What I load in ComfyUI, and which models do true instruction edits vs. needing img2img. Includes the encoders, VAEs and ControlNets you need.
-
black-forest-labs/FLUX.2-dev
Image-to-Image • 32B • Updated • 952k • • 2.04k -
black-forest-labs/FLUX.1-dev
Text-to-Image • 12B • Updated • 586k • • 14.2k -
Comfy-Org/flux1-dev
Updated • 384k • 654 -
black-forest-labs/FLUX.1-schnell
Text-to-Image • 12B • Updated • 365k • • 5.56k
