ZH version is available. Content is displayed in original English for accuracy.
The model has 3B active parameters. We put the code, homepage, paper and model links here:
- Code: https://github.com/bytedance/Lance
- Homepage: https://lance-project.github.io/
- Paper: https://arxiv.org/abs/2605.18678
- Model: https://huggingface.co/bytedance-research/Lance
p.s. Lance is a research project, not a polished product. The model was trained using fewer than 128 GPUs.

Discussion (13 Comments)Read Original on HackerNews
Why do that? Seems strange to be building sub-hd resolution video models in 2026.
Fabulous.
This is not ground-breaking by any means, but achieving this in a 3B model and sharing the approach + weights advances engineering and certainly more contribution that 'silly little slop videos' imo.