updates

Author: sayakpaul

.github/workflows/push_tests_mps.yml

@@ -46,7 +46,7 @@ jobs:
       shell: arch -arch arm64 bash {0}
       run: |
         ${CONDA_RUN} python -m pip install --upgrade pip uv
-        ${CONDA_RUN} python -m uv pip install -e [quality,test]
+        ${CONDA_RUN} python -m uv pip install -e ".[quality,test]"
         ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio
         ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
         ${CONDA_RUN} python -m uv pip install transformers --upgrade

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

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import AutoencoderKLHunyuanVideo
 
-vae = AutoencoderKLHunyuanVideo.from_pretrained("tencent/HunyuanVideo", torch_dtype=torch.float16)
+vae = AutoencoderKLHunyuanVideo.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder="vae", torch_dtype=torch.float16)
 ```
 
 ## AutoencoderKLHunyuanVideo

docs/source/en/api/models/hunyuan_video_transformer_3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import HunyuanVideoTransformer3DModel
 
-transformer = HunyuanVideoTransformer3DModel.from_pretrained("tencent/HunyuanVideo", torch_dtype=torch.bfloat16)
+transformer = HunyuanVideoTransformer3DModel.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder="transformer", torch_dtype=torch.bfloat16)
 ```
 
 ## HunyuanVideoTransformer3DModel

docs/source/en/api/models/sana_transformer2d.md

@@ -22,7 +22,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import SanaTransformer2DModel
 
-transformer = SanaTransformer2DModel.from_pretrained("Efficient-Large-Model/Sana_1600M_1024px_diffusers", subfolder="transformer", torch_dtype=torch.float16)
+transformer = SanaTransformer2DModel.from_pretrained("Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
 ```
 
 ## SanaTransformer2DModel

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

@@ -268,6 +268,43 @@ images = pipe(
 images[0].save("flux-redux.png")
 ```
 
+## Combining Flux Turbo LoRAs with Flux Control, Fill, and Redux
+
+We can combine Flux Turbo LoRAs with Flux Control and other pipelines like Fill and Redux to enable few-steps' inference. The example below shows how to do that for Flux Control LoRA for depth and turbo LoRA from [`ByteDance/Hyper-SD`](https://hf.co/ByteDance/Hyper-SD).
+
+```py
+from diffusers import FluxControlPipeline
+from image_gen_aux import DepthPreprocessor
+from diffusers.utils import load_image
+from huggingface_hub import hf_hub_download
+import torch
+
+control_pipe = FluxControlPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
+control_pipe.load_lora_weights("black-forest-labs/FLUX.1-Depth-dev-lora", adapter_name="depth")
+control_pipe.load_lora_weights(
+    hf_hub_download("ByteDance/Hyper-SD", "Hyper-FLUX.1-dev-8steps-lora.safetensors"), adapter_name="hyper-sd"
+)
+control_pipe.set_adapters(["depth", "hyper-sd"], adapter_weights=[0.85, 0.125])
+control_pipe.enable_model_cpu_offload()
+
+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 = control_pipe(
+    prompt=prompt,
+    control_image=control_image,
+    height=1024,
+    width=1024,
+    num_inference_steps=8,
+    guidance_scale=10.0,
+    generator=torch.Generator().manual_seed(42),
+).images[0]
+image.save("output.png")
+```
+
 ## Running FP16 inference
 
 Flux can generate high-quality images with FP16 (i.e. to accelerate inference on Turing/Volta GPUs) but produces different outputs compared to FP32/BF16. The issue is that some activations in the text encoders have to be clipped when running in FP16, which affects the overall image. Forcing text encoders to run with FP32 inference thus removes this output difference. See [here](https://github.com/huggingface/diffusers/pull/9097#issuecomment-2272292516) for details.

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

@@ -29,7 +29,7 @@ Recommendations for inference:
 - Transformer should be in `torch.bfloat16`.
 - VAE should be in `torch.float16`.
 - `num_frames` should be of the form `4 * k + 1`, for example `49` or `129`.
-- For smaller resolution images, try lower values of `shift` (between `2.0` to `5.0`) in the [Scheduler](https://huggingface.co/docs/diffusers/main/en/api/schedulers/flow_match_euler_discrete#diffusers.FlowMatchEulerDiscreteScheduler.shift). For larger resolution images, try higher values (between `7.0` and `12.0`). The default value is `7.0` for HunyuanVideo.
+- For smaller resolution videos, try lower values of `shift` (between `2.0` to `5.0`) in the [Scheduler](https://huggingface.co/docs/diffusers/main/en/api/schedulers/flow_match_euler_discrete#diffusers.FlowMatchEulerDiscreteScheduler.shift). For larger resolution images, try higher values (between `7.0` and `12.0`). The default value is `7.0` for HunyuanVideo.
 - For more information about supported resolutions and other details, please refer to the original repository [here](https://github.com/Tencent/HunyuanVideo/).
 
 ## HunyuanVideoPipeline

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

@@ -79,7 +79,6 @@ transformer = LTXVideoTransformer3DModel.from_single_file(
 pipe = LTXPipeline.from_pretrained(
     "Lightricks/LTX-Video",
     transformer=transformer,
-    generator=torch.manual_seed(0),
     torch_dtype=torch.bfloat16,
 )
 pipe.enable_model_cpu_offload()

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

@@ -13,7 +13,7 @@
 # limitations under the License.
 -->
 
-# Mochi
+# Mochi 1 Preview
 
 [Mochi 1 Preview](https://huggingface.co/genmo/mochi-1-preview) from Genmo.
 
@@ -25,6 +25,201 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.m
 
 </Tip>
 
+## Generating videos with Mochi-1 Preview
+
+The following example will download the full precision `mochi-1-preview` weights and produce the highest quality results but will require at least 42GB VRAM to run.
+
+```python
+import torch
+from diffusers import MochiPipeline
+from diffusers.utils import export_to_video
+
+pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview")
+
+# Enable memory savings
+pipe.enable_model_cpu_offload()
+pipe.enable_vae_tiling()
+
+prompt = "Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k."
+
+with torch.autocast("cuda", torch.bfloat16, cache_enabled=False):
+      frames = pipe(prompt, num_frames=85).frames[0]
+
+export_to_video(frames, "mochi.mp4", fps=30)
+```
+
+## Using a lower precision variant to save memory
+
+The following example will use the `bfloat16` variant of the model and requires 22GB VRAM to run. There is a slight drop in the quality of the generated video as a result.
+
+```python
+import torch
+from diffusers import MochiPipeline
+from diffusers.utils import export_to_video
+
+pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview", variant="bf16", torch_dtype=torch.bfloat16)
+
+# Enable memory savings
+pipe.enable_model_cpu_offload()
+pipe.enable_vae_tiling()
+
+prompt = "Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k."
+frames = pipe(prompt, num_frames=85).frames[0]
+
+export_to_video(frames, "mochi.mp4", fps=30)
+```
+
+## Reproducing the results from the Genmo Mochi repo
+
+The [Genmo Mochi implementation](https://github.com/genmoai/mochi/tree/main) uses different precision values for each stage in the inference process. The text encoder and VAE use `torch.float32`, while the DiT uses `torch.bfloat16` with the [attention kernel](https://pytorch.org/docs/stable/generated/torch.nn.attention.sdpa_kernel.html#torch.nn.attention.sdpa_kernel) set to `EFFICIENT_ATTENTION`. Diffusers pipelines currently do not support setting different `dtypes` for different stages of the pipeline. In order to run inference in the same way as the the original implementation, please refer to the following example.
+
+<Tip>
+The original Mochi implementation zeros out empty prompts. However, enabling this option and placing the entire pipeline under autocast can lead to numerical overflows with the T5 text encoder.
+
+When enabling `force_zeros_for_empty_prompt`, it is recommended to run the text encoding step outside the autocast context in full precision.
+</Tip>
+
+<Tip>
+Decoding the latents in full precision is very memory intensive. You will need at least 70GB VRAM to generate the 163 frames in this example. To reduce memory, either reduce the number of frames or run the decoding step in `torch.bfloat16`.
+</Tip>
+
+```python
+import torch
+from torch.nn.attention import SDPBackend, sdpa_kernel
+
+from diffusers import MochiPipeline
+from diffusers.utils import export_to_video
+from diffusers.video_processor import VideoProcessor
+
+pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview", force_zeros_for_empty_prompt=True)
+pipe.enable_vae_tiling()
+pipe.enable_model_cpu_offload()
+
+prompt =  "An aerial shot of a parade of elephants walking across the African savannah. The camera showcases the herd and the surrounding landscape."
+
+with torch.no_grad():
+    prompt_embeds, prompt_attention_mask, negative_prompt_embeds, negative_prompt_attention_mask = (
+        pipe.encode_prompt(prompt=prompt)
+    )
+
+with torch.autocast("cuda", torch.bfloat16):
+    with sdpa_kernel(SDPBackend.EFFICIENT_ATTENTION):
+        frames = pipe(
+            prompt_embeds=prompt_embeds,
+            prompt_attention_mask=prompt_attention_mask,
+            negative_prompt_embeds=negative_prompt_embeds,
+            negative_prompt_attention_mask=negative_prompt_attention_mask,
+            guidance_scale=4.5,
+            num_inference_steps=64,
+            height=480,
+            width=848,
+            num_frames=163,
+            generator=torch.Generator("cuda").manual_seed(0),
+            output_type="latent",
+            return_dict=False,
+        )[0]
+
+video_processor = VideoProcessor(vae_scale_factor=8)
+has_latents_mean = hasattr(pipe.vae.config, "latents_mean") and pipe.vae.config.latents_mean is not None
+has_latents_std = hasattr(pipe.vae.config, "latents_std") and pipe.vae.config.latents_std is not None
+if has_latents_mean and has_latents_std:
+    latents_mean = (
+        torch.tensor(pipe.vae.config.latents_mean).view(1, 12, 1, 1, 1).to(frames.device, frames.dtype)
+    )
+    latents_std = (
+        torch.tensor(pipe.vae.config.latents_std).view(1, 12, 1, 1, 1).to(frames.device, frames.dtype)
+    )
+    frames = frames * latents_std / pipe.vae.config.scaling_factor + latents_mean
+else:
+    frames = frames / pipe.vae.config.scaling_factor
+
+with torch.no_grad():
+    video = pipe.vae.decode(frames.to(pipe.vae.dtype), return_dict=False)[0]
+
+video = video_processor.postprocess_video(video)[0]
+export_to_video(video, "mochi.mp4", fps=30)
+```
+
+## Running inference with multiple GPUs
+
+It is possible to split the large Mochi transformer across multiple GPUs using the `device_map` and `max_memory` options in `from_pretrained`. In the following example we split the model across two GPUs, each with 24GB of VRAM.
+
+```python
+import torch
+from diffusers import MochiPipeline, MochiTransformer3DModel
+from diffusers.utils import export_to_video
+
+model_id = "genmo/mochi-1-preview"
+transformer = MochiTransformer3DModel.from_pretrained(
+    model_id,
+    subfolder="transformer",
+    device_map="auto",
+    max_memory={0: "24GB", 1: "24GB"}
+)
+
+pipe = MochiPipeline.from_pretrained(model_id,  transformer=transformer)
+pipe.enable_model_cpu_offload()
+pipe.enable_vae_tiling()
+
+with torch.autocast(device_type="cuda", dtype=torch.bfloat16, cache_enabled=False):
+    frames = pipe(
+        prompt="Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k.",
+        negative_prompt="",
+        height=480,
+        width=848,
+        num_frames=85,
+        num_inference_steps=50,
+        guidance_scale=4.5,
+        num_videos_per_prompt=1,
+        generator=torch.Generator(device="cuda").manual_seed(0),
+        max_sequence_length=256,
+        output_type="pil",
+    ).frames[0]
+
+export_to_video(frames, "output.mp4", fps=30)
+```
+
+## Using single file loading with the Mochi Transformer
+
+You can use `from_single_file` to load the Mochi transformer in its original format.
+
+<Tip>
+Diffusers currently doesn't support using the FP8 scaled versions of the Mochi single file checkpoints.
+</Tip>
+
+```python
+import torch
+from diffusers import MochiPipeline, MochiTransformer3DModel
+from diffusers.utils import export_to_video
+
+model_id = "genmo/mochi-1-preview"
+
+ckpt_path = "https://huggingface.co/Comfy-Org/mochi_preview_repackaged/blob/main/split_files/diffusion_models/mochi_preview_bf16.safetensors"
+
+transformer = MochiTransformer3DModel.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16)
+
+pipe = MochiPipeline.from_pretrained(model_id,  transformer=transformer)
+pipe.enable_model_cpu_offload()
+pipe.enable_vae_tiling()
+
+with torch.autocast(device_type="cuda", dtype=torch.bfloat16, cache_enabled=False):
+    frames = pipe(
+        prompt="Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k.",
+        negative_prompt="",
+        height=480,
+        width=848,
+        num_frames=85,
+        num_inference_steps=50,
+        guidance_scale=4.5,
+        num_videos_per_prompt=1,
+        generator=torch.Generator(device="cuda").manual_seed(0),
+        max_sequence_length=256,
+        output_type="pil",
+    ).frames[0]
+
+export_to_video(frames, "output.mp4", fps=30)
+```
+
 ## MochiPipeline
 
 [[autodoc]] MochiPipeline

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

@@ -32,9 +32,9 @@ Available models:
 
 | Model | Recommended dtype |
 |:-----:|:-----------------:|
+| [`Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers) | `torch.bfloat16` |
 | [`Efficient-Large-Model/Sana_1600M_1024px_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px_diffusers) | `torch.float16` |
 | [`Efficient-Large-Model/Sana_1600M_1024px_MultiLing_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px_MultiLing_diffusers) | `torch.float16` |
-| [`Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers) | `torch.bfloat16` |
 | [`Efficient-Large-Model/Sana_1600M_512px_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_1600M_512px_diffusers) | `torch.float16` |
 | [`Efficient-Large-Model/Sana_1600M_512px_MultiLing_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_1600M_512px_MultiLing_diffusers) | `torch.float16` |
 | [`Efficient-Large-Model/Sana_600M_1024px_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_600M_1024px_diffusers) | `torch.float16` |

docs/source/en/quantization/gguf.md

@@ -45,12 +45,11 @@ transformer = FluxTransformer2DModel.from_single_file(
 pipe = FluxPipeline.from_pretrained(
     "black-forest-labs/FLUX.1-dev",
     transformer=transformer,
-    generator=torch.manual_seed(0),
     torch_dtype=torch.bfloat16,
 )
 pipe.enable_model_cpu_offload()
 prompt = "A cat holding a sign that says hello world"
-image = pipe(prompt).images[0]
+image = pipe(prompt, generator=torch.manual_seed(0)).images[0]
 image.save("flux-gguf.png")
 ```