JVT: Just Video Transformer makes pixel-space video diffusion simple
Zhou, Hua Geng, Haoyu Guo
JVT: Just Video Transformer makes pixel-space video diffusion simple: 14 upvotes on Hugging Face Daily Papers, #12 of 40 papers on 2026-11-16. Day-by-day upvote history.
Upvotes over time
It had 14 upvotes by its first day, 15 upvotes by the next day, 14 upvotes by day 3, 14 upvotes by day 7, and has 14 now. It ranked #38 of 146 papers in its week and #189 of 520 in its month. Its code repository has 41 GitHub stars.
Direct diffusion modeling of high-dimensional raw video data is challenging, and existing pixel-space methods often rely on specialized architectures. We introduce JVT (Just Video Transformer), a simple large-patch DiT-style Transformer for pixel-space video diffusion, without a pretrained autoencoder, auxiliary detailers, cascaded stages, or U-Net-style skip connections. We systematically examine video patch embeddings, register tokens, and adaptive layer normalization to identify design choices that balance generation quality and computational efficiency. The resulting JVT design achieves generation quality competitive with latent diffusion baselines in both class-conditioned and unconditional settings. The pixel-space formulation of JVT also naturally supports joint generation of pixel-aligned modalities. We demonstrate this capability through camera-conditioned RGB-disparity generation, which improves camera following relative to RGB-only baselines and yields explicit scene geometry without an additional reconstruction model at inference. These results highlight the potential of simple DiT-style Transformers for pixel-space video diffusion, and we hope our findings offer useful insights and practical guidance for future research.
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.