futureproof

Signed-off-by: Vladimir Mandic <mandic00@live.com>

scripts/differential_diffusion.py

@@ -15,7 +15,7 @@ import PIL.Image
 import numpy as np
 import torch
 import torchvision
-from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTextModelWithProjection, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTextModelWithProjection, CLIPTokenizer
 from diffusers.image_processor import VaeImageProcessor
 from diffusers.loaders import FromSingleFileMixin, LoraLoaderMixin, TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
@@ -1059,7 +1059,7 @@ class StableDiffusionDiffImg2ImgPipeline(DiffusionPipeline):
         unet: UNet2DConditionModel,
         scheduler: KarrasDiffusionSchedulers,
         safety_checker: StableDiffusionSafetyChecker,
-        feature_extractor: CLIPFeatureExtractor,
+        feature_extractor: CLIPImageProcessor,
         requires_safety_checker: bool = False,
     ):
         super().__init__()
@@ -1353,17 +1353,6 @@ class StableDiffusionDiffImg2ImgPipeline(DiffusionPipeline):
 
         return prompt_embeds
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.run_safety_checker
-    def run_safety_checker(self, image, device, dtype):
-        if self.safety_checker is not None:
-            safety_checker_input = self.feature_extractor(self.numpy_to_pil(image), return_tensors="pt").to(device)
-            image, has_nsfw_concept = self.safety_checker(
-                images=image, clip_input=safety_checker_input.pixel_values.to(dtype)
-            )
-        else:
-            has_nsfw_concept = None
-        return image, has_nsfw_concept
-
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.decode_latents
     def decode_latents(self, latents):
         latents = 1 / self.vae.config.scaling_factor * latents