模型： revAnimatedFp16_122+blindbox_v3:1 LCM_1.5:1.0 Steps: 20, Sampler: Euler a, CFG scale: 2,

头部先放大，适当压扁。 需要control控制姿势 分别生成身子和头，头需要 重绘幅度 大些 50%左右，要不眼睛效果出不来。 尽量保持身体特征 20%左右，要不就不是原来的人了。

参数参考： 1girl,smile,black hair and eyes,school_uniform,chibi,realistic,full body,lora:blindbox_v3:1,, HDR, HD,UHD, 64K ,Highly detailed,Studio lighting,Professional,Vivid Colors,Bokeh,high quality,masterpiece ,best quality,ultra highres, ,ultra-detailed,finely detail,highres,8k wallpaper,chineselora:LCM_1.5:1.0 Negative prompt: worst quality:2.0 Steps: 20, Sampler: Euler a, CFG scale: 2, Seed: 3163071480, Size: 973x1050, Model hash: 3e654848b5, Model: revAnimatedFp16_122, Denoising strength: 0.2, ENSD: 31337, ControlNet 0: “Module: openpose_full, Model: control_v11p_sd15_openpose [cab727d4], Weight: 1, Resize Mode: Crop and Resize, Low Vram: False, Processor Res: 512, Guidance Start: 0, Guidance End: 1, Pixel Perfect: False, Control Mode: Balanced, Save Detected Map: True”, Lora hashes: “blindbox_v3: f221dbfed0d8, LCM_1.5: aaebf6360f7d”, Version: v1.6.0-2-g4afaaf8a, similarity = {}, ref_similarity = {}