InvokeAI 4.0.2__tar.gz → 4.0.3__tar.gz

{InvokeAI-4.0.2 → InvokeAI-4.0.3}/InvokeAI.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: InvokeAI
-Version: 4.0.2
+Version: 4.0.3
 Summary: An implementation of Stable Diffusion which provides various new features and options to aid the image generation process
 Author-email: The InvokeAI Project <lincoln.stein@gmail.com>
 License:                                  Apache License

{InvokeAI-4.0.2 → InvokeAI-4.0.3}/InvokeAI.egg-info/SOURCES.txt

@@ -196,13 +196,10 @@ invokeai/backend/raw_model.py
 invokeai/backend/textual_inversion.py
 invokeai/backend/image_util/__init__.py
 invokeai/backend/image_util/canny.py
-invokeai/backend/image_util/cv2_inpaint.py
 invokeai/backend/image_util/hed.py
 invokeai/backend/image_util/invisible_watermark.py
-invokeai/backend/image_util/lama.py
 invokeai/backend/image_util/lineart.py
 invokeai/backend/image_util/lineart_anime.py
-invokeai/backend/image_util/patchmatch.py
 invokeai/backend/image_util/pngwriter.py
 invokeai/backend/image_util/safety_checker.py
 invokeai/backend/image_util/seamless.py
@@ -219,6 +216,11 @@ invokeai/backend/image_util/dw_openpose/onnxdet.py
 invokeai/backend/image_util/dw_openpose/onnxpose.py
 invokeai/backend/image_util/dw_openpose/utils.py
 invokeai/backend/image_util/dw_openpose/wholebody.py
+invokeai/backend/image_util/infill_methods/cv2_inpaint.py
+invokeai/backend/image_util/infill_methods/lama.py
+invokeai/backend/image_util/infill_methods/mosaic.py
+invokeai/backend/image_util/infill_methods/patchmatch.py
+invokeai/backend/image_util/infill_methods/tile.py
 invokeai/backend/image_util/realesrgan/__init__.py
 invokeai/backend/image_util/realesrgan/realesrgan.py
 invokeai/backend/ip_adapter/__init__.py
@@ -312,11 +314,11 @@ invokeai/frontend/install/__init__.py
 invokeai/frontend/install/import_images.py
 invokeai/frontend/web/__init__.py
 invokeai/frontend/web/dist/index.html
+invokeai/frontend/web/dist/assets/App-BLcNMYZP.js
 invokeai/frontend/web/dist/assets/App-DI6oCUg0.css
-invokeai/frontend/web/dist/assets/App-De040c8N.js
 invokeai/frontend/web/dist/assets/ThemeLocaleProvider-Bsx7ESc2.css
-invokeai/frontend/web/dist/assets/ThemeLocaleProvider-CduMu4GW.js
-invokeai/frontend/web/dist/assets/index-Db_dTLB8.js
+invokeai/frontend/web/dist/assets/ThemeLocaleProvider-DKJ1LbAm.js
+invokeai/frontend/web/dist/assets/index-MDF-DOT9.js
 invokeai/frontend/web/dist/assets/inter-cyrillic-ext-wght-normal-DIEz8p5i.woff2
 invokeai/frontend/web/dist/assets/inter-cyrillic-wght-normal-BmJJXa8e.woff2
 invokeai/frontend/web/dist/assets/inter-greek-ext-wght-normal-D5AYLNiq.woff2

{InvokeAI-4.0.2 → InvokeAI-4.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: InvokeAI
-Version: 4.0.2
+Version: 4.0.3
 Summary: An implementation of Stable Diffusion which provides various new features and options to aid the image generation process
 Author-email: The InvokeAI Project <lincoln.stein@gmail.com>
 License:                                  Apache License

{InvokeAI-4.0.2 → InvokeAI-4.0.3}/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-4.0.3/invokeai/app/invocations/infill.py

@@ -0,0 +1,167 @@
+from abc import abstractmethod
+from typing import Literal, get_args
+
+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.misc import SEED_MAX
+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 get_infill_methods():
+    methods = Literal["tile", "color", "lama", "cv2"]  # TODO: add mosaic back
+    if PatchMatch.patchmatch_available():
+        methods = Literal["patchmatch", "tile", "color", "lama", "cv2"]  # TODO: add mosaic back
+    return methods
+
+
+INFILL_METHODS = get_infill_methods()
+DEFAULT_INFILL_METHOD = "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
+
+
+class InfillImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Base class for invocations that preprocess images for Infilling"""
+
+    image: ImageField = InputField(description="The image to process")
+
+    @abstractmethod
+    def infill(self, image: Image.Image) -> Image.Image:
+        """Infill the image with the specified method"""
+        pass
+
+    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
+
+    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))
+
+        # Perform Infill action
+        infilled_image = self.infill(input_image)
+
+        # Create ImageDTO for Infilled Image
+        infilled_image_dto = context.images.save(image=infilled_image)
+
+        # 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(InfillImageProcessorInvocation):
+    """Infills transparent areas of an image with a solid color"""
+
+    color: ColorField = InputField(
+        default=ColorField(r=127, g=127, b=127, a=255),
+        description="The color to use to infill",
+    )
+
+    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])
+        return infilled
+
+
+@invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.3")
+class InfillTileInvocation(InfillImageProcessorInvocation):
+    """Infills transparent areas of an image with tiles of the image"""
+
+    tile_size: int = InputField(default=32, ge=1, description="The tile size (px)")
+    seed: int = InputField(
+        default=0,
+        ge=0,
+        le=SEED_MAX,
+        description="The seed to use for tile generation (omit for random)",
+    )
+
+    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(InfillImageProcessorInvocation):
+    """Infills transparent areas of an image using the PatchMatch algorithm"""
+
+    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 infill(self, image: Image.Image):
+        resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
+
+        width = int(image.width / self.downscale)
+        height = int(image.height / self.downscale)
+
+        infilled = image.resize(
+            (width, height),
+            resample=resample_mode,
+        )
+        infilled = infill_patchmatch(image)
+        infilled = infilled.resize(
+            (image.width, image.height),
+            resample=resample_mode,
+        )
+        infilled.paste(image, (0, 0), mask=image.split()[-1])
+
+        return infilled
+
+
+@invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2")
+class LaMaInfillInvocation(InfillImageProcessorInvocation):
+    """Infills transparent areas of an image using the LaMa model"""
+
+    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(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 infill(self, image: Image.Image):
+        return infill_mosaic(image, (self.tile_width, self.tile_height), self.min_color.tuple(), self.max_color.tuple())

{InvokeAI-4.0.2 → InvokeAI-4.0.3}/invokeai/app/invocations/ip_adapter.py

@@ -65,7 +65,7 @@ class IPAdapterInvocation(BaseInvocation):
         ui_order=-1,
         ui_type=UIType.IPAdapterModel,
     )
-    clip_vision_model: Literal["auto", "ViT-H", "ViT-G"] = InputField(
+    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,
@@ -96,14 +96,9 @@ class IPAdapterInvocation(BaseInvocation):
         ip_adapter_info = context.models.get_config(self.ip_adapter_model.key)
         assert isinstance(ip_adapter_info, (IPAdapterInvokeAIConfig, IPAdapterCheckpointConfig))
 
-        if self.clip_vision_model == "auto":
-            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:
-                raise RuntimeError(
-                    "You need to set the appropriate CLIP Vision model for checkpoint IP Adapter models."
-                )
+        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]
 

{InvokeAI-4.0.2 → InvokeAI-4.0.3}/invokeai/app/invocations/latent.py

@@ -1254,7 +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-4.0.2 → InvokeAI-4.0.3}/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-4.0.2 → InvokeAI-4.0.3}/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-4.0.2/invokeai/backend/image_util → InvokeAI-4.0.3/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-4.0.3/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-4.0.3/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-4.0.3/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-4.0.2 → InvokeAI-4.0.3}/invokeai/backend/model_manager/load/model_cache/model_cache_default.py

@@ -421,13 +421,20 @@ 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:
             needed_gb = round(needed_size / GIG, 2)
             free_gb = round(free_mem / GIG, 2)