This is a test workflow that allows you to use the IL\Noob model as Flux.Kontext\Qwen_Edit to generate a character image from a Reference. It works best with the same model as Reference. You also need to add a character prompt.
Attention! The result depends greatly on the seed, so experiment.
I really need feedback and advice on how to improve this! So if anyone is interested, please share your thoughts on this.
Description
FAQ
Comments (6)
Can this be reworked to use realistic images in sdxl and realistic sdxl fine tunes? I tried redoing it with chatgpt but couldnt figure it out lol.
In theory it should work with any IL based model. But you need to test it.
I tested it with a model - Willy's Noob Realism
@Slavikson Like I am asking is there a way to convert the workflow to work with sdxl base or sdxl fine tunes, not noobai. From what I asked chatgpt the whole controlnet node scheme seemes like it needed to be changed to work with sdxl and I couldnt quite figure it out, as the nodes werent easily swapable. There was like a noobai depth node that I couldnt figure out how to swap out.
@anonameguyman1234252 The problem is that I have no idea how exactly ControlNet works in this case, I did it by accident, so it's better to test what the result will be with SDXL. So just choose the SDXL model and give it a try.
@Slavikson ah. Yea tried it with sdxl checkpoints and doesn't work.
@anonameguyman1234252 Thanks for the feedback. I've changed the title until I find an equivalent for SDXL.