diffusers 0.27.0__tar.gz → 0.27.2__tar.gz

{diffusers-0.27.0/src/diffusers.egg-info → diffusers-0.27.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: diffusers
-Version: 0.27.0
+Version: 0.27.2
 Summary: State-of-the-art diffusion in PyTorch and JAX.
 Home-page: https://github.com/huggingface/diffusers
 Author: The Hugging Face team (past and future) with the help of all our contributors (https://github.com/huggingface/diffusers/graphs/contributors)

{diffusers-0.27.0 → diffusers-0.27.2}/setup.py

@@ -249,7 +249,7 @@ version_range_max = max(sys.version_info[1], 10) + 1
 
 setup(
     name="diffusers",
-    version="0.27.0",  # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
+    version="0.27.2",  # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
     description="State-of-the-art diffusion in PyTorch and JAX.",
     long_description=open("README.md", "r", encoding="utf-8").read(),
     long_description_content_type="text/markdown",

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.27.0"
+__version__ = "0.27.2"
 
 from typing import TYPE_CHECKING
 

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/models/unets/unet_2d_condition.py

@@ -1081,6 +1081,8 @@ class UNet2DConditionModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin,
                 A tuple of tensors that if specified are added to the residuals of down unet blocks.
             mid_block_additional_residual: (`torch.Tensor`, *optional*):
                 A tensor that if specified is added to the residual of the middle unet block.
+            down_intrablock_additional_residuals (`tuple` of `torch.Tensor`, *optional*):
+                additional residuals to be added within UNet down blocks, for example from T2I-Adapter side model(s)
             encoder_attention_mask (`torch.Tensor`):
                 A cross-attention mask of shape `(batch, sequence_length)` is applied to `encoder_hidden_states`. If
                 `True` the mask is kept, otherwise if `False` it is discarded. Mask will be converted into a bias,
@@ -1088,18 +1090,6 @@ class UNet2DConditionModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin,
             return_dict (`bool`, *optional*, defaults to `True`):
                 Whether or not to return a [`~models.unets.unet_2d_condition.UNet2DConditionOutput`] instead of a plain
                 tuple.
-            cross_attention_kwargs (`dict`, *optional*):
-                A kwargs dictionary that if specified is passed along to the [`AttnProcessor`].
-            added_cond_kwargs: (`dict`, *optional*):
-                A kwargs dictionary containin additional embeddings that if specified are added to the embeddings that
-                are passed along to the UNet blocks.
-            down_block_additional_residuals (`tuple` of `torch.Tensor`, *optional*):
-                additional residuals to be added to UNet long skip connections from down blocks to up blocks for
-                example from ControlNet side model(s)
-            mid_block_additional_residual (`torch.Tensor`, *optional*):
-                additional residual to be added to UNet mid block output, for example from ControlNet side model
-            down_intrablock_additional_residuals (`tuple` of `torch.Tensor`, *optional*):
-                additional residuals to be added within UNet down blocks, for example from T2I-Adapter side model(s)
 
         Returns:
             [`~models.unets.unet_2d_condition.UNet2DConditionOutput`] or `tuple`:
@@ -1185,7 +1175,14 @@ class UNet2DConditionModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin,
             cross_attention_kwargs["gligen"] = {"objs": self.position_net(**gligen_args)}
 
         # 3. down
-        lora_scale = cross_attention_kwargs.get("scale", 1.0) if cross_attention_kwargs is not None else 1.0
+        # we're popping the `scale` instead of getting it because otherwise `scale` will be propagated
+        # to the internal blocks and will raise deprecation warnings. this will be confusing for our users.
+        if cross_attention_kwargs is not None:
+            cross_attention_kwargs = cross_attention_kwargs.copy()
+            lora_scale = cross_attention_kwargs.pop("scale", 1.0)
+        else:
+            lora_scale = 1.0
+
         if USE_PEFT_BACKEND:
             # weight the lora layers by setting `lora_scale` for each PEFT layer
             scale_lora_layers(self, lora_scale)

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/pipelines/deprecated/stable_diffusion_variants/pipeline_stable_diffusion_inpaint_legacy.py

@@ -528,15 +528,12 @@ class StableDiffusionInpaintPipelineLegacy(
                     f" {negative_prompt_embeds.shape}."
                 )
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.StableDiffusionImg2ImgPipeline.get_timesteps
     def get_timesteps(self, num_inference_steps, strength, device):
         # get the original timestep using init_timestep
         init_timestep = min(int(num_inference_steps * strength), num_inference_steps)
 
         t_start = max(num_inference_steps - init_timestep, 0)
         timesteps = self.scheduler.timesteps[t_start * self.scheduler.order :]
-        if hasattr(self.scheduler, "set_begin_index"):
-            self.scheduler.set_begin_index(t_start * self.scheduler.order)
 
         return timesteps, num_inference_steps - t_start
 

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade.py

@@ -100,8 +100,10 @@ class StableCascadeDecoderPipeline(DiffusionPipeline):
         )
         self.register_to_config(latent_dim_scale=latent_dim_scale)
 
-    def prepare_latents(self, image_embeddings, num_images_per_prompt, dtype, device, generator, latents, scheduler):
-        batch_size, channels, height, width = image_embeddings.shape
+    def prepare_latents(
+        self, batch_size, image_embeddings, num_images_per_prompt, dtype, device, generator, latents, scheduler
+    ):
+        _, channels, height, width = image_embeddings.shape
         latents_shape = (
             batch_size * num_images_per_prompt,
             4,
@@ -383,7 +385,19 @@ class StableCascadeDecoderPipeline(DiffusionPipeline):
         )
         if isinstance(image_embeddings, list):
             image_embeddings = torch.cat(image_embeddings, dim=0)
-        batch_size = image_embeddings.shape[0]
+
+        if prompt is not None and isinstance(prompt, str):
+            batch_size = 1
+        elif prompt is not None and isinstance(prompt, list):
+            batch_size = len(prompt)
+        else:
+            batch_size = prompt_embeds.shape[0]
+
+        # Compute the effective number of images per prompt
+        # We must account for the fact that the image embeddings from the prior can be generated with num_images_per_prompt > 1
+        # This results in a case where a single prompt is associated with multiple image embeddings
+        # Divide the number of image embeddings by the batch size to determine if this is the case.
+        num_images_per_prompt = num_images_per_prompt * (image_embeddings.shape[0] // batch_size)
 
         # 2. Encode caption
         if prompt_embeds is None and negative_prompt_embeds is None:
@@ -417,7 +431,7 @@ class StableCascadeDecoderPipeline(DiffusionPipeline):
 
         # 5. Prepare latents
         latents = self.prepare_latents(
-            image_embeddings, num_images_per_prompt, dtype, device, generator, latents, self.scheduler
+            batch_size, image_embeddings, num_images_per_prompt, dtype, device, generator, latents, self.scheduler
         )
 
         # 6. Run denoising loop

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/pipelines/stable_diffusion_diffedit/pipeline_stable_diffusion_diffedit.py

@@ -716,15 +716,12 @@ class StableDiffusionDiffEditPipeline(
                     f" `source_negative_prompt_embeds` {source_negative_prompt_embeds.shape}."
                 )
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.StableDiffusionImg2ImgPipeline.get_timesteps
     def get_timesteps(self, num_inference_steps, strength, device):
         # get the original timestep using init_timestep
         init_timestep = min(int(num_inference_steps * strength), num_inference_steps)
 
         t_start = max(num_inference_steps - init_timestep, 0)
         timesteps = self.scheduler.timesteps[t_start * self.scheduler.order :]
-        if hasattr(self.scheduler, "set_begin_index"):
-            self.scheduler.set_begin_index(t_start * self.scheduler.order)
 
         return timesteps, num_inference_steps - t_start
 

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/schedulers/scheduling_consistency_models.py

@@ -434,7 +434,11 @@ class CMStochasticIterativeScheduler(SchedulerMixin, ConfigMixin):
         # self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called bevore first denoising step to create inital latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/schedulers/scheduling_deis_multistep.py

@@ -768,10 +768,14 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
             schedule_timesteps = self.timesteps.to(original_samples.device)
             timesteps = timesteps.to(original_samples.device)
 
-        # begin_index is None when the scheduler is used for training
+        # begin_index is None when the scheduler is used for training or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called bevore first denoising step to create inital latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py

@@ -1011,10 +1011,14 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
             schedule_timesteps = self.timesteps.to(original_samples.device)
             timesteps = timesteps.to(original_samples.device)
 
-        # begin_index is None when the scheduler is used for training
+        # begin_index is None when the scheduler is used for training or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called bevore first denoising step to create inital latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/schedulers/scheduling_dpmsolver_sde.py

@@ -543,7 +543,11 @@ class DPMSolverSDEScheduler(SchedulerMixin, ConfigMixin):
         # self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called bevore first denoising step to create inital latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

@@ -961,10 +961,14 @@ class DPMSolverSinglestepScheduler(SchedulerMixin, ConfigMixin):
             schedule_timesteps = self.timesteps.to(original_samples.device)
             timesteps = timesteps.to(original_samples.device)
 
-        # begin_index is None when the scheduler is used for training
+        # begin_index is None when the scheduler is used for training or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called bevore first denoising step to create inital latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/schedulers/scheduling_edm_dpmsolver_multistep.py

@@ -669,7 +669,11 @@ class EDMDPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
         # self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called bevore first denoising step to create inital latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/schedulers/scheduling_edm_euler.py

@@ -367,7 +367,11 @@ class EDMEulerScheduler(SchedulerMixin, ConfigMixin):
         # self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called bevore first denoising step to create inital latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/schedulers/scheduling_euler_ancestral_discrete.py

@@ -467,7 +467,11 @@ class EulerAncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
         # self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called bevore first denoising step to create inital latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/schedulers/scheduling_euler_discrete.py

@@ -562,7 +562,11 @@ class EulerDiscreteScheduler(SchedulerMixin, ConfigMixin):
         # self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called bevore first denoising step to create inital latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/schedulers/scheduling_heun_discrete.py

@@ -468,7 +468,11 @@ class HeunDiscreteScheduler(SchedulerMixin, ConfigMixin):
         # self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called bevore first denoising step to create inital latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/schedulers/scheduling_k_dpm_2_ancestral_discrete.py

@@ -494,7 +494,11 @@ class KDPM2AncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
         # self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called bevore first denoising step to create inital latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/schedulers/scheduling_k_dpm_2_discrete.py

@@ -469,7 +469,11 @@ class KDPM2DiscreteScheduler(SchedulerMixin, ConfigMixin):
         # self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called bevore first denoising step to create inital latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/schedulers/scheduling_lms_discrete.py

@@ -461,7 +461,11 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
         # self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called bevore first denoising step to create inital latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

{diffusers-0.27.0 → diffusers-0.27.2}/src/diffusers/schedulers/scheduling_unipc_multistep.py

@@ -862,10 +862,14 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
             schedule_timesteps = self.timesteps.to(original_samples.device)
             timesteps = timesteps.to(original_samples.device)
 
-        # begin_index is None when the scheduler is used for training
+        # begin_index is None when the scheduler is used for training or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called bevore first denoising step to create inital latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

{diffusers-0.27.0 → diffusers-0.27.2/src/diffusers.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: diffusers
-Version: 0.27.0
+Version: 0.27.2
 Summary: State-of-the-art diffusion in PyTorch and JAX.
 Home-page: https://github.com/huggingface/diffusers
 Author: The Hugging Face team (past and future) with the help of all our contributors (https://github.com/huggingface/diffusers/graphs/contributors)