fix copies

Author: hlky

src/diffusers/pipelines/allegro/pipeline_allegro.py

@@ -251,13 +251,6 @@ def encode_prompt(
         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
 
@@ -302,12 +295,12 @@ def encode_prompt(
         # duplicate text embeddings and attention mask for each generation per prompt, using mps friendly method
         prompt_embeds = prompt_embeds.repeat(1, num_videos_per_prompt, 1)
         prompt_embeds = prompt_embeds.view(bs_embed * num_videos_per_prompt, seq_len, -1)
-        prompt_attention_mask = prompt_attention_mask.view(bs_embed, -1)
-        prompt_attention_mask = prompt_attention_mask.repeat(num_videos_per_prompt, 1)
+        prompt_attention_mask = prompt_attention_mask.repeat(1, num_videos_per_prompt)
+        prompt_attention_mask = prompt_attention_mask.view(bs_embed * num_videos_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(
@@ -334,10 +327,10 @@ def encode_prompt(
             negative_prompt_embeds = negative_prompt_embeds.to(dtype=dtype, device=device)
 
             negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_videos_per_prompt, 1)
-            negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_videos_per_prompt, seq_len, -1)
+            negative_prompt_embeds = negative_prompt_embeds.view(bs_embed * num_videos_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_videos_per_prompt, 1)
+            negative_prompt_attention_mask = negative_prompt_attention_mask.repeat(1, num_videos_per_prompt)
+            negative_prompt_attention_mask = negative_prompt_attention_mask.view(bs_embed * num_videos_per_prompt, -1)
         else:
             negative_prompt_embeds = None
             negative_prompt_attention_mask = None

src/diffusers/pipelines/pag/pipeline_pag_pixart_sigma.py

@@ -227,13 +227,6 @@ def encode_prompt(
         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 @@ def encode_prompt(
         # 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 @@ def encode_prompt(
             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

src/diffusers/pipelines/pixart_alpha/pipeline_pixart_sigma.py

@@ -264,13 +264,6 @@ def encode_prompt(
         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
 
@@ -315,12 +308,12 @@ def encode_prompt(
         # 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(
@@ -347,10 +340,10 @@ def encode_prompt(
             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