I wanted to give LoRA training feature a go, and I felt like I was missing "LowRA" from 1.5 so I used some stock photos that I thought would give a similar effect. I wasn't picky with my selection, and basically just took the first things I saw. There's a bias for cities, women and asian lettering.
This could probably be accomplished without LoRA at all, but I know it works and I just wanted to try recapping some buzz so I could play around with the feature some more.
Example images generated using datassRev3 in comfyui and a1111
DPM++ 2M Karras
20 steps, cfg 6
adetailer (face fix)
Upscaler: 4x_NMKD-Siax_200k
CNet Canny was used 0.01% for base image/noise because I didn't bother changing workflow.
Workflow on ComfyUI is a schizophrenic mess, im noob
Description
FAQ
Comments (4)
omg, i needed something like this. thank you!
Have you tried it? Would love to see what other people get out of it
@pogo Im currently working on very lora-heavy customized ponyrealism set, and it seems to overcook for me. It's also very hard to just work with my setup right now, but it does bring in an interesting color to it, just not currently workable for this setup i have.
very good