中文 | English
--
仿望月けい的作画风格的LoRA模型。
权重建议值:0.8 (or 0.5~1.2)
基于模型:Anything-5RE
训练信息:筛选出共计454张原画(含裁剪图),迭代908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 Mochikei.
Recommended weight value: 0.8 (or 0.5-1.2)
Based on model: Anything-5RE
Training information: A total of 454 original images (including cropped images) were selected for 908 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.