Please use on <a target="_blank" rel="ugc" href="https://github.com/AUTOMATIC1111/stable-diffusion-webui">https://github.com/AUTOMATIC1111/stable-diffusion-webui</a>Base Model<ul><li>Chilloutmix/chilloutmix_NiPrunedFp16Fix.safetensors [59ffe2243a]</li><li>512 * 768</li></ul>Tested On<ul><li>Chilloutmix/Chilloutmix.safetensors [a757fe8b3d]</li></ul>AdamW optimizer, trained on RTX4090, my inital try to use LoRA.Using Latex experments images. (Oh! I love there shoots!)Still going to updating!TODO:<ol><li>Add pic from refect desire (tested, interfer with current trained pic, will open another repo)</li><li>More pic</li><li>style focused</li></ol>Additional picture source is welcomed.

Latex (胶衣)

1000 images, mainly alex and juliThe output is better, watermark need to solveLet us make it a try!I reviewed the training process, it is likely overfitting. Concidering how similar the face to alex.

Files with SHA256: 7d9d0699afb00ea786cbfac3d345963c53ddeea94272266f0b2bb8f28f7b53dc