Unofficial ComfyUI implementation of Diffusion Self-Guidance for Controllable Image Generation
Clone this repo into custom_nodes folder or use Manager.
use example1.jpg
an onion and a carrot
- set
carrot
as target object, setonion
as fix object - shrink, scale factor = 0.8
- enlarge, scale factor = 1.3
use example2.jpg
a photo of an eclair and a shot of coffee
- set
eclair
as target object, setcoffee
as fix object - shrink, scale factor = 0.8
- enlarge, scale factor = 1.3
Currently only SD series models are supported.