Merge branch 'main' into lstein/feat/simple-mm2-api

invokeai/backend/image_util/__init__.py

@@ -4,5 +4,4 @@ Initialization file for invokeai.backend.image_util methods.
 
 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/safety_checker.py

@@ -8,7 +8,7 @@ from pathlib import Path
 
 import numpy as np
 from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker
-from PIL import Image
+from PIL import Image, ImageFilter
 from transformers import AutoFeatureExtractor
 
 import invokeai.backend.util.logging as logger
@@ -16,6 +16,7 @@ from invokeai.app.services.config.config_default import get_config
 from invokeai.backend.util.devices import TorchDevice
 from invokeai.backend.util.silence_warnings import SilenceWarnings
 
+repo_id = "CompVis/stable-diffusion-safety-checker"
 CHECKER_PATH = "core/convert/stable-diffusion-safety-checker"
 
 
@@ -24,30 +25,30 @@ class SafetyChecker:
     Wrapper around SafetyChecker model.
     """
 
-    safety_checker = None
     feature_extractor = None
-    tried_load: bool = False
+    safety_checker = None
 
     @classmethod
     def _load_safety_checker(cls):
-        if cls.tried_load:
+        if cls.safety_checker is not None and cls.feature_extractor is not None:
             return
 
         try:
-            cls.safety_checker = StableDiffusionSafetyChecker.from_pretrained(get_config().models_path / CHECKER_PATH)
-            cls.feature_extractor = AutoFeatureExtractor.from_pretrained(get_config().models_path / CHECKER_PATH)
+            model_path = get_config().models_path / CHECKER_PATH
+            if model_path.exists():
+                cls.feature_extractor = AutoFeatureExtractor.from_pretrained(model_path)
+                cls.safety_checker = StableDiffusionSafetyChecker.from_pretrained(model_path)
+            else:
+                model_path.mkdir(parents=True, exist_ok=True)
+                cls.feature_extractor = AutoFeatureExtractor.from_pretrained(repo_id)
+                cls.feature_extractor.save_pretrained(model_path, safe_serialization=True)
+                cls.safety_checker = StableDiffusionSafetyChecker.from_pretrained(repo_id)
+                cls.safety_checker.save_pretrained(model_path, safe_serialization=True)
         except Exception as e:
             logger.warning(f"Could not load NSFW checker: {str(e)}")
-        cls.tried_load = True
-
-    @classmethod
-    def safety_checker_available(cls) -> bool:
-        return Path(get_config().models_path, CHECKER_PATH).exists()
 
     @classmethod
     def has_nsfw_concept(cls, image: Image.Image) -> bool:
-        if not cls.safety_checker_available() and cls.tried_load:
-            return False
         cls._load_safety_checker()
         if cls.safety_checker is None or cls.feature_extractor is None:
             return False
@@ -60,3 +61,24 @@ class SafetyChecker:
         with SilenceWarnings():
             checked_image, has_nsfw_concept = cls.safety_checker(images=x_image, clip_input=features.pixel_values)
         return has_nsfw_concept[0]
+
+    @classmethod
+    def blur_if_nsfw(cls, image: Image.Image) -> Image.Image:
+        if cls.has_nsfw_concept(image):
+            logger.warning("A potentially NSFW image has been detected. Image will be blurred.")
+            blurry_image = image.filter(filter=ImageFilter.GaussianBlur(radius=32))
+            caution = cls._get_caution_img()
+            # Center the caution image on the blurred image
+            x = (blurry_image.width - caution.width) // 2
+            y = (blurry_image.height - caution.height) // 2
+            blurry_image.paste(caution, (x, y), caution)
+            image = blurry_image
+
+        return image
+
+    @classmethod
+    def _get_caution_img(cls) -> Image.Image:
+        import invokeai.app.assets.images as image_assets
+
+        caution = Image.open(Path(image_assets.__path__[0]) / "caution.png")
+        return caution.resize((caution.width // 2, caution.height // 2))

invokeai/backend/image_util/seamless.py

@@ -1,52 +0,0 @@
-import torch.nn as nn
-
-
-def _conv_forward_asymmetric(self, input, weight, bias):
-    """
-    Patch for Conv2d._conv_forward that supports asymmetric padding
-    """
-    working = nn.functional.pad(input, self.asymmetric_padding["x"], mode=self.asymmetric_padding_mode["x"])
-    working = nn.functional.pad(working, self.asymmetric_padding["y"], mode=self.asymmetric_padding_mode["y"])
-    return nn.functional.conv2d(
-        working,
-        weight,
-        bias,
-        self.stride,
-        nn.modules.utils._pair(0),
-        self.dilation,
-        self.groups,
-    )
-
-
-def configure_model_padding(model, seamless, seamless_axes):
-    """
-    Modifies the 2D convolution layers to use a circular padding mode based on
-    the `seamless` and `seamless_axes` options.
-    """
-    # TODO: get an explicit interface for this in diffusers: https://github.com/huggingface/diffusers/issues/556
-    for m in model.modules():
-        if isinstance(m, (nn.Conv2d, nn.ConvTranspose2d)):
-            if seamless:
-                m.asymmetric_padding_mode = {}
-                m.asymmetric_padding = {}
-                m.asymmetric_padding_mode["x"] = "circular" if ("x" in seamless_axes) else "constant"
-                m.asymmetric_padding["x"] = (
-                    m._reversed_padding_repeated_twice[0],
-                    m._reversed_padding_repeated_twice[1],
-                    0,
-                    0,
-                )
-                m.asymmetric_padding_mode["y"] = "circular" if ("y" in seamless_axes) else "constant"
-                m.asymmetric_padding["y"] = (
-                    0,
-                    0,
-                    m._reversed_padding_repeated_twice[2],
-                    m._reversed_padding_repeated_twice[3],
-                )
-                m._conv_forward = _conv_forward_asymmetric.__get__(m, nn.Conv2d)
-            else:
-                m._conv_forward = nn.Conv2d._conv_forward.__get__(m, nn.Conv2d)
-                if hasattr(m, "asymmetric_padding_mode"):
-                    del m.asymmetric_padding_mode
-                if hasattr(m, "asymmetric_padding"):
-                    del m.asymmetric_padding