add PAG support for SD architecture (huggingface#8725)

* add pag to sd pipelines

Author: shauray8

docs/source/en/api/pipelines/pag.md

@@ -20,6 +20,11 @@ The abstract from the paper is:
 
 *Recent studies have demonstrated that diffusion models are capable of generating high-quality samples, but their quality heavily depends on sampling guidance techniques, such as classifier guidance (CG) and classifier-free guidance (CFG). These techniques are often not applicable in unconditional generation or in various downstream tasks such as image restoration. In this paper, we propose a novel sampling guidance, called Perturbed-Attention Guidance (PAG), which improves diffusion sample quality across both unconditional and conditional settings, achieving this without requiring additional training or the integration of external modules. PAG is designed to progressively enhance the structure of samples throughout the denoising process. It involves generating intermediate samples with degraded structure by substituting selected self-attention maps in diffusion U-Net with an identity matrix, by considering the self-attention mechanisms' ability to capture structural information, and guiding the denoising process away from these degraded samples. In both ADM and Stable Diffusion, PAG surprisingly improves sample quality in conditional and even unconditional scenarios. Moreover, PAG significantly improves the baseline performance in various downstream tasks where existing guidances such as CG or CFG cannot be fully utilized, including ControlNet with empty prompts and image restoration such as inpainting and deblurring.*
 
+## StableDiffusionPAGPipeline
+[[autodoc]] StableDiffusionPAGPipeline
+	- all
+	- __call__
+
 ## StableDiffusionXLPAGPipeline
 [[autodoc]] StableDiffusionXLPAGPipeline
 	- all

src/diffusers/__init__.py

@@ -304,6 +304,7 @@
             "StableDiffusionLatentUpscalePipeline",
             "StableDiffusionLDM3DPipeline",
             "StableDiffusionModelEditingPipeline",
+            "StableDiffusionPAGPipeline",
             "StableDiffusionPanoramaPipeline",
             "StableDiffusionParadigmsPipeline",
             "StableDiffusionPipeline",
@@ -702,6 +703,7 @@
             StableDiffusionLatentUpscalePipeline,
             StableDiffusionLDM3DPipeline,
             StableDiffusionModelEditingPipeline,
+            StableDiffusionPAGPipeline,
             StableDiffusionPanoramaPipeline,
             StableDiffusionParadigmsPipeline,
             StableDiffusionPipeline,

src/diffusers/pipelines/__init__.py

@@ -141,6 +141,7 @@
     )
     _import_structure["pag"].extend(
         [
+            "StableDiffusionPAGPipeline",
             "StableDiffusionXLPAGPipeline",
             "StableDiffusionXLPAGInpaintPipeline",
             "StableDiffusionXLControlNetPAGPipeline",
@@ -491,6 +492,7 @@
         )
         from .musicldm import MusicLDMPipeline
         from .pag import (
+            StableDiffusionPAGPipeline,
             StableDiffusionXLControlNetPAGPipeline,
             StableDiffusionXLPAGImg2ImgPipeline,
             StableDiffusionXLPAGInpaintPipeline,

src/diffusers/pipelines/auto_pipeline.py

@@ -47,6 +47,7 @@
 from .kandinsky3 import Kandinsky3Img2ImgPipeline, Kandinsky3Pipeline
 from .latent_consistency_models import LatentConsistencyModelImg2ImgPipeline, LatentConsistencyModelPipeline
 from .pag import (
+    StableDiffusionPAGPipeline,
     StableDiffusionXLControlNetPAGPipeline,
     StableDiffusionXLPAGImg2ImgPipeline,
     StableDiffusionXLPAGInpaintPipeline,
@@ -88,6 +89,7 @@
         ("lcm", LatentConsistencyModelPipeline),
         ("pixart-alpha", PixArtAlphaPipeline),
         ("pixart-sigma", PixArtSigmaPipeline),
+        ("stable-diffusion-pag", StableDiffusionPAGPipeline),
         ("stable-diffusion-xl-pag", StableDiffusionXLPAGPipeline),
         ("stable-diffusion-xl-controlnet-pag", StableDiffusionXLControlNetPAGPipeline),
     ]

src/diffusers/pipelines/pag/__init__.py

@@ -23,6 +23,7 @@
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
     _import_structure["pipeline_pag_controlnet_sd_xl"] = ["StableDiffusionXLControlNetPAGPipeline"]
+    _import_structure["pipeline_pag_sd"] = ["StableDiffusionPAGPipeline"]
     _import_structure["pipeline_pag_sd_xl"] = ["StableDiffusionXLPAGPipeline"]
     _import_structure["pipeline_pag_sd_xl_img2img"] = ["StableDiffusionXLPAGImg2ImgPipeline"]
     _import_structure["pipeline_pag_sd_xl_inpaint"] = ["StableDiffusionXLPAGInpaintPipeline"]
@@ -36,6 +37,7 @@
         from ...utils.dummy_torch_and_transformers_objects import *
     else:
         from .pipeline_pag_controlnet_sd_xl import StableDiffusionXLControlNetPAGPipeline
+        from .pipeline_pag_sd import StableDiffusionPAGPipeline
         from .pipeline_pag_sd_xl import StableDiffusionXLPAGPipeline
         from .pipeline_pag_sd_xl_img2img import StableDiffusionXLPAGImg2ImgPipeline
         from .pipeline_pag_sd_xl_inpaint import StableDiffusionXLPAGInpaintPipeline