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 β’ 32B β’ Updated β’ 891k β’ β’ 2.05k -
black-forest-labs/FLUX.1-dev
Text-to-Image β’ 12B β’ Updated β’ 595k β’ β’ 14.2k -
Comfy-Org/flux1-dev
Updated β’ 373k β’ 654 -
black-forest-labs/FLUX.1-schnell
Text-to-Image β’ 12B β’ Updated β’ 375k β’ β’ 5.57k