Rare find

Emu3.5. An AI model that understands pictures and text together to predict what comes next.

github.com/baaivision/Emu3.5

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

December 2025
  • support download from HF
  • support download from HF
November 2025
  • Update README.md
  • Update README.md
  • Update README.md for apps
  • Update README.md
  • Update README.md
  • Merge branch 'main' of https://github.com/baaivision/Emu3.5
  • [feat] Add recursive proto visualization with default results/ output
  • [vLLM] add vLLM offline inference (#47)
  • [feat] add gradio demo (#42)
  • Merge pull request #44 from zhaoyinglia/add_eval_branch
  • [vq] skip compute quant_loss when eval
  • Update README.md
  • Merge branch 'main' of https://github.com/baaivision/Emu3.5
  • [feat] Improve viz export and dynamic text rendering for proto outputs
  • [feat] support save cot text
  • modify print info
  • Feature/add custom t2i hw control (#38)
  • Merge pull request #18 from yangliu96/feature/add-custom-t2i-hw-control