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
I updated my workflow to make it easier to read and fixed some points.
FAQ
Comments (10)
Can you link all models u have used in workflow pls
All links to the right of Load Checkpoint
@Slavikson My bad, thx a lot. Btw I get sageattention error. Anyway to use it without installing sageattention?
@Arcoo3 just mute it or remove this node, it's only there to speed up generation
@Arcoo3 So what do you think? I need feedback to know how I can improve this.
@Slavikson I did not have enough time to test it. But did couple of generations, works well. But i wish it was neater and easier to move around. It is hard to understand what group of nodes are responsible for. I prefer when most of the things are visible and controllable on 110% zoom and without moving around. I will upload my Illustrious generation workflow to show what I mean.
@Slavikson Here is my workflow:
@Arcoo3 Did it get better?
@Slavikson how long does it take u to run a generation/upscale
@Arcoo3 1:20 generation. 11:02 together with upscale, I have an RTX 3050 8 GB