Just a quick low effort model trained on PonyDiffusion to make bellies saggier. Images were extracted from the hyperfusion dataset, so uses similar tags to that. but the only important tags are "bellysag" and the typical belly related tags.

bellysag-SDXL

Trained on PonyDiffusion-SDXL_v6 with ~200 images.Training Config (kohya):<ul><li>lr 2e-4</li><li>frozen text encoder</li><li>batch 2</li><li>GA 4</li><li>lr scheduler cosine</li><li>dim 16</li><li>alpha 8</li><li>conv_dim 8</li><li>conv_alpha 4</li><li>tag dropout 15%</li><li>network dropout 30%</li><li>res 1024 bucket max 1024</li><li>shuffle captions</li><li>flip</li><li>ip_noise_gamma 0.02</li><li>min_snr_gamma 4</li></ul>

Files with SHA256: 943a6fda32c4152d266125c7556237c976a807eea01162c3a3a5e06d7b740a12