ByteDance · Video Editing
Bernini-Diffusers-v2
Splits generation in two: Qwen2.5-VL-7B plans the semantic change from the instruction, then Wan2.2-T2V-A14B renders it - roughly 21B across the pair. Covers text-to-image, image-to-image, text-to-video, video-to-video and reference-guided variants. Scores 8.02 on EditVerse, 63.83 on OpenS2V and 84.46 on VBench. Apache-2.0, weights out.
Open the source ↗Similar Video & Animation releases
- SenseNova 6.8 Code2Video
OpenSenseNova (SenseNova) · Code-driven video model · Week 45, 2026
- Open-H3-Regenerate-2K
NVlabs (SoL-Engine research blog, SANA project page) · Open video refiner · Week 45, 2026
- MatAnyone-E
Shuyun Wang, Shangchen Zhou, Peiqing Yang, Yuekun Dai, Xin Yu and Chen Change Loy · Efficient 4K matting · Week 45, 2026
- OpenFilm
openfilm · Coding-agent video · Week 45, 2026
- showhow
Sirio Berati (tein) · Coded explainer reels · Week 45, 2026
- AI Video Production Editor
LudwigKienle · AI film studio · Week 45, 2026
More from ByteDance
- Seedream 5.0 Pro
ByteDance · Text-to-Image · Week 29, 2026
- ByteDance Seed 2.1
ByteDance · Code Generation · Week 26, 2026
- Seedance 2.x
ByteDance · Text-to-Video · Week 26, 2026
- Bernini-R
ByteDance · Text-to-Video · Week 24, 2026
- Bernini
ByteDance · Text-to-Video · Week 23, 2026
- Seed Dance 2.0
ByteDance · Text-to-Video · Week 20, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.