It would be better to use a 2.5D model, e.g.: revAnimated_v11.safetensors

Keywords: jinkesi_quan,jinkesi_lian,high quality,1girl,solo
Model size dim: "128"

Model alphanetwork_alpha: "64.0"

Parameters

High quality,jinkesi_quan,jinkesi_lian,1girl,simple background, (side bangs), blue hair, tattoos, (pink eyes), (double twists), (long twists) (raised eyebrow) looking at viewer
(black ruffled tie), white collared shirt, black blazer, school uniform
Pendant, Necklace, Jewelry, Portrait, Shiny, (Original)
Original, (Masterpiece), (Illustration), (Extremely Fine and Beautiful), Perfect Detail, Realistic, (Nice Clear Background: 1.25), (Depth of Field: 0.7), (Beautiful Face), Casual, .
Negative cues: easynegative, bad-hands-5, ng_deepnegative_v1_75t, bad-picture-chill-75v, bad-image-v2-39000, verybadimagenegative_v1, painting, drawing, text, cropping. jpeg artifact, ((monochrome)), ((grayscale)), (worst quality, low quality, normal quality, blur: 1. 4), (ugly, sickly, mutated, disfigured: 1. 3), (more than 1 person: 1. 4), out of frame, long neck, age spot, skin blemishes, mole, acnes. cross-eyed, unbalanced eyes, different eye color, extra fingers, mutated hands, bad anatomy, long nails, bad proportions, extra limbs, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, twisted legs, fused legs, long neck, username, watermark, poor facial details, bad composition, de poor facial details, bad composition, deformed body features.
Steps: 30, Sampler: DPM++ 2S a Karras, CFG scale: 7, Seed: 2762493402, Size: 512x768, Model hash: d725be5d18, Model: revAnimated_v11, Clip skip: 2, ENSD: 31337

Translated with DeepL