Merge branch 'main' into get-2d-sincos-pos-embed-np

Author: hlky

docs/source/en/api/models/autoencoder_dc.md

@@ -37,6 +37,26 @@ from diffusers import AutoencoderDC
 ae = AutoencoderDC.from_pretrained("mit-han-lab/dc-ae-f32c32-sana-1.0-diffusers", torch_dtype=torch.float32).to("cuda")
 ```
 
+## Load a model in Diffusers via `from_single_file`
+
+```python
+from difusers import AutoencoderDC
+
+ckpt_path = "https://huggingface.co/mit-han-lab/dc-ae-f32c32-sana-1.0/blob/main/model.safetensors"
+model = AutoencoderDC.from_single_file(ckpt_path) 
+
+```
+
+The `AutoencoderDC` model has `in` and `mix` single file checkpoint variants that have matching checkpoint keys, but use different scaling factors. It is not possible for Diffusers to automatically infer the correct config file to use with the model based on just the checkpoint and will default to configuring the model using the `mix` variant config file. To override the automatically determined config, please use the `config` argument when using single file loading with `in` variant checkpoints. 
+
+```python
+from diffusers import AutoencoderDC
+
+ckpt_path = "https://huggingface.co/mit-han-lab/dc-ae-f128c512-in-1.0/blob/main/model.safetensors"
+model = AutoencoderDC.from_single_file(ckpt_path, config="mit-han-lab/dc-ae-f128c512-in-1.0-diffusers")
+```
+
+
 ## AutoencoderDC
 
 [[autodoc]] AutoencoderDC

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

@@ -143,6 +143,35 @@ image = pipe(
 image.save("output.png")
 ```
 
+Canny Control is also possible with a LoRA variant of this condition. The usage is as follows:
+
+```python
+# !pip install -U controlnet-aux
+import torch
+from controlnet_aux import CannyDetector
+from diffusers import FluxControlPipeline
+from diffusers.utils import load_image
+
+pipe = FluxControlPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to("cuda")
+pipe.load_lora_weights("black-forest-labs/FLUX.1-Canny-dev-lora")
+
+prompt = "A robot made of exotic candies and chocolates of different kinds. The background is filled with confetti and celebratory gifts."
+control_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")
+
+processor = CannyDetector()
+control_image = processor(control_image, low_threshold=50, high_threshold=200, detect_resolution=1024, image_resolution=1024)
+
+image = pipe(
+    prompt=prompt,
+    control_image=control_image,
+    height=1024,
+    width=1024,
+    num_inference_steps=50,
+    guidance_scale=30.0,
+).images[0]
+image.save("output.png")
+```
+
 ### Depth Control
 
 **Note:** `black-forest-labs/Flux.1-Depth-dev` is _not_ a ControlNet model. [`ControlNetModel`] models are a separate component from the UNet/Transformer whose residuals are added to the actual underlying model. Depth Control is an alternate architecture that achieves effectively the same results as a ControlNet model would, by using channel-wise concatenation with input control condition and ensuring the transformer learns structure control by following the condition as closely as possible.
@@ -174,6 +203,36 @@ image = pipe(
 image.save("output.png")
 ```
 
+Depth Control is also possible with a LoRA variant of this condition. The usage is as follows:
+
+```python
+# !pip install git+https://github.com/huggingface/image_gen_aux
+import torch
+from diffusers import FluxControlPipeline, FluxTransformer2DModel
+from diffusers.utils import load_image
+from image_gen_aux import DepthPreprocessor
+
+pipe = FluxControlPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to("cuda")
+pipe.load_lora_weights("black-forest-labs/FLUX.1-Depth-dev-lora")
+
+prompt = "A robot made of exotic candies and chocolates of different kinds. The background is filled with confetti and celebratory gifts."
+control_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")
+
+processor = DepthPreprocessor.from_pretrained("LiheYoung/depth-anything-large-hf")
+control_image = processor(control_image)[0].convert("RGB")
+
+image = pipe(
+    prompt=prompt,
+    control_image=control_image,
+    height=1024,
+    width=1024,
+    num_inference_steps=30,
+    guidance_scale=10.0,
+    generator=torch.Generator().manual_seed(42),
+).images[0]
+image.save("output.png")
+```
+
 ### Redux
 
 * Flux Redux pipeline is an adapter for FLUX.1 base models. It can be used with both flux-dev and flux-schnell, for image-to-image generation.

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

@@ -48,6 +48,11 @@ Since RegEx is supported as a way for matching layer identifiers, it is crucial
   - all
   - __call__
 
+## StableDiffusionPAGInpaintPipeline
+[[autodoc]] StableDiffusionPAGInpaintPipeline
+	- all
+	- __call__
+
 ## StableDiffusionPAGPipeline
 [[autodoc]] StableDiffusionPAGPipeline
 	- all

examples/cogvideo/train_cogvideox_image_to_video_lora.py

@@ -872,10 +872,9 @@ def prepare_rotary_positional_embeddings(
         crops_coords=grid_crops_coords,
         grid_size=(grid_height, grid_width),
         temporal_size=num_frames,
+        device=device,
     )
 
-    freqs_cos = freqs_cos.to(device=device)
-    freqs_sin = freqs_sin.to(device=device)
     return freqs_cos, freqs_sin
 
 

examples/cogvideo/train_cogvideox_lora.py

@@ -894,10 +894,9 @@ def prepare_rotary_positional_embeddings(
         crops_coords=grid_crops_coords,
         grid_size=(grid_height, grid_width),
         temporal_size=num_frames,
+        device=device,
     )
 
-    freqs_cos = freqs_cos.to(device=device)
-    freqs_sin = freqs_sin.to(device=device)
     return freqs_cos, freqs_sin