Updated: Oct 6, 2024
tool
A version of the AIT workflow, but this one does img+img, instead of text2img.
[REQUIRED NODES/MODELS]:
-https://github.com/FizzleDorf/AIT
-https://github.com/BlenderNeko/ComfyUI_ADV_CLIP_emb
-THIS IS CRUCIAL: https://huggingface.co/comfyanonymous/clip_vision_g/tree/main
use:
FOR BATCH SIZE 4, YOU MUST HAVE WINDOWS FOR NOW, LINUX WILL BE COMPATIBLE WITH BS4 SOON; IF YOU DON'T WANT BS4, you can change the batch size to 1.
you can weight imageA and imageB according to output; recommended is to start from 1:1, then adjust accordingly if output image is more like imageA than B or the other way around.
speed should be as fast as the normal version of this workflow due to AIT.