metadata
license: apache-2.0
datasets:
- FastVideo/Wan-Syn_77x448x832_600k
base_model:
- Wan-AI/Wan2.1-T2V-1.3B-Diffusers
FastVideo FastWan2.1-T2V-1.3B-Diffusers Model
Introduction
This model is jointly finetuned with DMD and VSA, based on Wan-AI/Wan2.1-T2V-1.3B-Diffusers. It supports efficient 3-step inference and generates high-quality videos at 61×448×832 resolution. We adopt the FastVideo 480P Synthetic Wan dataset, consisting of 600k synthetic latents.
Model Overview
- 3-step inference is supported and achieves up to 20 FPS on a single H100 GPU.
- Our model is trained on 61×448×832 resolution, but it supports generating videos with any resolution.(quality may degrade)
- Finetuning and inference scripts are available in the FastVideo repository:
- Try it out on FastVideo — we support a wide range of GPUs from H100 to 4090, and also support Mac users!
Training Infrastructure
Training was conducted on 4 nodes with 32 H200 GPUs in total, using a global batch size = 64.
We enable gradient checkpointing, set gradient_accumulation_steps=2, and use learning rate = 1e-5.
We set VSA attention sparsity to 0.8, and training runs for 4000 steps (~12 hours)
The detailed training example script is available here.
If you use the FastWan2.1-T2V-1.3B-Diffusers model for your research, please cite our paper:
@article{zhang2025vsa,
title={VSA: Faster Video Diffusion with Trainable Sparse Attention},
author={Zhang, Peiyuan and Huang, Haofeng and Chen, Yongqi and Lin, Will and Liu, Zhengzhong and Stoica, Ion and Xing, Eric and Zhang, Hao},
journal={arXiv preprint arXiv:2505.13389},
year={2025}
}
@article{zhang2025fast,
title={Fast video generation with sliding tile attention},
author={Zhang, Peiyuan and Chen, Yongqi and Su, Runlong and Ding, Hangliang and Stoica, Ion and Liu, Zhengzhong and Zhang, Hao},
journal={arXiv preprint arXiv:2502.04507},
year={2025}
}