Fix check_inputs in upscaler pipeline to allow embeds (huggingface#2892)

* Remove suggestion to use cuDNN benchmark in docs

* removing the wrong line

* add support for embeds

* fix line length

Author: d1g1t

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py

@@ -326,10 +326,50 @@ def decode_latents(self, latents):
         image = image.cpu().permute(0, 2, 3, 1).float().numpy()
         return image
 
-    def check_inputs(self, prompt, image, noise_level, callback_steps):
-        if not isinstance(prompt, str) and not isinstance(prompt, list):
+    def check_inputs(
+        self,
+        prompt,
+        image,
+        noise_level,
+        callback_steps,
+        negative_prompt=None,
+        prompt_embeds=None,
+        negative_prompt_embeds=None,
+    ):
+        if (callback_steps is None) or (
+            callback_steps is not None and (not isinstance(callback_steps, int) or callback_steps <= 0)
+        ):
+            raise ValueError(
+                f"`callback_steps` has to be a positive integer but is {callback_steps} of type"
+                f" {type(callback_steps)}."
+            )
+
+        if prompt is not None and prompt_embeds is not None:
+            raise ValueError(
+                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
+                " only forward one of the two."
+            )
+        elif prompt is None and prompt_embeds is None:
+            raise ValueError(
+                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
+            )
+        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
             raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
 
+        if negative_prompt is not None and negative_prompt_embeds is not None:
+            raise ValueError(
+                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
+                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
+            )
+
+        if prompt_embeds is not None and negative_prompt_embeds is not None:
+            if prompt_embeds.shape != negative_prompt_embeds.shape:
+                raise ValueError(
+                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
+                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
+                    f" {negative_prompt_embeds.shape}."
+                )
+
         if (
             not isinstance(image, torch.Tensor)
             and not isinstance(image, PIL.Image.Image)
@@ -489,13 +529,27 @@ def __call__(
         """
 
         # 1. Check inputs
-        self.check_inputs(prompt, image, noise_level, callback_steps)
+        self.check_inputs(
+            prompt,
+            image,
+            noise_level,
+            callback_steps,
+            negative_prompt,
+            prompt_embeds,
+            negative_prompt_embeds,
+        )
 
         if image is None:
             raise ValueError("`image` input cannot be undefined.")
 
         # 2. Define call parameters
-        batch_size = 1 if isinstance(prompt, str) else len(prompt)
+        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]
+
         device = self._execution_device
         # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
         # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`