v1.0 better
RealCosplay (noobReal) 是一种多风格模型,不仅限于现实主义。
I don't want to destroy the anime concept of illust or noob,like other Lora or Merge model. So i finetune this model in anime style by default.I'm aimming to use high-quality real photo data to achieve realistic style, and improve anime concept's anatomical\scene composition, through its realistic concept.
下一步:
我在 2025 年 5 月购买了 4090 48G 版本,在接下来的 realcosplay 版本中我会尝试更多的训练方法和更高分辨率的训练。
推荐设置:
现实的积极提示
写真 / 写实 ,cosplay,
负提示 realistic
插画,动漫,素描,漫画,卡通,卡通,油画\(中等\),平面颜色,轮廓,3D,2.5D,2D,虚幻,统一,搅拌机,动漫,光滑的皮肤,半人类,厚涂,
建议参数
每分钟移动分辨率++ 2M
CFG : 2.5~4
postive prompts for realistic
photograph / realistic ,cosplay,
negative prompts for realistic
illustration,anime,sketch,comic,cartoon,toon,oil painting \(medium\),flat color,outline,3D,2.5D,2D,unreal,unity,blender,anime,smooth skin,semi-anthro,impasto,
Suggest parameters
DPM++ 2M
cfg : 2.5~4
v1.0 better
RealCosplay (noobReal) 是一种多风格模型,不仅限于现实主义。
I don't want to destroy the anime concept of illust or noob,like other Lora or Merge model. So i finetune this model in anime style by default.I'm aimming to use high-quality real photo data to achieve realistic style, and improve anime concept's anatomical\scene composition, through its realistic concept.
下一步:
我在 2025 年 5 月购买了 4090 48G 版本,在接下来的 realcosplay 版本中我会尝试更多的训练方法和更高分辨率的训练。
推荐设置:
现实的积极提示
写真 / 写实 ,cosplay,
负提示 realistic
插画,动漫,素描,漫画,卡通,卡通,油画\(中等\),平面颜色,轮廓,3D,2.5D,2D,虚幻,统一,搅拌机,动漫,光滑的皮肤,半人类,厚涂,
建议参数
每分钟移动分辨率++ 2M
CFG : 2.5~4
postive prompts for realistic
photograph / realistic ,cosplay,
negative prompts for realistic
illustration,anime,sketch,comic,cartoon,toon,oil painting \(medium\),flat color,outline,3D,2.5D,2D,unreal,unity,blender,anime,smooth skin,semi-anthro,impasto,
Suggest parameters
DPM++ 2M
cfg : 2.5~4