跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-13AI 評分48

FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching

FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching

AI 導讀

FlashVSR+提出混合注意力架構及獎勵收益分佈匹配蒸餾(Ry-DMD),以改善影片超分辨率的高解像度推理效率及生成結果與人類偏好的對齊。混合注意力最高帶來 2 倍 DiT 加速及 45% 峯值記憶體用量減少,支援在單張 24GB RTX 4090 上進行無切片 4K 影片超分辨率。Ry-DMD 亦可應用於文字生成圖像,論文並公開程式碼、模型及訓練資料。

正文

Published on Oct 13

Authors:

,

,

,

,

,

,

,

,

Abstract

Recent video super-resolution (VSR) models achieve efficient one-step generation through diffusion distillation. However, high-resolution inference remains costly, and distilled models are difficult to align with human preferences. These challenges call for improvements in both model architecture and training strategy. We present FlashVSR+ to address both limitations. On the architecture side, we introduce hybrid attention based on the strong locality observed in pretrained VSR models, while retaining sparse global interaction for long-range consistency. It achieves up to 2times DiT speedup and 45\% lower peak memory, enabling spatially untiled 4K VSR on a single 24GB RTX 4090. On the training side, we propose Reward-Yield Distribution Matching Distillation (Ry-DMD) for preference-aligned one-step generation. Ry-DMD uses reward-weighted teacher rollouts to incorporate black-box rewards into distribution matching, without backpropagating through the reward model. We further show that Ry-DMD generalizes beyond VSR to T2I generation. Together, FlashVSR+ delivers stronger restoration quality and substantially improves high-resolution efficiency, with consistent gains in user preference. We release our code, models, and training data at https://www.flashvsr.tech{FlashBlue{www.flashvsr.tech}}.

View arXiv page View PDF Project page GitHub 11 Add to collection

Get this paper in your agent:

hf papers read 2610.17552

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

ruchangyao/FlashVSR_plus

Video-to-Video •

Updated about 2 hours ago

•

25

•

3

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.17552 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/2610.17552 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