[StableDiffusionXLAdapterPipeline] allow negative micro conds (huggingface#4941)

* allow negative micro conds in t2i pipeline

* Empty-Commit

---------

Co-authored-by: Sayak Paul <[email protected]>

Author: patil-suraj

src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_xl_adapter.py

@@ -655,6 +655,9 @@ def __call__(
         original_size: Optional[Tuple[int, int]] = None,
         crops_coords_top_left: Tuple[int, int] = (0, 0),
         target_size: Optional[Tuple[int, int]] = None,
+        negative_original_size: Optional[Tuple[int, int]] = None,
+        negative_crops_coords_top_left: Tuple[int, int] = (0, 0),
+        negative_target_size: Optional[Tuple[int, int]] = None,
         adapter_conditioning_scale: Union[float, List[float]] = 1.0,
         adapter_conditioning_factor: float = 1.0,
     ):
@@ -764,6 +767,22 @@ def __call__(
                 For most cases, `target_size` should be set to the desired height and width of the generated image. If
                 not specified it will default to `(width, height)`. Part of SDXL's micro-conditioning as explained in
                 section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
+                section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
+            negative_original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
+                To negatively condition the generation process based on a specific image resolution. Part of SDXL's
+                micro-conditioning as explained in section 2.2 of
+                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
+                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
+            negative_crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
+                To negatively condition the generation process based on a specific crop coordinates. Part of SDXL's
+                micro-conditioning as explained in section 2.2 of
+                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
+                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
+            negative_target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
+                To negatively condition the generation process based on a target image resolution. It should be as same
+                as the `target_size` for most cases. Part of SDXL's micro-conditioning as explained in section 2.2 of
+                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
+                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
             adapter_conditioning_scale (`float` or `List[float]`, *optional*, defaults to 1.0):
                 The outputs of the adapter are multiplied by `adapter_conditioning_scale` before they are added to the
                 residual in the original unet. If multiple adapters are specified in init, you can set the
@@ -876,11 +895,20 @@ def __call__(
         add_time_ids = self._get_add_time_ids(
             original_size, crops_coords_top_left, target_size, dtype=prompt_embeds.dtype
         )
+        if negative_original_size is not None and negative_target_size is not None:
+            negative_add_time_ids = self._get_add_time_ids(
+                negative_original_size,
+                negative_crops_coords_top_left,
+                negative_target_size,
+                dtype=prompt_embeds.dtype,
+            )
+        else:
+            negative_add_time_ids = add_time_ids
 
         if do_classifier_free_guidance:
             prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
             add_text_embeds = torch.cat([negative_pooled_prompt_embeds, add_text_embeds], dim=0)
-            add_time_ids = torch.cat([add_time_ids, add_time_ids], dim=0)
+            add_time_ids = torch.cat([negative_add_time_ids, add_time_ids], dim=0)
 
         prompt_embeds = prompt_embeds.to(device)
         add_text_embeds = add_text_embeds.to(device)