<h3 id="model-training-summary:-p6zuya4zs">Model Training Summary:</h3><ul><li>Dataset: Focused on images of trimmed pubic areas on females. (NOT EXPLICIT - HARDCORE) standing mostly</li><li>Captioning: Generated using Koyha_SS with GIT captioning.</li><li>Training Platform: Conducted on Civit’s onsite trainer, targeting 2,475 steps.</li></ul><h3 id="training-configuration:-h85llelzv">Training Configuration:</h3><ul><li>Engine: Kohya</li><li>Learning Rates:<ul><li>UNet LR: 0.0005</li><li>Text Encoder LR: 0</li></ul></li><li>Clip Skip: 1</li><li>LoRA Configuration:<ul><li>Type: LoRA</li><li>Network Dimensions: 2</li><li>Alpha: 16</li></ul></li><li>Training Details:<ul><li>Repeats: 30</li><li>Resolution: 1024</li><li>Batch Size: 4</li><li>Max Epochs: 6</li><li>LR Scheduler: Cosine with Restarts (3 cycles)</li><li>Min SNR Gamma: 5</li><li>Noise Offset: 0.1</li><li>Bucket Enabled: True</li><li>Optimizer: AdamW8Bit</li></ul></li><li>Augmentation: No flip augmentation; captions were not shuffled.</li></ul><h3 id="notes:-4pczjguuv">Notes:</h3><ul><li>Model is designed to handle images of trimmed pubic areas on females.</li><li>Training emphasizes a high number of steps and epochs to ensure model accuracy and refinement.</li></ul>

Files with SHA256: e5b631ee2e0b74ea28f903ad45ecb9d68747321d44b422066d2bada0029bb980