類型
TextualInversion
发布時間
2024-04-16
基础模型
SD 1.5
触发词
HVL
復制
版本介绍
Sampling method: DPM++ 2S a Karras - Set at: 50
CFG Scale: set at 4
ADetailer: mediapipe_face_full
Clip Skip: 1
Trained 30 images with:
Batch Size: 1 Gradient accumulation steps: 1
Embedding Learning Rate at:
0.004:1000, 0.001:2000, 0.0001:3000, 0.0005:3500
