中文 | English
仿LM7的作画风格的LoRA模型,认识的话应该一眼能认出来这个画风。
权重建议值:1 (or 0.5~1.4)
基于模型:Anything-5RE
训练信息:筛选出共计196张原画(含裁剪图),迭代1176步,多分辨率智能定向训练。
其他的一些建议:EasyNegative。此外,万一畸形四肢换个种子重画就行。
The LoRA model imitates the painting style of LM7, and if you're familiar with this artist, you should be able to recognize it at a glance.
Recommended weight value: 1 (or 0.5-1.4)
Based on model: Anything-5RE
Training information: A total of 196 original images (including cropped images) were selected for 1176 iterations of multi-resolution intelligent targeted training.
Other suggestions: Use EasyNegative. Additionally, if there are any abnormal limbs, try redrawing them with a different seed.