Merge branch 'main' into dora-tests

Author: sayakpaul

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

@@ -53,6 +53,11 @@ Since RegEx is supported as a way for matching layer identifiers, it is crucial
 	- all
 	- __call__
 
+## StableDiffusionPAGImg2ImgPipeline
+[[autodoc]] StableDiffusionPAGImg2ImgPipeline
+	- all
+	- __call__
+
 ## StableDiffusionControlNetPAGPipeline
 [[autodoc]] StableDiffusionControlNetPAGPipeline
 

src/diffusers/__init__.py

@@ -344,6 +344,7 @@
             "StableDiffusionLatentUpscalePipeline",
             "StableDiffusionLDM3DPipeline",
             "StableDiffusionModelEditingPipeline",
+            "StableDiffusionPAGImg2ImgPipeline",
             "StableDiffusionPAGPipeline",
             "StableDiffusionPanoramaPipeline",
             "StableDiffusionParadigmsPipeline",
@@ -795,6 +796,7 @@
             StableDiffusionLatentUpscalePipeline,
             StableDiffusionLDM3DPipeline,
             StableDiffusionModelEditingPipeline,
+            StableDiffusionPAGImg2ImgPipeline,
             StableDiffusionPAGPipeline,
             StableDiffusionPanoramaPipeline,
             StableDiffusionParadigmsPipeline,

src/diffusers/pipelines/__init__.py

@@ -164,6 +164,7 @@
             "HunyuanDiTPAGPipeline",
             "StableDiffusion3PAGPipeline",
             "StableDiffusionPAGPipeline",
+            "StableDiffusionPAGImg2ImgPipeline",
             "StableDiffusionControlNetPAGPipeline",
             "StableDiffusionXLPAGPipeline",
             "StableDiffusionXLPAGInpaintPipeline",
@@ -569,6 +570,7 @@
             StableDiffusion3PAGPipeline,
             StableDiffusionControlNetPAGInpaintPipeline,
             StableDiffusionControlNetPAGPipeline,
+            StableDiffusionPAGImg2ImgPipeline,
             StableDiffusionPAGPipeline,
             StableDiffusionXLControlNetPAGImg2ImgPipeline,
             StableDiffusionXLControlNetPAGPipeline,

src/diffusers/pipelines/auto_pipeline.py

@@ -63,6 +63,7 @@
     StableDiffusion3PAGPipeline,
     StableDiffusionControlNetPAGInpaintPipeline,
     StableDiffusionControlNetPAGPipeline,
+    StableDiffusionPAGImg2ImgPipeline,
     StableDiffusionPAGPipeline,
     StableDiffusionXLControlNetPAGImg2ImgPipeline,
     StableDiffusionXLControlNetPAGPipeline,
@@ -131,6 +132,7 @@
         ("kandinsky22", KandinskyV22Img2ImgCombinedPipeline),
         ("kandinsky3", Kandinsky3Img2ImgPipeline),
         ("stable-diffusion-controlnet", StableDiffusionControlNetImg2ImgPipeline),
+        ("stable-diffusion-pag", StableDiffusionPAGImg2ImgPipeline),
         ("stable-diffusion-xl-controlnet", StableDiffusionXLControlNetImg2ImgPipeline),
         ("stable-diffusion-xl-pag", StableDiffusionXLPAGImg2ImgPipeline),
         ("stable-diffusion-xl-controlnet-pag", StableDiffusionXLControlNetPAGImg2ImgPipeline),

src/diffusers/pipelines/controlnet/pipeline_controlnet.py

@@ -893,6 +893,10 @@ def cross_attention_kwargs(self):
     def num_timesteps(self):
         return self._num_timesteps
 
+    @property
+    def interrupt(self):
+        return self._interrupt
+
     @torch.no_grad()
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
@@ -1089,6 +1093,7 @@ def __call__(
         self._guidance_scale = guidance_scale
         self._clip_skip = clip_skip
         self._cross_attention_kwargs = cross_attention_kwargs
+        self._interrupt = False
 
         # 2. Define call parameters
         if prompt is not None and isinstance(prompt, str):
@@ -1235,6 +1240,9 @@ def __call__(
         is_torch_higher_equal_2_1 = is_torch_version(">=", "2.1")
         with self.progress_bar(total=num_inference_steps) as progress_bar:
             for i, t in enumerate(timesteps):
+                if self.interrupt:
+                    continue
+
                 # Relevant thread:
                 # https://dev-discuss.pytorch.org/t/cudagraphs-in-pytorch-2-0/1428
                 if (is_unet_compiled and is_controlnet_compiled) and is_torch_higher_equal_2_1:

src/diffusers/pipelines/controlnet/pipeline_controlnet_img2img.py

@@ -891,6 +891,10 @@ def cross_attention_kwargs(self):
     def num_timesteps(self):
         return self._num_timesteps
 
+    @property
+    def interrupt(self):
+        return self._interrupt
+
     @torch.no_grad()
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
@@ -1081,6 +1085,7 @@ def __call__(
         self._guidance_scale = guidance_scale
         self._clip_skip = clip_skip
         self._cross_attention_kwargs = cross_attention_kwargs
+        self._interrupt = False
 
         # 2. Define call parameters
         if prompt is not None and isinstance(prompt, str):
@@ -1211,6 +1216,9 @@ def __call__(
         num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
         with self.progress_bar(total=num_inference_steps) as progress_bar:
             for i, t in enumerate(timesteps):
+                if self.interrupt:
+                    continue
+
                 # expand the latents if we are doing classifier free guidance
                 latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
                 latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py

@@ -976,6 +976,10 @@ def cross_attention_kwargs(self):
     def num_timesteps(self):
         return self._num_timesteps
 
+    @property
+    def interrupt(self):
+        return self._interrupt
+
     @torch.no_grad()
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
@@ -1191,6 +1195,7 @@ def __call__(
         self._guidance_scale = guidance_scale
         self._clip_skip = clip_skip
         self._cross_attention_kwargs = cross_attention_kwargs
+        self._interrupt = False
 
         # 2. Define call parameters
         if prompt is not None and isinstance(prompt, str):
@@ -1375,6 +1380,9 @@ def __call__(
         num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
         with self.progress_bar(total=num_inference_steps) as progress_bar:
             for i, t in enumerate(timesteps):
+                if self.interrupt:
+                    continue
+
                 # expand the latents if we are doing classifier free guidance
                 latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
                 latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint_sd_xl.py

@@ -1145,6 +1145,10 @@ def cross_attention_kwargs(self):
     def num_timesteps(self):
         return self._num_timesteps
 
+    @property
+    def interrupt(self):
+        return self._interrupt
+
     @torch.no_grad()
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
@@ -1427,6 +1431,7 @@ def __call__(
         self._guidance_scale = guidance_scale
         self._clip_skip = clip_skip
         self._cross_attention_kwargs = cross_attention_kwargs
+        self._interrupt = False
 
         # 2. Define call parameters
         if prompt is not None and isinstance(prompt, str):
@@ -1695,6 +1700,9 @@ def denoising_value_valid(dnv):
 
         with self.progress_bar(total=num_inference_steps) as progress_bar:
             for i, t in enumerate(timesteps):
+                if self.interrupt:
+                    continue
+
                 # expand the latents if we are doing classifier free guidance
                 latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
 

src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl.py

@@ -990,6 +990,10 @@ def denoising_end(self):
     def num_timesteps(self):
         return self._num_timesteps
 
+    @property
+    def interrupt(self):
+        return self._interrupt
+
     @torch.no_grad()
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
@@ -1245,6 +1249,7 @@ def __call__(
         self._clip_skip = clip_skip
         self._cross_attention_kwargs = cross_attention_kwargs
         self._denoising_end = denoising_end
+        self._interrupt = False
 
         # 2. Define call parameters
         if prompt is not None and isinstance(prompt, str):
@@ -1442,6 +1447,9 @@ def __call__(
         is_torch_higher_equal_2_1 = is_torch_version(">=", "2.1")
         with self.progress_bar(total=num_inference_steps) as progress_bar:
             for i, t in enumerate(timesteps):
+                if self.interrupt:
+                    continue
+
                 # Relevant thread:
                 # https://dev-discuss.pytorch.org/t/cudagraphs-in-pytorch-2-0/1428
                 if (is_unet_compiled and is_controlnet_compiled) and is_torch_higher_equal_2_1:

src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl_img2img.py

@@ -1070,6 +1070,10 @@ def cross_attention_kwargs(self):
     def num_timesteps(self):
         return self._num_timesteps
 
+    @property
+    def interrupt(self):
+        return self._interrupt
+
     @torch.no_grad()
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
@@ -1338,6 +1342,7 @@ def __call__(
         self._guidance_scale = guidance_scale
         self._clip_skip = clip_skip
         self._cross_attention_kwargs = cross_attention_kwargs
+        self._interrupt = False
 
         # 2. Define call parameters
         if prompt is not None and isinstance(prompt, str):
@@ -1510,6 +1515,9 @@ def __call__(
         num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
         with self.progress_bar(total=num_inference_steps) as progress_bar:
             for i, t in enumerate(timesteps):
+                if self.interrupt:
+                    continue
+
                 # expand the latents if we are doing classifier free guidance
                 latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
                 latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)