Verified: 10 months ago
SafeTensor
Type | |
Stats | 650 2,715 |
Reviews | (64) |
Published | Jan 10, 2024 |
Base Model | |
Training | Steps: 32,000 Epochs: 12 |
Usage Tips | Clip Skip: 2 Strength: 0.8 |
Hash | AutoV2 EE13AA825A |
阿戈魔AGM Style LoRA V4
中文 | English
--
--
自备人物模型。主要针对技法进行训练。四肢有问题时降低模型权重。
Bring your own character model. Mainly for the training of painting techniques. Lower model weights when limbs are problematic.
--
仿阿戈魔AGM的作画风格的LoRA模型。
权重建议值:1 (or 0.5~1.2)
The LoRA model mimics AGM's painting style.
Recommended weight value: 1 (or 0.5~1.2)
--
训练相关/About training:
训练集共计8张图。双向差异法+多模型蒸馏。
This version of the model uses bidirectional difference method + multi-model distillation. The training set consists of a total of 8 images.
loss rate < 0.3%
--
任何问题,欢迎反馈,问题不提出就不会得到解决。
Any questions are welcome for feedback, as problems will not be solved without being raised.