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.
FAQ
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.