VA-TDM:以速度對抗蒸餾改善少步擴散模型的統一方法
VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation
VA-TDM結合速度對抗蒸餾(VAD)與軌跡感知監督,在文字生成圖像和文字生成影片中,於多種模型骨幹上取得四步生成的最先進表現。VAD透過學習到的判別器比較學生與教師的速度場,並統一分數蒸餾、基於Fisher的匹配及矩匹配。VA-TDM可擴展至33B MiniMax-H3;按人類偏好評分,其表現明顯優於少步 Fast-H3,並更接近原始多步 H3。
Published on Nov 4
Authors:
,
Abstract
Velocity Adversarial Distillation and trajectory-aware supervision enable high-quality few-step diffusion and flow generation with state-of-the-art results.
Few-step distillation offers efficient generation with diffusion and flow models, but preserving quality with only a few sampling steps remains challenging. Distribution-matching methods via score distillation provide a strong foundation, yet they rely on accurately tracking the student's changing distribution. At intermediate generation steps in few-step sampling, student-score estimation can be difficult, and commonly used estimators may describe a different distribution from the one used to update the student. Flow matching allows a more flexible approach to supervision through velocity fields constructed from the student's sampling process. Building on this perspective, we introduce Velocity Adversarial Distillation (VAD), which uses a learned critic to compare student and teacher fields and turn their disagreement into feedback for learning. VAD unifies score distillation, Fisher-based matching, and moment matching, also explaining existing heuristic MMD updates and delivering new training objectives. We further develop VA-TDM, which follows trajectory distribution matching: providing supervision for partial denoising along the student trajectory. Beyond this, VA-TDM combines transition-aware online velocity learning and dual-form VAD supervision across intermediate student transitions. Extensive results show that VA-TDM is powerful for learning few-step generators, achieving state-of-the-art four-step performance in both text-to-image and text-to-video generation across various backbones and scaling effectively to 33B MiniMax-H3. In particular, our VA-TDM-H3 notably outperforms the few-step Fast-H3 and is closer to the original many-step H3 according to human preference.
View arXiv page View PDF Project page GitHub 0 Add to collection
Get this paper in your agent:
hf papers read 2611.06796
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.06796 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.06796 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.06796 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co