Specially for portraits and closeup portraits. Selected eyes look at camera. HD and sharp images selected to dataset. Used 100-150 photos.
Trained on Comfyui FluxTrainer on 16gb Vram
Better use resolution 768 (minimize face-body proportion distortions) and than upscale whatever you want.
Small size of LORA because of training only 2 blocks: 7 and 20.
Top line of the GRID is this checkpoint. Grids for lora strength 0.8 and 1.2
描述:
several version steps compared, this
lora=1.2 looks ok.
训练词语:
名称: mckenna_768_rank128_bf16-step03500.safetensors
大小 (KB): 9222
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
