• Top
  • New

Janus-Pro: Autoregressive framework unifying multimodal understanding&generation

by victormustar on 1/27/2025, 4:25:27 PM with 4 comments
  • by Tiberium on 1/27/2025, 4:40:46 PM

    As for what it is: it is a multimodal LLM that can accept both text and images, and generate both text and images as output.

  • by minimaxir on 1/27/2025, 4:26:59 PM

    Note: this model was just released from DeepSeek. https://github.com/deepseek-ai/Janus

  • by ChrisArchitect on 1/27/2025, 6:13:12 PM

    Later discussion: https://news.ycombinator.com/item?id=42843131

  • by pieix on 1/27/2025, 4:49:29 PM

    Anybody used this yet and can share example outputs?