ComfyUI v0.29.0

v0.29.0
Added 11
  • Send ComfyUI Job Id in request headers for partner nodes
  • Add JoyImageEdit native model support
  • Add GPT5.6 models for OpenAI partner nodes
  • Add Gemini 3.5 Flash LLM model for Google partner nodes
  • Add HeyGen Avatar, Talking Photo, Create Avatar, Video Translate and TTS nodes
  • Support anima lllite control models
Changed 1
  • Bump default background usage clamp to 128GB
Fixed 6
  • Stream video transcode instead of buffering every frame in RAM
  • Fix gfx1035 not being treated like RDNA2
  • Fix Wan dancer issue with batches
  • Fix MageFlow on cards that don't support bf16
  • Switch Google Omni model to the Interactions API
  • Pass videos as inline data for Gemini-Omni
Deprecated 1
  • Deprecate Runway Gen3a model
What's Changed
New Contributors

Full Changelog: https://github.com/Comfy-Org/ComfyUI/compare/v0.28.0...v0.29.0

View original

Upgraded? How did it go?

Discussion