Generated examples are with Realistic Vision V1.3 First ever trained LoRA. ***NSFW by nature, be deliberate with sfw prompts and hope for it to generate with clothes *** check Model Version description for training log

Kira Noir

InfoImages: 114Repeats: 20Dimm: 128Basev1.5-pruned.ckptClient Kohya_ss LOG: running training <ul><li> num train images * repeats / Number of learning images x number of iterations: 2280</li><li> num reg images / Number of regularized images: 0</li><li> num batches per epoch / Batch size per 1 epoch: 1140</li><li> num epochs / epoch: 1</li><li> batch size per device / Batch size: 2</li><li> total batch size (including parallel learning and gradient sum: 2</li><li> gradient accumulation steps / Number of steps to sum gradients = 1</li><li> total optimization steps / Number of learning steps: 1140</li></ul>

Files with SHA256: d335ae40c0509edba2a5726c2ea24f2ca5548fc74bc580dd2451f4f48c8be01b