[Utils] Improve " # Copied from ..." statements in the pipelines (#6917)

* copied from for t2i pipelines without ip adapter support.

* two more pipelines with proper copied from comments.

* revert to the original implementation

src/diffusers/pipelines/semantic_stable_diffusion/pipeline_semantic_stable_diffusion.py

@@ -136,6 +136,7 @@ class SemanticStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
             extra_step_kwargs["generator"] = generator
         return extra_step_kwargs
 
+    # Copied from diffusers.pipelines.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
     def check_inputs(
         self,
         prompt,

src/diffusers/pipelines/stable_diffusion_gligen/pipeline_stable_diffusion_gligen_text_image.py

@@ -445,6 +445,7 @@ class StableDiffusionGLIGENTextImagePipeline(DiffusionPipeline, StableDiffusionM
             extra_step_kwargs["generator"] = generator
         return extra_step_kwargs
 
+    # Copied from diffusers.pipelines.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
     def check_inputs(
         self,
         prompt,
@@ -454,8 +455,6 @@ class StableDiffusionGLIGENTextImagePipeline(DiffusionPipeline, StableDiffusionM
         negative_prompt=None,
         prompt_embeds=None,
         negative_prompt_embeds=None,
-        ip_adapter_image=None,
-        ip_adapter_image_embeds=None,
         callback_on_step_end_tensor_inputs=None,
     ):
         if height % 8 != 0 or width % 8 != 0:
@@ -499,11 +498,6 @@ class StableDiffusionGLIGENTextImagePipeline(DiffusionPipeline, StableDiffusionM
                     f" {negative_prompt_embeds.shape}."
                 )
 
-        if ip_adapter_image is not None and ip_adapter_image_embeds is not None:
-            raise ValueError(
-                "Provide either `ip_adapter_image` or `ip_adapter_image_embeds`. Cannot leave both `ip_adapter_image` and `ip_adapter_image_embeds` defined."
-            )
-
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
         shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)

src/diffusers/pipelines/stable_diffusion_safe/pipeline_stable_diffusion_safe.py

@@ -361,6 +361,7 @@ class StableDiffusionPipelineSafe(DiffusionPipeline, StableDiffusionMixin, IPAda
             extra_step_kwargs["generator"] = generator
         return extra_step_kwargs
 
+    # Copied from diffusers.pipelines.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
     def check_inputs(
         self,
         prompt,

src/diffusers/pipelines/stable_diffusion_sag/pipeline_stable_diffusion_sag.py

@@ -446,6 +446,7 @@ class StableDiffusionSAGPipeline(DiffusionPipeline, StableDiffusionMixin, Textua
             extra_step_kwargs["generator"] = generator
         return extra_step_kwargs
 
+    # Copied from diffusers.pipelines.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
     def check_inputs(
         self,
         prompt,

src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_synth.py

@@ -374,6 +374,7 @@ class TextToVideoSDPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInve
             extra_step_kwargs["generator"] = generator
         return extra_step_kwargs
 
+    # Copied from diffusers.pipelines.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
     def check_inputs(
         self,
         prompt,

src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_zero.py

@@ -447,6 +447,7 @@ class TextToVideoZeroPipeline(DiffusionPipeline, StableDiffusionMixin, TextualIn
                         callback(step_idx, t, latents)
         return latents.clone().detach()
 
+    # Copied from diffusers.pipelines.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
     def check_inputs(
         self,
         prompt,