wip: Initial Infill Methods Refactor

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 +1,56 @@
+from typing import Tuple
+
+import numpy as np
+from PIL import Image
+
+
+def infill_mosaic(
+    image: Image.Image,
+    tile_shape: Tuple[int, int] = (64, 16),
+    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))]
+            filled_image[
+                y - (y % tile_height) : y - (y % tile_height) + tile_height,
+                x - (x % tile_width) : x - (x % tile_width) + tile_width,
+            ] = tile
+
+    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.py

@@ -0,0 +1,72 @@
+import math
+from typing import Optional
+
+import numpy as np
+from PIL import Image
+
+
+def get_tile_images(image: np.ndarray, width: int = 8, height: int = 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 infill_tile(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

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)