Thanks!
Dai-Wenxun
wxDai
AI & ML interests
None yet
Recent Activity
liked a model 1 day ago
MiniMaxAI/MiniMax-H3 liked a model 2 days ago
jdopensource/JoyAI-Video-Edit upvoted a paper 2 days ago
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive DiffusionOrganizations
replied to their post over 2 years ago
posted an update over 2 years ago
Post
1673
🔥Motion Latent Consistency Model🔥
Introducing MotionLCM💃, controlling and generating a motion in milliseconds!
Huggingface Space:
wxDai/MotionLCM
Huggingface Paper:
MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model (2404.19759)
Project page: https://dai-wenxun.github.io/MotionLCM-page/
Paper: https://arxiv.org/pdf/2404.19759.pdf
Code: https://github.com/Dai-Wenxun/MotionLCM
video: https://www.youtube.com/watch?v=BhrGmJYaRE4
MotionLCM supports inference pipelines of 1-4 steps, with almost no difference in effectiveness between 1 and 4 steps. Generating approximately 200 frames of motion only takes about 30ms, which averages to approximately 6k fps.
Our MotionLCM can achieve high-quality text-to-motion and precise motion control results (both sparse and dense conditions) in ∼30 ms.
We integrated a control module into the diffusion of the latent space, named Motion ControlNet, to achieve controllable motion generation. Our control algorithm is approximately 1,000 times faster than the best-performing baseline, with comparable quality.
Introducing MotionLCM💃, controlling and generating a motion in milliseconds!
Huggingface Space:
wxDai/MotionLCM
Huggingface Paper:
MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model (2404.19759)
Project page: https://dai-wenxun.github.io/MotionLCM-page/
Paper: https://arxiv.org/pdf/2404.19759.pdf
Code: https://github.com/Dai-Wenxun/MotionLCM
video: https://www.youtube.com/watch?v=BhrGmJYaRE4
MotionLCM supports inference pipelines of 1-4 steps, with almost no difference in effectiveness between 1 and 4 steps. Generating approximately 200 frames of motion only takes about 30ms, which averages to approximately 6k fps.
Our MotionLCM can achieve high-quality text-to-motion and precise motion control results (both sparse and dense conditions) in ∼30 ms.
We integrated a control module into the diffusion of the latent space, named Motion ControlNet, to achieve controllable motion generation. Our control algorithm is approximately 1,000 times faster than the best-performing baseline, with comparable quality.
- 2 replies