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 • 407k • • 2.4k -
black-forest-labs/FLUX.1-dev
Text-to-Image • 12B • Updated • 650k • • 15.5k -
Comfy-Org/flux1-dev
Updated • 1.04M • 689 -
black-forest-labs/FLUX.1-schnell
Text-to-Image • 12B • Updated • 595k • • 6.23k
