--- title: DistillAlign โ€” Autoregressive Video Distillation emoji: ๐ŸŽฌ colorFrom: green colorTo: pink sdk: gradio sdk_version: 6.30.0 app_file: app.py short_description: Few-step causal text-to-video with a 1.3B student python_version: "3.12" startup_duration_timeout: 1h --- # ๐ŸŽฌ DistillAlign โ€” Autoregressive Video Distillation **Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation** This Space runs the released **DistillAlign** generator: a **Wan2.1-T2V-1.3B** student distilled for few-step *causal* (autoregressive) text-to-video generation. It samples 21 latent frames in 7 causal blocks with a 4-step DMD schedule (`1000 โ†’ 750 โ†’ 500 โ†’ 250`), keeps a KV cache across blocks, and streams the latents through the causal Wan VAE โ€” **81 frames / 480ร—832 / 16 fps โ‰ˆ 5 s** of video. ## Links - **Model**: [LiJiaxing/DistillAlign](https://huggingface.co/LiJiaxing/DistillAlign) - **Code**: [LiJiaxing0213/DistillAlign](https://github.com/LiJiaxing0213/DistillAlign) - **Paper**: [arXiv 2607.26811](https://huggingface.co/papers/2607.26811) ยท [project page](https://lijiaxing0213.github.io/DistillAlign/) ## Notes - **Prompt style**: the model was distilled on long, detailed captions. Short prompts work but detailed multi-sentence descriptions give markedly better results โ€” the example prompts below are the authors' own evaluation prompts. - **Speed**: generation takes roughly a minute on the ZeroGPU RTX PRO 6000 (7 blocks ร— 4 denoising steps, plus streaming VAE decode). - **Seed**: set a seed to reproduce a video, or leave `0` for a random one. - **Checkpoint used**: `checkpoints/distillalign_distill_1p3b_teacher.pt` โ€” the final joint-distilled 1.3B generator (1.3B DMD teacher), loaded with `strict=True` into a causal Wan2.1-1.3B wrapper. ## Credits & licenses This is a demo wrapper around the authors' code. The example prompts are the authors' own evaluation prompts from `prompts/distribution_eval_16.txt` in the [official repository](https://github.com/LiJiaxing0213/DistillAlign) (Apache-2.0). The DistillAlign code and released weights are Apache-2.0; upstream [Wan2.1-T2V-1.3B](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B) weights remain subject to their own license. The causal VAE decoder wrapper follows the [Self-Forcing](https://github.com/guandeh17/Self-Forcing) (Apache-2.0) implementation.