Spaces:
Running on Zero
Running on Zero
| title: Light Forcing Video Generation | |
| emoji: 🎬 | |
| colorFrom: gray | |
| colorTo: pink | |
| sdk: gradio | |
| sdk_version: 6.15.1 | |
| app_file: app.py | |
| short_description: Text-to-video with Light Forcing sparse attention | |
| python_version: "3.12" | |
| startup_duration_timeout: 30m | |
| # Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention | |
| This Space demonstrates **Light Forcing**, a sparse attention acceleration method for autoregressive (AR) video generation models. It generates short videos (~5 seconds) from text prompts using the Wan2.1-T2V-1.3B model with Light Forcing's chunk-aware sparse attention. | |
| ## How it works | |
| Light Forcing introduces: | |
| - **Chunk-Aware Growth**: quantitatively estimates the contribution of each chunk to determine sparsity allocation | |
| - **Hierarchical Sparse Attention**: captures informative historical and local context in a coarse-to-fine manner | |
| ## Model | |
| - Base model: [Wan-AI/Wan2.1-T2V-1.3B](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B) | |
| - Light Forcing checkpoint: [mack-williams/Light-Forcing](https://huggingface.co/mack-williams/Light-Forcing) | |
| - Paper: [arXiv:2602.04789](https://arxiv.org/abs/2602.04789) | |
| - Code: [GitHub](https://github.com/chengtao-lv/LightForcing) | |
| ## License | |
| Apache 2.0 |