Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.03520 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917251993567232 |
|---|---|
| author | Cai, Yiyi Wu, Yuhan Li, Kunhang Zhou, You Zheng, Bo Liu, Haiyang |
| author_facet | Cai, Yiyi Wu, Yuhan Li, Kunhang Zhou, You Zheng, Bo Liu, Haiyang |
| contents | We present FloodDiffusion, a new framework for text-driven, streaming human motion generation. Given time-varying text prompts, FloodDiffusion generates text-aligned, seamless motion sequences with real-time latency. Unlike existing methods that rely on chunk-by-chunk or auto-regressive model with diffusion head, we adopt a diffusion forcing framework to model this time-series generation task under time-varying control events. We find that a straightforward implementation of vanilla diffusion forcing (as proposed for video models) fails to model real motion distributions. We demonstrate that to guarantee modeling the output distribution, the vanilla diffusion forcing must be tailored to: (i) train with a bi-directional attention instead of casual attention; (ii) implement a lower triangular time scheduler instead of a random one; (iii) utilize a continues time-varying way to introduce text conditioning. With these improvements, we demonstrate in the first time that the diffusion forcing-based framework achieves state-of-the-art performance on the streaming motion generation task, reaching an FID of 0.057 on the HumanML3D benchmark. Models, code, and weights are available. https://shandaai.github.io/FloodDiffusion/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_03520 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FloodDiffusion: Tailored Diffusion Forcing for Streaming Motion Generation Cai, Yiyi Wu, Yuhan Li, Kunhang Zhou, You Zheng, Bo Liu, Haiyang Computer Vision and Pattern Recognition We present FloodDiffusion, a new framework for text-driven, streaming human motion generation. Given time-varying text prompts, FloodDiffusion generates text-aligned, seamless motion sequences with real-time latency. Unlike existing methods that rely on chunk-by-chunk or auto-regressive model with diffusion head, we adopt a diffusion forcing framework to model this time-series generation task under time-varying control events. We find that a straightforward implementation of vanilla diffusion forcing (as proposed for video models) fails to model real motion distributions. We demonstrate that to guarantee modeling the output distribution, the vanilla diffusion forcing must be tailored to: (i) train with a bi-directional attention instead of casual attention; (ii) implement a lower triangular time scheduler instead of a random one; (iii) utilize a continues time-varying way to introduce text conditioning. With these improvements, we demonstrate in the first time that the diffusion forcing-based framework achieves state-of-the-art performance on the streaming motion generation task, reaching an FID of 0.057 on the HumanML3D benchmark. Models, code, and weights are available. https://shandaai.github.io/FloodDiffusion/ |
| title | FloodDiffusion: Tailored Diffusion Forcing for Streaming Motion Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.03520 |