Merge branch 'main' into enable_xpu

Author: sayakpaul

docs/source/en/api/pipelines/controlnet_sd3.md

@@ -28,6 +28,7 @@ This controlnet code is mainly implemented by [The InstantX Team](https://huggin
 | ControlNet type | Developer | Link |
 | -------- | ---------- | ---- |
 | Canny | [The InstantX Team](https://huggingface.co/InstantX) | [Link](https://huggingface.co/InstantX/SD3-Controlnet-Canny) |
+| Depth | [The InstantX Team](https://huggingface.co/InstantX) | [Link](https://huggingface.co/InstantX/SD3-Controlnet-Depth) |
 | Pose | [The InstantX Team](https://huggingface.co/InstantX) | [Link](https://huggingface.co/InstantX/SD3-Controlnet-Pose) |
 | Tile | [The InstantX Team](https://huggingface.co/InstantX) | [Link](https://huggingface.co/InstantX/SD3-Controlnet-Tile) |
 | Inpainting | [The AlimamaCreative Team](https://huggingface.co/alimama-creative) | [link](https://huggingface.co/alimama-creative/SD3-Controlnet-Inpainting) |

examples/wuerstchen/text_to_image/README.md renamed to examples/research_projects/wuerstchen/text_to_image/README.md

@@ -795,13 +795,11 @@ def apply_overlay(
                 The final image with the overlay applied.
         """
 
-        width, height = image.width, image.height
-
-        init_image = self.resize(init_image, width=width, height=height)
-        mask = self.resize(mask, width=width, height=height)
+        width, height = init_image.width, init_image.height
 
         init_image_masked = PIL.Image.new("RGBa", (width, height))
         init_image_masked.paste(init_image.convert("RGBA").convert("RGBa"), mask=ImageOps.invert(mask.convert("L")))
+
         init_image_masked = init_image_masked.convert("RGBA")
 
         if crop_coords is not None:

examples/wuerstchen/text_to_image/__init__.py renamed to examples/research_projects/wuerstchen/text_to_image/__init__.py

@@ -74,7 +74,7 @@ def load_ip_adapter(
                 list is passed, it should have the same length as `weight_name`.
             weight_name (`str` or `List[str]`):
                 The name of the weight file to load. If a list is passed, it should have the same length as
-                `weight_name`.
+                `subfolder`.
             image_encoder_folder (`str`, *optional*, defaults to `image_encoder`):
                 The subfolder location of the image encoder within a larger model repository on the Hub or locally.
                 Pass `None` to not load the image encoder. If the image encoder is located in a folder inside

examples/wuerstchen/text_to_image/modeling_efficient_net_encoder.py renamed to examples/research_projects/wuerstchen/text_to_image/modeling_efficient_net_encoder.py

@@ -5053,19 +5053,46 @@ def __init__(self):
 
 AttentionProcessor = Union[
     AttnProcessor,
-    AttnProcessor2_0,
-    FusedAttnProcessor2_0,
-    XFormersAttnProcessor,
-    SlicedAttnProcessor,
+    CustomDiffusionAttnProcessor,
     AttnAddedKVProcessor,
-    SlicedAttnAddedKVProcessor,
     AttnAddedKVProcessor2_0,
+    JointAttnProcessor2_0,
+    PAGJointAttnProcessor2_0,
+    PAGCFGJointAttnProcessor2_0,
+    FusedJointAttnProcessor2_0,
+    AllegroAttnProcessor2_0,
+    AuraFlowAttnProcessor2_0,
+    FusedAuraFlowAttnProcessor2_0,
+    FluxAttnProcessor2_0,
+    FluxAttnProcessor2_0_NPU,
+    FusedFluxAttnProcessor2_0,
+    FusedFluxAttnProcessor2_0_NPU,
+    CogVideoXAttnProcessor2_0,
+    FusedCogVideoXAttnProcessor2_0,
     XFormersAttnAddedKVProcessor,
-    CustomDiffusionAttnProcessor,
+    XFormersAttnProcessor,
+    AttnProcessorNPU,
+    AttnProcessor2_0,
+    MochiVaeAttnProcessor2_0,
+    StableAudioAttnProcessor2_0,
+    HunyuanAttnProcessor2_0,
+    FusedHunyuanAttnProcessor2_0,
+    PAGHunyuanAttnProcessor2_0,
+    PAGCFGHunyuanAttnProcessor2_0,
+    LuminaAttnProcessor2_0,
+    MochiAttnProcessor2_0,
+    FusedAttnProcessor2_0,
     CustomDiffusionXFormersAttnProcessor,
     CustomDiffusionAttnProcessor2_0,
-    PAGCFGIdentitySelfAttnProcessor2_0,
+    SlicedAttnProcessor,
+    SlicedAttnAddedKVProcessor,
+    IPAdapterAttnProcessor,
+    IPAdapterAttnProcessor2_0,
+    IPAdapterXFormersAttnProcessor,
     PAGIdentitySelfAttnProcessor2_0,
-    PAGCFGHunyuanAttnProcessor2_0,
-    PAGHunyuanAttnProcessor2_0,
+    PAGCFGIdentitySelfAttnProcessor2_0,
+    LoRAAttnProcessor,
+    LoRAAttnProcessor2_0,
+    LoRAXFormersAttnProcessor,
+    LoRAAttnAddedKVProcessor,
 ]