Papers › Video Diffusion Transformers are In-Context Learners
Video Diffusion Transformers are In-Context Learners
Zhengcong Fei, Di Qiu, Changqian Yu, Debang Li, Mingyuan Fan, Xiang Wen
This paper investigates a solution for enabling in-context capabilities of video diffusion transformers, with minimal tuning required for activation. Specifically, we propose a simple pipeline to leverage in-context generation: (i) concatenate videos along spacial or time dimension, (ii) jointly caption multi-scene video clips from one source, and (iii) apply task-specific fine-tuning using carefully curated small datasets. Through a series of diverse controllable tasks, we demonstrate qualitatively that existing advanced text-to-video models can effectively perform in-context generation. Notably, it allows for the creation of consistent multi-scene videos exceeding 30 seconds in duration, without additional computational overhead. Importantly, this method requires no modifications to the original models, results in high-fidelity video outputs that better align with prompt specifications and maintain role consistency. Our framework presents a valuable tool for the research community and offers critical insights for advancing product-level controllable video generation systems. The data, code, and model weights are publicly available at: \url{https://github.com/feizc/Video-In-Context}.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections