THIS MODEL IS FOR TESTING PURPOSES AND IS NOT FIT FOR USE YET
Whilst you're open to use it whilst it's publicly available, the results won't be ideal -- since I can't generate images on hardware at this time, I have to resort to Civitai's on-site generator. Apologies for this and thank you for your patience!
Version 0.5:
For now, 2DN checkpoint stabilises the model into some coherency. Whilst it's doing a great job, flexibility is an issue and Pony Diffusion V6 can be a good barometer on the Lora quality. I'm currently sweeping through learning rates before fine-tuning the prompts and the dataset.
Description
UNET LR: 2e-4
Recoloured eyes to yellow in some of the dataset images to see if it helps training understanding where eyes are in full-body shots.
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
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.