对天涯明月刀OL游戏内人物外观进行LORA模型训练后的成果,通过LoRA分层移除了对脸部的训练,使其脸部的生成更贴近大模型的效果,减少了崩脸的概率,但依旧推荐你采用面部修复,预览图所用大模型为Guofeng3_v34
对模型测试以及炼丹感兴趣的,欢迎来Q群850498709(一个人又训练又测试还要跑图,太疲乏了而且容易忽略问题)
如果你喜欢本模型,也欢迎你来赞助我,这将是我更新模型的最大动力,赞助链接:https://fpoh.usells.com/p/d9Uu7h
以下是展示预览图的生成信息(C站自动识别不了,一个一个填又太麻烦)
提示词
(best quality),((masterpiece)),<lora:[衣服]-[明玉-天刀少女]TDSVmy:0.7>,1girl,solo,loli,round face,kind_smile,flat chest,(standing:1.2),(full body:1.5),(beach:1.2),sea,on the beach,(looking_at_viewer:1.4), 🔄 ❓
负面提示词
(worst quality:2),(low quality:2),(normal quality:2),
(unclear eyes:1.331),bad hands,missing fingers,bad body,(more than 2 nipples:1.331),(extra legs:1.331),(unclear eyes:1.331),
其他参数
Steps: 25, Sampler: DPM++ 2M Karras, CFG scale: 11, Seed: 3444427363, Size: 768x1024, Model: [3D]-[国风]3Guofeng3_v34, VAE: 840K-EMA_VAE.safetensors, Denoising strength: 0.5, Clip skip: 2, RNG: CPU, ADetailer model: mediapipe_face_full, ADetailer confidence: 0.3, ADetailer dilate/erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer version: 23.9.1, Hires upscale: 1.5, Hires steps: 15, Hires upscaler: 4x-UltraSharp, Lora hashes: "TDSVmy_20230905084337-000007: 7ee3334b3d8b", Dynamic thresholding enabled: True, Mimic scale: 7, Separate Feature Channels: True, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 1, Threshold percentile: 100, SGM noise multiplier: True, Version: v1.6.0 🔄 ❓