Add semantic guidance pipeline (huggingface#2223)

* Add semantic guidance pipeline

* Fix style

* Refactor Pipeline

* Pipeline documentation

* Add documentation

* Fix style and quality

* Fix doctree

* Add tests for SEGA

* Update src/diffusers/pipelines/semantic_stable_diffusion/pipeline_semantic_stable_diffusion.py

Co-authored-by: Patrick von Platen <[email protected]>

* Update src/diffusers/pipelines/semantic_stable_diffusion/pipeline_semantic_stable_diffusion.py

Co-authored-by: Patrick von Platen <[email protected]>

* Update src/diffusers/pipelines/semantic_stable_diffusion/pipeline_semantic_stable_diffusion.py

Co-authored-by: Patrick von Platen <[email protected]>

* Make compatible with half precision

* Change deprecation warning to throw an exception

* update

---------

Co-authored-by: Patrick von Platen <[email protected]>

Author: manuelbrack

__init__.py

@@ -110,6 +110,7 @@
         CycleDiffusionPipeline,
         LDMTextToImagePipeline,
         PaintByExamplePipeline,
+        SemanticStableDiffusionPipeline,
         StableDiffusionAttendAndExcitePipeline,
         StableDiffusionDepth2ImgPipeline,
         StableDiffusionImageVariationPipeline,

pipelines/__init__.py

@@ -44,6 +44,7 @@
     from .alt_diffusion import AltDiffusionImg2ImgPipeline, AltDiffusionPipeline
     from .latent_diffusion import LDMTextToImagePipeline
     from .paint_by_example import PaintByExamplePipeline
+    from .semantic_stable_diffusion import SemanticStableDiffusionPipeline
     from .stable_diffusion import (
         CycleDiffusionPipeline,
         StableDiffusionAttendAndExcitePipeline,

pipelines/semantic_stable_diffusion/__init__.py

@@ -0,0 +1,31 @@
+from dataclasses import dataclass
+from enum import Enum
+from typing import List, Optional, Union
+
+import numpy as np
+import PIL
+from PIL import Image
+
+from ...utils import BaseOutput, is_torch_available, is_transformers_available
+
+
+@dataclass
+class SemanticStableDiffusionPipelineOutput(BaseOutput):
+    """
+    Output class for Stable Diffusion pipelines.
+
+    Args:
+        images (`List[PIL.Image.Image]` or `np.ndarray`)
+            List of denoised PIL images of length `batch_size` or numpy array of shape `(batch_size, height, width,
+            num_channels)`. PIL images or numpy array present the denoised images of the diffusion pipeline.
+        nsfw_content_detected (`List[bool]`)
+            List of flags denoting whether the corresponding generated image likely represents "not-safe-for-work"
+            (nsfw) content, or `None` if safety checking could not be performed.
+    """
+
+    images: Union[List[PIL.Image.Image], np.ndarray]
+    nsfw_content_detected: Optional[List[bool]]
+
+
+if is_transformers_available() and is_torch_available():
+    from .pipeline_semantic_stable_diffusion import SemanticStableDiffusionPipeline