Fix TypeError when using prompt_embeds and negative_prompt (huggingface#2982)

* test: Added test case

* fix: fixed type checking issue on _encode_prompt

* fix: fixed copies consistency

* fix: one copy was not sufficient

Author: At-sushi

src/diffusers/pipelines/alt_diffusion/pipeline_alt_diffusion.py

@@ -369,7 +369,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/alt_diffusion/pipeline_alt_diffusion_img2img.py

@@ -378,7 +378,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_cycle_diffusion.py

@@ -387,7 +387,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py

@@ -372,7 +372,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py

@@ -384,7 +384,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_controlnet.py

@@ -427,7 +427,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_depth2img.py

@@ -256,7 +256,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py

@@ -385,7 +385,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py

@@ -437,7 +437,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint_legacy.py

@@ -376,7 +376,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_k_diffusion.py

@@ -288,7 +288,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_model_editing.py

@@ -315,7 +315,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_panorama.py

@@ -279,7 +279,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_pix2pix_zero.py

@@ -520,7 +520,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py

@@ -296,7 +296,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py

@@ -296,7 +296,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_unclip.py

@@ -416,7 +416,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/stable_diffusion/pipeline_stable_unclip_img2img.py

@@ -316,7 +316,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_synth.py

@@ -305,7 +305,7 @@ def _encode_prompt(
             uncond_tokens: List[str]
             if negative_prompt is None:
                 uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
+            elif prompt is not None and 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)}."

tests/pipelines/stable_diffusion/test_stable_diffusion.py

@@ -251,6 +251,45 @@ def test_stable_diffusion_negative_prompt_embeds(self):
 
         assert np.abs(image_slice_1.flatten() - image_slice_2.flatten()).max() < 1e-4
 
+    def test_stable_diffusion_prompt_embeds_with_plain_negative_prompt_list(self):
+        components = self.get_dummy_components()
+        sd_pipe = StableDiffusionPipeline(**components)
+        sd_pipe = sd_pipe.to(torch_device)
+        sd_pipe = sd_pipe.to(torch_device)
+        sd_pipe.set_progress_bar_config(disable=None)
+
+        inputs = self.get_dummy_inputs(torch_device)
+        negative_prompt = 3 * ["this is a negative prompt"]
+        inputs["negative_prompt"] = negative_prompt
+        inputs["prompt"] = 3 * [inputs["prompt"]]
+
+        # forward
+        output = sd_pipe(**inputs)
+        image_slice_1 = output.images[0, -3:, -3:, -1]
+
+        inputs = self.get_dummy_inputs(torch_device)
+        inputs["negative_prompt"] = negative_prompt
+        prompt = 3 * [inputs.pop("prompt")]
+
+        text_inputs = sd_pipe.tokenizer(
+            prompt,
+            padding="max_length",
+            max_length=sd_pipe.tokenizer.model_max_length,
+            truncation=True,
+            return_tensors="pt",
+        )
+        text_inputs = text_inputs["input_ids"].to(torch_device)
+
+        prompt_embeds = sd_pipe.text_encoder(text_inputs)[0]
+
+        inputs["prompt_embeds"] = prompt_embeds
+
+        # forward
+        output = sd_pipe(**inputs)
+        image_slice_2 = output.images[0, -3:, -3:, -1]
+
+        assert np.abs(image_slice_1.flatten() - image_slice_2.flatten()).max() < 1e-4
+
     def test_stable_diffusion_ddim_factor_8(self):
         device = "cpu"  # ensure determinism for the device-dependent torch.Generator