Add inpaint lora scale support (huggingface#3460)

* add inpaint lora scale support

* add inpaint lora scale test

---------

Co-authored-by: yueyang.hyy <[email protected]>

Author: Glaceon-Hyy

pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py

@@ -14,7 +14,7 @@
 
 import inspect
 import warnings
-from typing import Callable, List, Optional, Union
+from typing import Any, Callable, Dict, List, Optional, Union
 
 import numpy as np
 import PIL
@@ -744,6 +744,7 @@ def __call__(
         return_dict: bool = True,
         callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
         callback_steps: int = 1,
+        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
     ):
         r"""
         Function invoked when calling the pipeline for generation.
@@ -815,7 +816,10 @@ def __call__(
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.
-
+            cross_attention_kwargs (`dict`, *optional*):
+                A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under
+                `self.processor` in
+                [diffusers.cross_attention](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/cross_attention.py).
         Examples:
 
         ```py
@@ -966,9 +970,13 @@ def __call__(
                 latent_model_input = torch.cat([latent_model_input, mask, masked_image_latents], dim=1)
 
                 # predict the noise residual
-                noise_pred = self.unet(latent_model_input, t, encoder_hidden_states=prompt_embeds, return_dict=False)[
-                    0
-                ]
+                noise_pred = self.unet(
+                    latent_model_input,
+                    t,
+                    encoder_hidden_states=prompt_embeds,
+                    cross_attention_kwargs=cross_attention_kwargs,
+                    return_dict=False,
+                )[0]
 
                 # perform guidance
                 if do_classifier_free_guidance: