LoRA trained on images from InZOI's character creation screen.

InZOI Character Creator

Dataset: 121 images taken in-game with character creation screenshot toolModel INZOIV1A summary:- Base Model: Stable Diffusion v1-5- LoRA Type: Standard, LyCORIS preset (full)- Precision: fp16- Optimizer: Adafactor, huber loss with SNR schedule- Resolution: 768x768, bucketed between 256–2048- Training:- Epochs: 8, sampling every 4- 121 images in dataset- Batch Size: 3, gradient accumulation: 1- Learning Rate: 0.0001 (UNet and text encoder)- Adaptive Noise: Multires noise discount at 0.3; Original noise offset- Output:- Format: bf16 <code>safetensors</code>- Sampling: Euler-A, prompts "inzoi style, a man" and "inzoi style, a woman"

Files with SHA256: 7f42f8e338fed81ef70de4adcaa1ebc57681680fec93054901ade887b9fd93e6