Downloads · 30 days
0
control-hair-step-10000
WK1997/control-hair-step-10000
control-hair-step-10000 is a image-to-video model from WK1997. Use it for the image-to-video task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Public inference-only checkpoint for ControlHair: Synergizing Physics Simulator and Video Diffusion for Controllable Dynamic Hair Rendering.
Access
Public
Updated Aug 28, 2026
Repo size
2.5 GB
Likes
1
Trending 1
Repo makeup
Click a slice to open those files.
.safetensors2.5 GB · 100%
At a glance
- Task
- Image-to-Video
- License
- apache-2.0
- Access
- Public
- Created
- Aug 22, 2026
- Updated
- Aug 28, 2026
- SHA
- e638ee04
Base models
Model card
From the Hugging Face model README
ControlHair inference checkpoint
Public inference-only checkpoint for ControlHair: Synergizing Physics Simulator and Video Diffusion for Controllable Dynamic Hair Rendering.
- 800 LoRA tensors
- 26 conditioning-encoder tensors
- 2.29 GiB tensor payload
- composed from training revision 6627c52acd7648b0a014e93d9ce8383e3fe68f6b
The full DeepSpeed training save is not required for inference. ## License
The original ControlHair model modifications in this repository are licensed under the Apache License 2.0. This checkpoint is based on Wan2.1 (Apache-2.0) and UniAnimate-DiT (MIT); upstream components remain subject to their respective licenses and attribution requirements. See LICENSE and the upstream repositories for details.
- Task
- Image-to-Video
- License
- apache-2.0
- Created
- Aug 22, 2026
- Updated
- Aug 28, 2026