant="subtext">
+            <Text variant="subtext" noOfLines={1} wordBreak="break-all">
               {t('modelManager.source')}: {data?.source}
             </Text>
           )}

invokeai/frontend/web/src/features/modelManagerV2/subpanels/ModelPanel/ModelAttrView.tsx

@@ -9,7 +9,9 @@ export const ModelAttrView = ({ label, value }: Props) => {
   return (
     <FormControl flexDir="column" alignItems="flex-start" gap={0}>
       <FormLabel>{label}</FormLabel>
-      <Text fontSize="md">{value || '-'}</Text>
+      <Text fontSize="md" noOfLines={1} wordBreak="break-all">
+        {value || '-'}
+      </Text>
     </FormControl>
   );
 };

invokeai/frontend/web/src/features/modelManagerV2/subpanels/ModelPanel/ModelView.tsx

@@ -53,7 +53,7 @@ export const ModelView = () => {
             </>
           )}
 
-          {data.type === 'ip_adapter' && (
+          {data.type === 'ip_adapter' && data.format === 'invokeai' && (
             <Flex gap={2}>
               <ModelAttrView label={t('modelManager.imageEncoderModelId')} value={data.image_encoder_model_id} />
             </Flex>

invokeai/frontend/web/src/features/nodes/store/nodesSlice.ts

@@ -1,6 +1,7 @@
 import type { PayloadAction } from '@reduxjs/toolkit';
 import { createSlice, isAnyOf } from '@reduxjs/toolkit';
 import type { PersistConfig, RootState } from 'app/store/store';
+import { deepClone } from 'common/util/deepClone';
 import { workflowLoaded } from 'features/nodes/store/actions';
 import { SHARED_NODE_PROPERTIES } from 'features/nodes/types/constants';
 import type {
@@ -44,7 +45,7 @@ import {
 } from 'features/nodes/types/field';
 import type { AnyNode, InvocationTemplate, NodeExecutionState } from 'features/nodes/types/invocation';
 import { isInvocationNode, isNotesNode, zNodeStatus } from 'features/nodes/types/invocation';
-import { cloneDeep, forEach } from 'lodash-es';
+import { forEach } from 'lodash-es';
 import type {
   Connection,
   Edge,
@@ -571,8 +572,23 @@ export const nodesSlice = createSlice({
       );
     },
     selectionCopied: (state) => {
-      state.nodesToCopy = state.nodes.filter((n) => n.selected).map(cloneDeep);
-      state.edgesToCopy = state.edges.filter((e) => e.selected).map(cloneDeep);
+      const nodesToCopy: AnyNode[] = [];
+      const edgesToCopy: Edge[] = [];
+
+      for (const node of state.nodes) {
+        if (node.selected) {
+          nodesToCopy.push(deepClone(node));
+        }
+      }
+
+      for (const edge of state.edges) {
+        if (edge.selected) {
+          edgesToCopy.push(deepClone(edge));
+        }
+      }
+
+      state.nodesToCopy = nodesToCopy;
+      state.edgesToCopy = edgesToCopy;
 
       if (state.nodesToCopy.length > 0) {
         const averagePosition = { x: 0, y: 0 };
@@ -594,11 +610,21 @@ export const nodesSlice = createSlice({
     },
     selectionPasted: (state, action: PayloadAction<{ cursorPosition?: XYPosition }>) => {
       const { cursorPosition } = action.payload;
-      const newNodes = state.nodesToCopy.map(cloneDeep);
+      const newNodes: AnyNode[] = [];
+
+      for (const node of state.nodesToCopy) {
+        newNodes.push(deepClone(node));
+      }
+
       const oldNodeIds = newNodes.map((n) => n.data.id);
-      const newEdges = state.edgesToCopy
-        .filter((e) => oldNodeIds.includes(e.source) && oldNodeIds.includes(e.target))
-        .map(cloneDeep);
+
+      const newEdges: Edge[] = [];
+
+      for (const edge of state.edgesToCopy) {
+        if (oldNodeIds.includes(edge.source) && oldNodeIds.includes(edge.target)) {
+          newEdges.push(deepClone(edge));
+        }
+      }
 
       newEdges.forEach((e) => (e.selected = true));
 

invokeai/frontend/web/src/features/nodes/store/workflowSlice.ts

@@ -1,6 +1,7 @@
 import type { PayloadAction } from '@reduxjs/toolkit';
 import { createSlice } from '@reduxjs/toolkit';
 import type { PersistConfig, RootState } from 'app/store/store';
+import { deepClone } from 'common/util/deepClone';
 import { workflowLoaded } from 'features/nodes/store/actions';
 import { isAnyNodeOrEdgeMutation, nodeEditorReset, nodesChanged, nodesDeleted } from 'features/nodes/store/nodesSlice';
 import type {
@@ -11,7 +12,7 @@ import type {
 import type { FieldIdentifier } from 'features/nodes/types/field';
 import { isInvocationNode } from 'features/nodes/types/invocation';
 import type { WorkflowCategory, WorkflowV3 } from 'features/nodes/types/workflow';
-import { cloneDeep, isEqual, omit, uniqBy } from 'lodash-es';
+import { isEqual, omit, uniqBy } from 'lodash-es';
 
 const blankWorkflow: Omit<WorkflowV3, 'nodes' | 'edges'> = {
   name: '',
@@ -131,8 +132,8 @@ export const workflowSlice = createSlice({
       });
 
       return {
-        ...cloneDeep(initialWorkflowState),
-        ...cloneDeep(workflowExtra),
+        ...deepClone(initialWorkflowState),
+        ...deepClone(workflowExtra),
         originalExposedFieldValues,
         mode: state.mode,
       };
@@ -144,7 +145,7 @@ export const workflowSlice = createSlice({
       });
     });
 
-    builder.addCase(nodeEditorReset, () => cloneDeep(initialWorkflowState));
+    builder.addCase(nodeEditorReset, () => deepClone(initialWorkflowState));
 
     builder.addCase(nodesChanged, (state, action) => {
       // Not all changes to nodes should result in the workflow being marked touched

invokeai/frontend/web/src/features/nodes/util/graph/addIPAdapterToLinearGraph.ts

@@ -48,7 +48,7 @@ export const addIPAdapterToLinearGraph = async (
       if (!ipAdapter.model) {
         return;
       }
-      const { id, weight, model, beginStepPct, endStepPct, controlImage } = ipAdapter;
+      const { id, weight, model, clipVisionModel, beginStepPct, endStepPct, controlImage } = ipAdapter;
 
       assert(controlImage, 'IP Adapter image is required');
 
@@ -58,6 +58,7 @@ export const addIPAdapterToLinearGraph = async (
         is_intermediate: true,
         weight: weight,
         ip_adapter_model: model,
+        clip_vision_model: clipVisionModel,
         begin_step_percent: beginStepPct,
         end_step_percent: endStepPct,
         image: {
@@ -83,7 +84,7 @@ export const addIPAdapterToLinearGraph = async (
 };
 
 const buildIPAdapterMetadata = (ipAdapter: IPAdapterConfig): S['IPAdapterMetadataField'] => {
-  const { controlImage, beginStepPct, endStepPct, model, weight } = ipAdapter;
+  const { controlImage, beginStepPct, endStepPct, model, clipVisionModel, weight } = ipAdapter;
 
   assert(model, 'IP Adapter model is required');
 
@@ -99,6 +100,7 @@ const buildIPAdapterMetadata = (ipAdapter: IPAdapterConfig): S['IPAdapterMetadat
 
   return {
     ip_adapter_model: model,
+    clip_vision_model: clipVisionModel,
     weight,
     begin_step_percent: beginStepPct,
     end_step_percent: endStepPct,

invokeai/frontend/web/src/features/nodes/util/graph/buildCanvasOutpaintGraph.ts

@@ -65,6 +65,11 @@ export const buildCanvasOutpaintGraph = async (
     infillTileSize,
     infillPatchmatchDownscaleSize,
     infillMethod,
+    // infillMosaicTileWidth,
+    // infillMosaicTileHeight,
+    // infillMosaicMinColor,
+    // infillMosaicMaxColor,
+    infillColorValue,
     clipSkip,
     seamlessXAxis,
     seamlessYAxis,
@@ -356,6 +361,28 @@ export const buildCanvasOutpaintGraph = async (
     };
   }
 
+  // TODO: add mosaic back
+  // if (infillMethod === 'mosaic') {
+  //   graph.nodes[INPAINT_INFILL] = {
+  //     type: 'infill_mosaic',
+  //     id: INPAINT_INFILL,
+  //     is_intermediate,
+  //     tile_width: infillMosaicTileWidth,
+  //     tile_height: infillMosaicTileHeight,
+  //     min_color: infillMosaicMinColor,
+  //     max_color: infillMosaicMaxColor,
+  //   };
+  // }
+
+  if (infillMethod === 'color') {
+    graph.nodes[INPAINT_INFILL] = {
+      type: 'infill_rgba',
+      id: INPAINT_INFILL,
+      color: infillColorValue,
+      is_intermediate,
+    };
+  }
+
   // Handle Scale Before Processing
   if (isUsingScaledDimensions) {
     const scaledWidth: number = scaledBoundingBoxDimensions.width;

invokeai/frontend/web/src/features/nodes/util/graph/buildCanvasSDXLOutpaintGraph.ts

@@ -66,6 +66,11 @@ export const buildCanvasSDXLOutpaintGraph = async (
     infillTileSize,
     infillPatchmatchDownscaleSize,
     infillMethod,
+    // infillMosaicTileWidth,
+    // infillMosaicTileHeight,
+    // infillMosaicMinColor,
+    // infillMosaicMaxColor,
+    infillColorValue,
     seamlessXAxis,
     seamlessYAxis,
     canvasCoherenceMode,
@@ -365,6 +370,28 @@ export const buildCanvasSDXLOutpaintGraph = async (
     };
   }
 
+  // TODO: add mosaic back
+  // if (infillMethod === 'mosaic') {
+  //   graph.nodes[INPAINT_INFILL] = {
+  //     type: 'infill_mosaic',
+  //     id: INPAINT_INFILL,
+  //     is_intermediate,
+  //     tile_width: infillMosaicTileWidth,
+  //     tile_height: infillMosaicTileHeight,
+  //     min_color: infillMosaicMinColor,
+  //     max_color: infillMosaicMaxColor,
+  //   };
+  // }
+
+  if (infillMethod === 'color') {
+    graph.nodes[INPAINT_INFILL] = {
+      type: 'infill_rgba',
+      id: INPAINT_INFILL,
+      is_intermediate,
+      color: infillColorValue,
+    };
+  }
+
   // Handle Scale Before Processing
   if (isUsingScaledDimensions) {
     const scaledWidth: number = scaledBoundingBoxDimensions.width;

invokeai/frontend/web/src/features/nodes/util/node/nodeUpdate.ts

@@ -1,8 +1,9 @@
+import { deepClone } from 'common/util/deepClone';
 import { satisfies } from 'compare-versions';
 import { NodeUpdateError } from 'features/nodes/types/error';
 import type { InvocationNode, InvocationTemplate } from 'features/nodes/types/invocation';
 import { zParsedSemver } from 'features/nodes/types/semver';
-import { cloneDeep, defaultsDeep, keys, pick } from 'lodash-es';
+import { defaultsDeep, keys, pick } from 'lodash-es';
 
 import { buildInvocationNode } from './buildInvocationNode';
 
@@ -50,7 +51,7 @@ export const updateNode = (node: InvocationNode, template: InvocationTemplate):
   // The updateability of a node, via semver comparison, relies on the this kind of recursive merge
   // being valid. We rely on the template's major version to be majorly incremented if this kind of
   // merge would result in an invalid node.
-  const clone = cloneDeep(node);
+  const clone = deepClone(node);
   clone.data.version = template.version;
   defaultsDeep(clone, defaults); // mutates!
 

invokeai/frontend/web/src/features/nodes/util/workflow/buildWorkflow.ts

@@ -1,11 +1,12 @@
 import { logger } from 'app/logging/logger';
+import { deepClone } from 'common/util/deepClone';
 import { parseify } from 'common/util/serialize';
 import type { NodesState, WorkflowsState } from 'features/nodes/store/types';
 import { isInvocationNode, isNotesNode } from 'features/nodes/types/invocation';
 import type { WorkflowV3 } from 'features/nodes/types/workflow';
 import { zWorkflowV3 } from 'features/nodes/types/workflow';
 import i18n from 'i18n';
-import { cloneDeep, pick } from 'lodash-es';
+import { pick } from 'lodash-es';
 import { fromZodError } from 'zod-validation-error';
 
 export type BuildWorkflowArg = {
@@ -30,7 +31,7 @@ const workflowKeys = [
 type BuildWorkflowFunction = (arg: BuildWorkflowArg) => WorkflowV3;
 
 export const buildWorkflowFast: BuildWorkflowFunction = ({ nodes, edges, workflow }: BuildWorkflowArg): WorkflowV3 => {
-  const clonedWorkflow = pick(cloneDeep(workflow), workflowKeys);
+  const clonedWorkflow = pick(deepClone(workflow), workflowKeys);
 
   const newWorkflow: WorkflowV3 = {
     ...clonedWorkflow,
@@ -43,14 +44,14 @@ export const buildWorkflowFast: BuildWorkflowFunction = ({ nodes, edges, workflo
       newWorkflow.nodes.push({
         id: node.id,
         type: node.type,
-        data: cloneDeep(node.data),
+        data: deepClone(node.data),
         position: { ...node.position },
       });
     } else if (isNotesNode(node) && node.type) {
       newWorkflow.nodes.push({
         id: node.id,
         type: node.type,
-        data: cloneDeep(node.data),
+        data: deepClone(node.data),
         position: { ...node.position },
       });
     }

invokeai/frontend/web/src/features/nodes/util/workflow/migrations.ts

@@ -1,4 +1,5 @@
 import { $store } from 'app/store/nanostores/store';
+import { deepClone } from 'common/util/deepClone';
 import { WorkflowMigrationError, WorkflowVersionError } from 'features/nodes/types/error';
 import type { FieldType } from 'features/nodes/types/field';
 import type { InvocationNodeData } from 'features/nodes/types/invocation';
@@ -11,7 +12,7 @@ import { zWorkflowV2 } from 'features/nodes/types/v2/workflow';
 import type { WorkflowV3 } from 'features/nodes/types/workflow';
 import { zWorkflowV3 } from 'features/nodes/types/workflow';
 import { t } from 'i18next';
-import { cloneDeep, forEach } from 'lodash-es';
+import { forEach } from 'lodash-es';
 import { z } from 'zod';
 
 /**
@@ -89,7 +90,7 @@ export const parseAndMigrateWorkflow = (data: unknown): WorkflowV3 => {
     throw new WorkflowVersionError(t('nodes.unableToGetWorkflowVersion'));
   }
 
-  let workflow = cloneDeep(data) as WorkflowV1 | WorkflowV2 | WorkflowV3;
+  let workflow = deepClone(data) as WorkflowV1 | WorkflowV2 | WorkflowV3;
 
   if (workflow.meta.version === '1.0.0') {
     const v1 = zWorkflowV1.parse(workflow);

invokeai/frontend/web/src/features/parameters/components/Canvas/InfillAndScaling/ParamInfillColorOptions.tsx

@@ -0,0 +1,46 @@
+import { Box, Flex, FormControl, FormLabel } from '@invoke-ai/ui-library';
+import { createSelector } from '@reduxjs/toolkit';
+import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
+import IAIColorPicker from 'common/components/IAIColorPicker';
+import { selectGenerationSlice, setInfillColorValue } from 'features/parameters/store/generationSlice';
+import { memo, useCallback, useMemo } from 'react';
+import type { RgbaColor } from 'react-colorful';
+import { useTranslation } from 'react-i18next';
+
+const ParamInfillColorOptions = () => {
+  const dispatch = useAppDispatch();
+
+  const selector = useMemo(
+    () =>
+      createSelector(selectGenerationSlice, (generation) => ({
+        infillColor: generation.infillColorValue,
+      })),
+    []
+  );
+
+  const { infillColor } = useAppSelector(selector);
+
+  const infillMethod = useAppSelector((s) => s.generation.infillMethod);
+
+  const { t } = useTranslation();
+
+  const handleInfillColor = useCallback(
+    (v: RgbaColor) => {
+      dispatch(setInfillColorValue(v));
+    },
+    [dispatch]
+  );
+
+  return (
+    <Flex flexDir="column" gap={4}>
+      <FormControl isDisabled={infillMethod !== 'color'}>
+        <FormLabel>{t('parameters.infillColorValue')}</FormLabel>
+        <Box w="full" pt={2} pb={2}>
+          <IAIColorPicker color={infillColor} onChange={handleInfillColor} />
+        </Box>
+      </FormControl>
+    </Flex>
+  );
+};
+
+export default memo(ParamInfillColorOptions);