Few-Step Streaming Video Generation via Condition Shifting

Deyuan Liu, Jungang Li, Kaiwen Zheng, jiang kai, Jintao Chen, Yaole Wang, Ming Lin, Tao Lin, Jianfei Chen, Jun Zhu, Jintao Zhang

Few-Step Streaming Video Generation via Condition Shifting: 88 upvotes on Hugging Face Daily Papers, #1 of 39 papers on 2026-11-11. Day-by-day upvote history.

Upvotes over time

It had 47 upvotes by its first day, 88 upvotes by the next day, 88 upvotes by day 3, 88 upvotes by day 7, and has 88 now. It ranked #3 of 133 papers in its week and #8 of 340 in its month.

Few-step sampling reduces the cost of streaming video generation. Distribution Matching Distillation (DMD) supervises few-step generators with a separate fake-score network, which adds training memory and computation and must track the evolving generator. We extend APEX to streaming video by using condition shifting to estimate the velocity field of the generated distribution within the generator. The original text condition selects generation, while a shifted condition selects fake estimation using the same parameters. This removes the independent fake network while retaining S2-Avatar's frozen reference teacher, Self-Replay Forcing, and perceptual regularization. We evaluate APEX on 180-second videos using three backbone evaluations per block and a one-step spatial Refiner, with a 70-case human study and a 320-case StreamAV-Bench comparison. Compared with S2-Avatar, APEX achieves higher video instruction fulfillment on the Progressive track (3.856 versus 3.831) and higher visual aesthetics across both tracks (0.641898 versus 0.632606). Human raters favor APEX most strongly on instruction following, with +30.0% net preference, followed by consistency and video quality at +4.3% each. Motion quality favors S2-Avatar, audiovisual synchronization is predominantly tied, and usability is unchanged. Separate measurements under matched training settings show 4.4% lower peak allocated GPU memory per GPU and 9.2% shorter mean iteration time than DMD.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.