混了一堆自己觉得可以的模型，取其精华去其糟粕，得到一个不论是身材、样貌、光影、色彩等等都相对来说比较好的模型，分享给大家吧。

Steps: 20~24

Sampler: DPM++ SDE Karras

CFG scale: 6~7

模型自带了VAE

分享一下自己常用的正反向prompts：

Prompt:

(8k, RAW photo, best quality, masterpiece:1.2), (photorealistic, realistic:1.4),

(200mm Sigma f/1.2 ZEISS lens, F1.2, 1/200s, ISO 100, photograpy:1.4), (professional lighting, cinematic lighting, soft lighting, Bright:1.2),

delicate, ultra-detailed, beautiful, extremely detailed eyes and face,

Negative prompt:

CG, 3D, paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, manboobs, backlight, glasses, panty, anime, cartoon, drawing, illustration, boring, out of frame, extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, glitchy, bokeh, (((long neck))), red eyes, extra heads, text, watermarks, logo, EasyNegative,