diffusers 0.30.3__py3-none-any.whl → 0.32.0__py3-none-any.whl

diffusers/pipelines/pag/pipeline_pag_hunyuandit.py

@@ -128,9 +128,21 @@ def get_resize_crop_region_for_grid(src, tgt_size):
 
 # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.rescale_noise_cfg
 def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
-    """
-    Rescale `noise_cfg` according to `guidance_rescale`. Based on findings of [Common Diffusion Noise Schedules and
-    Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf). See Section 3.4
+    r"""
+    Rescales `noise_cfg` tensor based on `guidance_rescale` to improve image quality and fix overexposure. Based on
+    Section 3.4 from [Common Diffusion Noise Schedules and Sample Steps are
+    Flawed](https://arxiv.org/pdf/2305.08891.pdf).
+
+    Args:
+        noise_cfg (`torch.Tensor`):
+            The predicted noise tensor for the guided diffusion process.
+        noise_pred_text (`torch.Tensor`):
+            The predicted noise tensor for the text-guided diffusion process.
+        guidance_rescale (`float`, *optional*, defaults to 0.0):
+            A rescale factor applied to the noise predictions.
+
+    Returns:
+        noise_cfg (`torch.Tensor`): The rescaled noise prediction tensor.
     """
     std_text = noise_pred_text.std(dim=list(range(1, noise_pred_text.ndim)), keepdim=True)
     std_cfg = noise_cfg.std(dim=list(range(1, noise_cfg.ndim)), keepdim=True)
@@ -806,7 +818,11 @@ class HunyuanDiTPAGPipeline(DiffusionPipeline, PAGMixin):
         base_size = 512 // 8 // self.transformer.config.patch_size
         grid_crops_coords = get_resize_crop_region_for_grid((grid_height, grid_width), base_size)
         image_rotary_emb = get_2d_rotary_pos_embed(
-            self.transformer.inner_dim // self.transformer.num_heads, grid_crops_coords, (grid_height, grid_width)
+            self.transformer.inner_dim // self.transformer.num_heads,
+            grid_crops_coords,
+            (grid_height, grid_width),
+            device=device,
+            output_type="pt",
         )
 
         style = torch.tensor([0], device=device)
@@ -893,8 +909,8 @@ class HunyuanDiTPAGPipeline(DiffusionPipeline, PAGMixin):
 
                 # perform guidance
                 if self.do_perturbed_attention_guidance:
-                    noise_pred = self._apply_perturbed_attention_guidance(
-                        noise_pred, self.do_classifier_free_guidance, self.guidance_scale, t
+                    noise_pred, noise_pred_text = self._apply_perturbed_attention_guidance(
+                        noise_pred, self.do_classifier_free_guidance, self.guidance_scale, t, True
                     )
                 elif self.do_classifier_free_guidance:
                     noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)

diffusers/pipelines/pag/pipeline_pag_kolors.py

@@ -75,7 +75,7 @@ def retrieve_timesteps(
     sigmas: Optional[List[float]] = None,
     **kwargs,
 ):
-    """
+    r"""
     Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles
     custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`.
 

diffusers/pipelines/pag/pipeline_pag_pixart_sigma.py

@@ -81,7 +81,7 @@ def retrieve_timesteps(
     sigmas: Optional[List[float]] = None,
     **kwargs,
 ):
-    """
+    r"""
     Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles
     custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`.
 
@@ -227,13 +227,6 @@ class PixArtSigmaPAGPipeline(DiffusionPipeline, PAGMixin):
         if device is None:
             device = self._execution_device
 
-        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]
-
         # See Section 3.1. of the paper.
         max_length = max_sequence_length
 
@@ -278,12 +271,12 @@ class PixArtSigmaPAGPipeline(DiffusionPipeline, PAGMixin):
         # duplicate text embeddings and attention mask for each generation per prompt, using mps friendly method
         prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
         prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)
-        prompt_attention_mask = prompt_attention_mask.view(bs_embed, -1)
-        prompt_attention_mask = prompt_attention_mask.repeat(num_images_per_prompt, 1)
+        prompt_attention_mask = prompt_attention_mask.repeat(1, num_images_per_prompt)
+        prompt_attention_mask = prompt_attention_mask.view(bs_embed * num_images_per_prompt, -1)
 
         # get unconditional embeddings for classifier free guidance
         if do_classifier_free_guidance and negative_prompt_embeds is None:
-            uncond_tokens = [negative_prompt] * batch_size if isinstance(negative_prompt, str) else negative_prompt
+            uncond_tokens = [negative_prompt] * bs_embed if isinstance(negative_prompt, str) else negative_prompt
             uncond_tokens = self._text_preprocessing(uncond_tokens, clean_caption=clean_caption)
             max_length = prompt_embeds.shape[1]
             uncond_input = self.tokenizer(
@@ -310,10 +303,10 @@ class PixArtSigmaPAGPipeline(DiffusionPipeline, PAGMixin):
             negative_prompt_embeds = negative_prompt_embeds.to(dtype=dtype, device=device)
 
             negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
-            negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)
+            negative_prompt_embeds = negative_prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)
 
-            negative_prompt_attention_mask = negative_prompt_attention_mask.view(bs_embed, -1)
-            negative_prompt_attention_mask = negative_prompt_attention_mask.repeat(num_images_per_prompt, 1)
+            negative_prompt_attention_mask = negative_prompt_attention_mask.repeat(1, num_images_per_prompt)
+            negative_prompt_attention_mask = negative_prompt_attention_mask.view(bs_embed * num_images_per_prompt, -1)
         else:
             negative_prompt_embeds = None
             negative_prompt_attention_mask = None