This is a socks Z Image Base LoRA
It helps to create low cut socks. It can create socks in all colors and in different poses. The dataset was only black and white socks with used/dirty look.
Use natural language.
Example prompt: "a blonde woman is sitting with her socked feet up on the table, the focus is on the small black sporty socks, they are close to the camera and highly detailed".
I highly recommend using the Z-Image Fun Distill Lora: https://civarchive.com/models/2362961?modelVersionId=2677144
Works with Z image turbo as well but strength needs to be around 1.5.
Trained locally on RTX 4070 Super (12GB VRAM) with 32GB system RAM using 59 images.
Description
1st version to test the concept. I will probably train higher quality version, since the lora is working.
FAQ
Looks like we don't have an active mirror for this one right now.
This archive is kept alive by community contributions, so there are still some gaps, especially for newly removed content.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.