Verified: 2 years ago
SafeTensor
Type | |
Stats | 573 6,846 |
Reviews | (52) |
Published | Jul 6, 2023 |
Base Model | |
Training | Steps: 6 Epochs: 6 |
Usage Tips | Clip Skip: 1 |
Hash | AutoV2 EC354B33AD |
A small project to try training on only realistic AI generated pictures of asian girls with consistent face.
Trained on SDv1-5-pruned with 24 pictures (so you can use it with any realistic checkpoint).
I recommend using clip skip = 1. (2 works too)
No prompt activator.
But you can use this prompts to increase lora's strength : 1girl, adelinemu, brown hair, long hair, solo, looking at viewer, realistic
Reviews are really appreciated, i love to see the community use my work, that's why I share it.
If you like my work, you can tip me here.
Got a specific request ? I'm open for commission on my kofi or fiverr gig *! If you provide enough data, OCs are accepted
*Any paid request will not be presented on this page, unless you give me permission to.