[StableDiffusionimg2img] validating input type (#1913)

* [StableDiffusionimg2img] validating input type

* fixing tests

* running make style

* make fix-copies

src/diffusers/pipelines/alt_diffusion/pipeline_alt_diffusion_img2img.py

@@ -424,6 +424,11 @@ class AltDiffusionImg2ImgPipeline(DiffusionPipeline):
         return timesteps, num_inference_steps - t_start
 
     def prepare_latents(self, image, timestep, batch_size, num_images_per_prompt, dtype, device, generator=None):
+        if not isinstance(image, (torch.Tensor, PIL.Image.Image, list)):
+            raise ValueError(
+                f"`image` has to be of type `torch.Tensor`, `PIL.Image.Image` or list but is {type(image)}"
+            )
+
         image = image.to(device=device, dtype=dtype)
 
         batch_size = batch_size * num_images_per_prompt

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_depth2img.py

@@ -343,6 +343,11 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline):
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.StableDiffusionImg2ImgPipeline.prepare_latents
     def prepare_latents(self, image, timestep, batch_size, num_images_per_prompt, dtype, device, generator=None):
+        if not isinstance(image, (torch.Tensor, PIL.Image.Image, list)):
+            raise ValueError(
+                f"`image` has to be of type `torch.Tensor`, `PIL.Image.Image` or list but is {type(image)}"
+            )
+
         image = image.to(device=device, dtype=dtype)
 
         batch_size = batch_size * num_images_per_prompt

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py

@@ -434,6 +434,11 @@ class StableDiffusionImg2ImgPipeline(DiffusionPipeline):
         return timesteps, num_inference_steps - t_start
 
     def prepare_latents(self, image, timestep, batch_size, num_images_per_prompt, dtype, device, generator=None):
+        if not isinstance(image, (torch.Tensor, PIL.Image.Image, list)):
+            raise ValueError(
+                f"`image` has to be of type `torch.Tensor`, `PIL.Image.Image` or list but is {type(image)}"
+            )
+
         image = image.to(device=device, dtype=dtype)
 
         batch_size = batch_size * num_images_per_prompt