Show HN: Lance – image/video generation and understanding in one model

Category: ai-ml

Tags: multimodal, image-generation, video-generation, video-understanding, image-editing

Score: 7.3/10 (Innovation: 7, Technical: 8, Documentation: 7, Utility: 7)

Lance is a 3B-parameter unified multimodal model from ByteDance that handles image/video understanding, generation, and editing within a single framework, trained from scratch with a staged multi-task recipe. Its innovative combination of diverse multimodal capabilities at a relatively small scale is interesting for efficient AI research.

Target audience: ai researchers, machine learning engineers

Repository: https://github.com/bytedance/Lance · Python · Apache-2.0 · 441 stars

View on Hacker News