fix negative_prompt=None

pipeline.py

@@ -550,6 +550,7 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
 
         if isinstance(prompt, str):
             batch_size = 1
+            prompt = [prompt]
         elif isinstance(prompt, list):
             batch_size = len(prompt)
         else:
@@ -576,28 +577,21 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
         # corresponds to doing no classifier free guidance.
         do_classifier_free_guidance = guidance_scale > 1.0
         # get unconditional embeddings for classifier free guidance
-        uncond_tokens = [""]
-        if do_classifier_free_guidance:
-            if type(prompt) is not type(negative_prompt):
-                raise TypeError(
-                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
-                    f" {type(prompt)}."
-                )
-            elif isinstance(negative_prompt, str):
-                uncond_tokens = [negative_prompt]
-            elif batch_size != len(negative_prompt):
-                raise ValueError(
-                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
-                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
-                    " the batch size of `prompt`."
-                )
-            else:
-                uncond_tokens = negative_prompt
+        if negative_prompt is None:
+            negative_prompt = [""] * batch_size
+        elif isinstance(negative_prompt, str):
+            negative_prompt = [negative_prompt] * batch_size
+        if batch_size != len(negative_prompt):
+            raise ValueError(
+                f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
+                f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
+                " the batch size of `prompt`."
+            )
 
         text_embeddings, uncond_embeddings  = get_weighted_text_embeddings(
             pipe=self,
             prompt=prompt,
-            uncond_prompt=uncond_tokens if do_classifier_free_guidance else None,
+            uncond_prompt=negative_prompt if do_classifier_free_guidance else None,
             max_embeddings_multiples=max_embeddings_multiples,
             **kwargs
         )
@@ -682,6 +676,7 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
                 )
             else:
                 noise = torch.randn(init_latents.shape, generator=generator, device=self.device, dtype=latents_dtype)
+            print(timesteps.shape)
             latents = self.scheduler.add_noise(init_latents, noise, timesteps)
 
             t_start = max(num_inference_steps - init_timestep + offset, 0)