中文 | English
--
Recommended:
2D:
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 11.5, Size: 672x1056, Model hash: 1065c5d2e0, Model: CreationMixV1, Denoising strength: 0.45, Clip skip: 2, Hires upscale: 1.6, Hires steps: 15, Hires upscaler: Lanczos
More details:
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 9.5, Size: 672x1056, Model hash: 1065c5d2e0, Model: CreationMixV1, Denoising strength: 0.62, Clip skip: 2, Hires upscale: 1.6, Hires steps: 15, Hires upscaler: Latent
--
仿ごとp的作画风格的LoRA模型。
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224张原画(含裁剪图),迭代1120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 ごとp.
Recommended weight value: 1 (or 0.5-1.4)
Based on model: Anything-5RE
Training information: A total of 224 original images (including cropped images) were selected for 1120 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.