Yanke Song, Shuo Chen, Chris Rockwell, Ming-Hsuan Yang, Xun Huang et al. · Pixel-space video diffusion
PixVid: Back to Pixels, Lifting Latent Video Diffusion into Pixel Space
PixVid finetunes a pretrained latent video model, Wan2.1-14B, to generate every frame directly in pixels. It keeps the diffusion transformer, replaces the VAE with a linear patch embedding and a causal convolutional detailer head, and finds that predicting clean video with a much larger noise shift is critical to quality. The authors report quality competitive with the original latent model within 20K iterations. Working frame by frame, it generates 1664 × 960 video with the same 30 × 52 tokens per frame as the 832 × 480 model, keeps depth-conditioned editing aligned under fast motion, and applies each action on the next frame rather than waiting for a 4-frame block (up to 133 ms of delay at 30 FPS). The page does not state licence or code availability.
Open the source ↗Similar Video & Animation releases
- Open-H3-Regenerate-2K
NVlabs (SANA / SoL-Engine team) · Open video refiner · Week 47, 2026
- pi-H3
Hansheng Chen, Shengqu Cai, Jiaming Song, Gordon Wetzstein, Xinchen Yan and Leonidas Guibas · Decoder-free few-step video · Week 47, 2026
- MPEG-Diffusion: Mixed-Resolution Video Generation
Dennis Menn, Tianpei Gu, Guande He, Aryan V S, Yanke Song, Nan Liu, Desai Xie, Xun Huang, Chenfeng Xu and Diana Marculescu · Mixed-resolution video diffusion · Week 47, 2026
- Reshoot 4D
itsmetamike · 4D video reshooting · Week 47, 2026
- Seedance 2.5 Camera Control (pill pipeline)
Sirio Berati · Code-driven AI camera control · Week 47, 2026
- Few-Step Streaming Video Generation via Condition Shifting
Tsinghua University (Deyuan Liu, Jungang Li, Kaiwen Zheng, Kai Jiang, Jintao Chen, Yaole Wang, Ming Lin, Tao Lin) · Streaming Video Distillation · Week 47, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.