Papers › MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
Mingyuan Zhang, Zhongang Cai, Liang Pan, Fangzhou Hong, Xinying Guo, Lei Yang, Ziwei Liu
Human motion modeling is important for many modern graphics applications, which typically require professional skills. In order to remove the skill barriers for laymen, recent motion generation methods can directly generate human motions conditioned on natural languages. However, it remains challenging to achieve diverse and fine-grained motion generation with various text inputs. To address this problem, we propose MotionDiffuse, the first diffusion model-based text-driven motion generation framework, which demonstrates several desired properties over existing methods. 1) Probabilistic Mapping. Instead of a deterministic language-motion mapping, MotionDiffuse generates motions through a series of denoising steps in which variations are injected. 2) Realistic Synthesis. MotionDiffuse excels at modeling complicated data distribution and generating vivid motion sequences. 3) Multi-Level Manipulation. MotionDiffuse responds to fine-grained instructions on body parts, and arbitrary-length motion synthesis with time-varied text prompts. Our experiments show MotionDiffuse outperforms existing SoTA methods by convincing margins on text-driven motion generation and action-conditioned motion generation. A qualitative analysis further demonstrates MotionDiffuse's controllability for comprehensive motion generation. Homepage: https://mingyuan-zhang.github.io/projects/MotionDiffuse.html
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Motion Synthesis | HumanML3D | MotionDiffuse | Diversity | 9.410 | #30 of 37 | Archive leaderboard | report |
| Motion Synthesis | HumanML3D | MotionDiffuse | FID | 0.630 | #30 of 37 | Archive leaderboard | report |
| Motion Synthesis | HumanML3D | MotionDiffuse | Multimodality | 1.553 | #30 of 37 | Archive leaderboard | report |
| Motion Synthesis | HumanML3D | MotionDiffuse | R Precision Top3 | 0.782 | #30 of 37 | Archive leaderboard | report |
| Motion Synthesis | KIT Motion-Language | MotionDiffuse | Diversity | 11.10 | #26 of 31 | Archive leaderboard | report |
| Motion Synthesis | KIT Motion-Language | MotionDiffuse | FID | 1.954 | #26 of 31 | Archive leaderboard | report |
| Motion Synthesis | KIT Motion-Language | MotionDiffuse | Multimodality | 0.730 | #26 of 31 | Archive leaderboard | report |
| Motion Synthesis | KIT Motion-Language | MotionDiffuse | R Precision Top3 | 0.739 | #26 of 31 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections