Rename 'CLIPFeatureExtractor' class to 'CLIPImageProcessor'

docs/source/en/api/pipelines/overview.mdx

@@ -19,9 +19,9 @@ components - all of which are needed to have a functioning end-to-end diffusion
 As an example, [Stable Diffusion](https://huggingface.co/blog/stable_diffusion) has three independently trained models:
 - [Autoencoder](./api/models#vae)
 - [Conditional Unet](./api/models#UNet2DConditionModel)
-- [CLIP text encoder](https://huggingface.co/docs/transformers/v4.21.2/en/model_doc/clip#transformers.CLIPTextModel)
+- [CLIP text encoder](https://huggingface.co/docs/transformers/v4.27.1/en/model_doc/clip#transformers.CLIPTextModel)
 - a scheduler component, [scheduler](./api/scheduler#pndm), 
-- a [CLIPFeatureExtractor](https://huggingface.co/docs/transformers/v4.21.2/en/model_doc/clip#transformers.CLIPFeatureExtractor),
+- a [CLIPImageProcessor](https://huggingface.co/docs/transformers/v4.27.1/en/model_doc/clip#transformers.CLIPImageProcessor),
 - as well as a [safety checker](./stable_diffusion#safety_checker).
 All of these components are necessary to run stable diffusion in inference even though they were trained 
 or created independently from each other.

docs/source/en/using-diffusers/custom_pipeline_examples.mdx

@@ -45,11 +45,11 @@ The following code requires roughly 12GB of GPU RAM.
 
 ```python
 from diffusers import DiffusionPipeline
-from transformers import CLIPFeatureExtractor, CLIPModel
+from transformers import CLIPImageProcessor, CLIPModel
 import torch
 
 
-feature_extractor = CLIPFeatureExtractor.from_pretrained("laion/CLIP-ViT-B-32-laion2B-s34B-b79K")
+feature_extractor = CLIPImageProcessor.from_pretrained("laion/CLIP-ViT-B-32-laion2B-s34B-b79K")
 clip_model = CLIPModel.from_pretrained("laion/CLIP-ViT-B-32-laion2B-s34B-b79K", torch_dtype=torch.float16)
 
 

docs/source/en/using-diffusers/custom_pipeline_overview.mdx

@@ -50,11 +50,11 @@ and passing pipeline modules directly.
 
 ```python
 from diffusers import DiffusionPipeline
-from transformers import CLIPFeatureExtractor, CLIPModel
+from transformers import CLIPImageProcessor, CLIPModel
 
 clip_model_id = "laion/CLIP-ViT-B-32-laion2B-s34B-b79K"
 
-feature_extractor = CLIPFeatureExtractor.from_pretrained(clip_model_id)
+feature_extractor = CLIPImageProcessor.from_pretrained(clip_model_id)
 clip_model = CLIPModel.from_pretrained(clip_model_id)
 
 pipeline = DiffusionPipeline.from_pretrained(

docs/source/en/using-diffusers/loading.mdx

@@ -415,7 +415,7 @@ print(pipe)
 StableDiffusionPipeline {
   "feature_extractor": [
     "transformers",
-    "CLIPFeatureExtractor"
+    "CLIPImageProcessor"
   ],
   "safety_checker": [
     "stable_diffusion",
@@ -445,7 +445,7 @@ StableDiffusionPipeline {
 ```
 
 First, we see that the official pipeline is the [`StableDiffusionPipeline`], and second we see that the `StableDiffusionPipeline` consists of 7 components:
-- `"feature_extractor"` of class `CLIPFeatureExtractor` as defined [in `transformers`](https://huggingface.co/docs/transformers/main/en/model_doc/clip#transformers.CLIPFeatureExtractor).
+- `"feature_extractor"` of class `CLIPImageProcessor` as defined [in `transformers`](https://huggingface.co/docs/transformers/main/en/model_doc/clip#transformers.CLIPImageProcessor).
 - `"safety_checker"` as defined [here](https://github.com/huggingface/diffusers/blob/e55687e1e15407f60f32242027b7bb8170e58266/src/diffusers/pipelines/stable_diffusion/safety_checker.py#L32).
 - `"scheduler"` of class [`PNDMScheduler`].
 - `"text_encoder"` of class `CLIPTextModel` as defined [in `transformers`](https://huggingface.co/docs/transformers/main/en/model_doc/clip#transformers.CLIPTextModel).
@@ -493,7 +493,7 @@ In the case of `runwayml/stable-diffusion-v1-5` the `model_index.json` is theref
   "_diffusers_version": "0.6.0",
   "feature_extractor": [
     "transformers",
-    "CLIPFeatureExtractor"
+    "CLIPImageProcessor"
   ],
   "safety_checker": [
     "stable_diffusion",

examples/community/README.md

@@ -49,11 +49,11 @@ The following code requires roughly 12GB of GPU RAM.
 
 ```python
 from diffusers import DiffusionPipeline
-from transformers import CLIPFeatureExtractor, CLIPModel
+from transformers import CLIPImageProcessor, CLIPModel
 import torch
 
 
-feature_extractor = CLIPFeatureExtractor.from_pretrained("laion/CLIP-ViT-B-32-laion2B-s34B-b79K")
+feature_extractor = CLIPImageProcessor.from_pretrained("laion/CLIP-ViT-B-32-laion2B-s34B-b79K")
 clip_model = CLIPModel.from_pretrained("laion/CLIP-ViT-B-32-laion2B-s34B-b79K", torch_dtype=torch.float16)
 
 

examples/community/clip_guided_stable_diffusion.py

@@ -5,7 +5,7 @@
 from torch import nn
 from torch.nn import functional as F
 from torchvision import transforms
-from transformers import CLIPFeatureExtractor, CLIPModel, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPModel, CLIPTextModel, CLIPTokenizer
 
 from diffusers import (
     AutoencoderKL,
@@ -64,7 +64,7 @@ def __init__(
         tokenizer: CLIPTokenizer,
         unet: UNet2DConditionModel,
         scheduler: Union[PNDMScheduler, LMSDiscreteScheduler, DDIMScheduler],
-        feature_extractor: CLIPFeatureExtractor,
+        feature_extractor: CLIPImageProcessor,
     ):
         super().__init__()
         self.register_modules(

examples/community/composable_stable_diffusion.py

@@ -17,7 +17,7 @@
 
 import torch
 from packaging import version
-from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 from diffusers import DiffusionPipeline
 from diffusers.configuration_utils import FrozenDict
@@ -64,7 +64,7 @@ class ComposableStableDiffusionPipeline(DiffusionPipeline):
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
             Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
-        feature_extractor ([`CLIPFeatureExtractor`]):
+        feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """
     _optional_components = ["safety_checker", "feature_extractor"]
@@ -84,7 +84,7 @@ def __init__(
             DPMSolverMultistepScheduler,
         ],
         safety_checker: StableDiffusionSafetyChecker,
-        feature_extractor: CLIPFeatureExtractor,
+        feature_extractor: CLIPImageProcessor,
         requires_safety_checker: bool = True,
     ):
         super().__init__()

examples/community/imagic_stable_diffusion.py

@@ -15,7 +15,7 @@
 # TODO: remove and import from diffusers.utils when the new version of diffusers is released
 from packaging import version
 from tqdm.auto import tqdm
-from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 from diffusers import DiffusionPipeline
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
@@ -80,7 +80,7 @@ class ImagicStableDiffusionPipeline(DiffusionPipeline):
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offsensive or harmful.
             Please, refer to the [model card](https://huggingface.co/CompVis/stable-diffusion-v1-4) for details.
-        feature_extractor ([`CLIPFeatureExtractor`]):
+        feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """
 
@@ -92,7 +92,7 @@ def __init__(
         unet: UNet2DConditionModel,
         scheduler: Union[DDIMScheduler, PNDMScheduler, LMSDiscreteScheduler],
         safety_checker: StableDiffusionSafetyChecker,
-        feature_extractor: CLIPFeatureExtractor,
+        feature_extractor: CLIPImageProcessor,
     ):
         super().__init__()
         self.register_modules(

examples/community/img2img_inpainting.py

@@ -4,7 +4,7 @@
 import numpy as np
 import PIL
 import torch
-from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 from diffusers import DiffusionPipeline
 from diffusers.configuration_utils import FrozenDict
@@ -79,7 +79,7 @@ class ImageToImageInpaintingPipeline(DiffusionPipeline):
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
             Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
-        feature_extractor ([`CLIPFeatureExtractor`]):
+        feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """
 
@@ -91,7 +91,7 @@ def __init__(
         unet: UNet2DConditionModel,
         scheduler: Union[DDIMScheduler, PNDMScheduler, LMSDiscreteScheduler],
         safety_checker: StableDiffusionSafetyChecker,
-        feature_extractor: CLIPFeatureExtractor,
+        feature_extractor: CLIPImageProcessor,
     ):
         super().__init__()
 

examples/community/interpolate_stable_diffusion.py

@@ -5,7 +5,7 @@
 
 import numpy as np
 import torch
-from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 from diffusers import DiffusionPipeline
 from diffusers.configuration_utils import FrozenDict
@@ -70,7 +70,7 @@ class StableDiffusionWalkPipeline(DiffusionPipeline):
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
             Please, refer to the [model card](https://huggingface.co/CompVis/stable-diffusion-v1-4) for details.
-        feature_extractor ([`CLIPFeatureExtractor`]):
+        feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """
 
@@ -82,7 +82,7 @@ def __init__(
         unet: UNet2DConditionModel,
         scheduler: Union[DDIMScheduler, PNDMScheduler, LMSDiscreteScheduler],
         safety_checker: StableDiffusionSafetyChecker,
-        feature_extractor: CLIPFeatureExtractor,
+        feature_extractor: CLIPImageProcessor,
     ):
         super().__init__()
 

examples/community/lpw_stable_diffusion.py

@@ -6,7 +6,7 @@
 import PIL
 import torch
 from packaging import version
-from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 import diffusers
 from diffusers import SchedulerMixin, StableDiffusionPipeline
@@ -422,7 +422,7 @@ class StableDiffusionLongPromptWeightingPipeline(StableDiffusionPipeline):
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
             Please, refer to the [model card](https://huggingface.co/CompVis/stable-diffusion-v1-4) for details.
-        feature_extractor ([`CLIPFeatureExtractor`]):
+        feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """
 
@@ -436,7 +436,7 @@ def __init__(
             unet: UNet2DConditionModel,
             scheduler: SchedulerMixin,
             safety_checker: StableDiffusionSafetyChecker,
-            feature_extractor: CLIPFeatureExtractor,
+            feature_extractor: CLIPImageProcessor,
             requires_safety_checker: bool = True,
         ):
             super().__init__(
@@ -461,7 +461,7 @@ def __init__(
             unet: UNet2DConditionModel,
             scheduler: SchedulerMixin,
             safety_checker: StableDiffusionSafetyChecker,
-            feature_extractor: CLIPFeatureExtractor,
+            feature_extractor: CLIPImageProcessor,
         ):
             super().__init__(
                 vae=vae,

examples/community/lpw_stable_diffusion_onnx.py

@@ -6,7 +6,7 @@
 import PIL
 import torch
 from packaging import version
-from transformers import CLIPFeatureExtractor, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPTokenizer
 
 import diffusers
 from diffusers import OnnxRuntimeModel, OnnxStableDiffusionPipeline, SchedulerMixin
@@ -441,7 +441,7 @@ def __init__(
             unet: OnnxRuntimeModel,
             scheduler: SchedulerMixin,
             safety_checker: OnnxRuntimeModel,
-            feature_extractor: CLIPFeatureExtractor,
+            feature_extractor: CLIPImageProcessor,
             requires_safety_checker: bool = True,
         ):
             super().__init__(
@@ -468,7 +468,7 @@ def __init__(
             unet: OnnxRuntimeModel,
             scheduler: SchedulerMixin,
             safety_checker: OnnxRuntimeModel,
-            feature_extractor: CLIPFeatureExtractor,
+            feature_extractor: CLIPImageProcessor,
         ):
             super().__init__(
                 vae_encoder=vae_encoder,

examples/community/multilingual_stable_diffusion.py

@@ -3,7 +3,7 @@
 
 import torch
 from transformers import (
-    CLIPFeatureExtractor,
+    CLIPImageProcessor,
     CLIPTextModel,
     CLIPTokenizer,
     MBart50TokenizerFast,
@@ -79,7 +79,7 @@ class MultilingualStableDiffusion(DiffusionPipeline):
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
             Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
-        feature_extractor ([`CLIPFeatureExtractor`]):
+        feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """
 
@@ -94,7 +94,7 @@ def __init__(
         unet: UNet2DConditionModel,
         scheduler: Union[DDIMScheduler, PNDMScheduler, LMSDiscreteScheduler],
         safety_checker: StableDiffusionSafetyChecker,
-        feature_extractor: CLIPFeatureExtractor,
+        feature_extractor: CLIPImageProcessor,
     ):
         super().__init__()
 

examples/community/sd_text2img_k_diffusion.py

@@ -65,7 +65,7 @@ class StableDiffusionPipeline(DiffusionPipeline):
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
             Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
-        feature_extractor ([`CLIPFeatureExtractor`]):
+        feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """
     _optional_components = ["safety_checker", "feature_extractor"]

examples/community/seed_resize_stable_diffusion.py

@@ -5,7 +5,7 @@
 from typing import Callable, List, Optional, Union
 
 import torch
-from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 from diffusers import DiffusionPipeline
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
@@ -42,7 +42,7 @@ class SeedResizeStableDiffusionPipeline(DiffusionPipeline):
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
             Please, refer to the [model card](https://huggingface.co/CompVis/stable-diffusion-v1-4) for details.
-        feature_extractor ([`CLIPFeatureExtractor`]):
+        feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """
 
@@ -54,7 +54,7 @@ def __init__(
         unet: UNet2DConditionModel,
         scheduler: Union[DDIMScheduler, PNDMScheduler, LMSDiscreteScheduler],
         safety_checker: StableDiffusionSafetyChecker,
-        feature_extractor: CLIPFeatureExtractor,
+        feature_extractor: CLIPImageProcessor,
     ):
         super().__init__()
         self.register_modules(

examples/community/speech_to_image_diffusion.py

@@ -3,7 +3,7 @@
 
 import torch
 from transformers import (
-    CLIPFeatureExtractor,
+    CLIPImageProcessor,
     CLIPTextModel,
     CLIPTokenizer,
     WhisperForConditionalGeneration,
@@ -37,7 +37,7 @@ def __init__(
         unet: UNet2DConditionModel,
         scheduler: Union[DDIMScheduler, PNDMScheduler, LMSDiscreteScheduler],
         safety_checker: StableDiffusionSafetyChecker,
-        feature_extractor: CLIPFeatureExtractor,
+        feature_extractor: CLIPImageProcessor,
     ):
         super().__init__()
 

examples/community/stable_diffusion_comparison.py

@@ -1,7 +1,7 @@
 from typing import Any, Callable, Dict, List, Optional, Union
 
 import torch
-from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 from diffusers import (
     AutoencoderKL,
@@ -46,7 +46,7 @@ class StableDiffusionComparisonPipeline(DiffusionPipeline):
         safety_checker ([`StableDiffusionMegaSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
             Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
-        feature_extractor ([`CLIPFeatureExtractor`]):
+        feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """
 
@@ -58,7 +58,7 @@ def __init__(
         unet: UNet2DConditionModel,
         scheduler: Union[DDIMScheduler, PNDMScheduler, LMSDiscreteScheduler],
         safety_checker: StableDiffusionSafetyChecker,
-        feature_extractor: CLIPFeatureExtractor,
+        feature_extractor: CLIPImageProcessor,
         requires_safety_checker: bool = True,
     ):
         super()._init_()

examples/community/stable_diffusion_controlnet_img2img.py

@@ -6,7 +6,7 @@
 import numpy as np
 import PIL.Image
 import torch
-from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 from diffusers import AutoencoderKL, ControlNetModel, DiffusionPipeline, UNet2DConditionModel, logging
 from diffusers.pipelines.stable_diffusion import StableDiffusionPipelineOutput, StableDiffusionSafetyChecker
@@ -135,7 +135,7 @@ def __init__(
         controlnet: ControlNetModel,
         scheduler: KarrasDiffusionSchedulers,
         safety_checker: StableDiffusionSafetyChecker,
-        feature_extractor: CLIPFeatureExtractor,
+        feature_extractor: CLIPImageProcessor,
         requires_safety_checker: bool = True,
     ):
         super().__init__()