Verified: a year ago
SafeTensor
Type | |
Stats | 1,484 223 |
Reviews | (235) |
Published | Sep 16, 2023 |
Base Model | |
Training | Steps: 12,415 Epochs: 15 |
Usage Tips | Clip Skip: 2 |
Hash | AutoV2 C936DFB573 |
The V2.0 model used more than 700 high-quality original pictures for training.
This model has a good effect of restoring the artist's style.
The training pictures are all from the original painting collection of the artist, and the TV version animation picture materials are not mixed in, so as to obtain the pure artist style LORA
Recommendation Weight:0.6~1.0,
Recommendation VAE:animevae.pt
Recommendation Model:scmix_NSM.ckpt
--- --- --- --- --- --- --- ---
V2.0版本模型使用了超过700张高质量的原始图片进行训练。
这个模型拥有很好的画风模仿效果。
训练图片全部来自该画师的原画集,TV版 刀剑神域 图片素材没有混入其中,得到纯净的abec(BUNBUN)风格LORA。
推荐权重:0.6~1.0
推荐vae:animevae.pt
推荐模型:scmix_NSM.ckpt