And now… we can literally prompt edits. Like, “oh, I want to change this part” and boom, the model can just do it (most of the time lol). Sure, sometimes you still need to do some manual touch-ups, upscaling, or extra passes, but man, the fact we can even do this locally on our PCs is just surreal to me

Does attention/emphasis (prompt:1.5) work? I've been elbows deep in Automatic1111 since Spring and having a blast. But I'm always exploring better ways to do this. Ever since I saw that little ComfyUI avatar in the SDXL live chat last week, I had an interest in checking out the app, especially since it was so stable at launch but I must be doing something wrong?

Is there a smarter way or workflow to generate consistent multi-character images using all three of my LoRAs together – ideally without relying on face swapping afterward? Using flux now, but I´m open for other suggestions as well. I'm also uploading a reference image of the three of us, if that helps! Any tips or experiences would be really appreciated Thanks in advance!