After studying this model for a while, I have learned some experiences to create better images:

1/ always add the keyword (80s anime style) at the beginning of the prompt. added gta style, the trigger keyword is (gtav style) note only one keyword can be added in the prompt, gta no anime, anime no gta

2/ use this negative prompt “illustration, painting, cartoons, sketch, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, ((monochrome)), ((grayscale)), collapsed eyeshadow, multiple eyeblows, vaginas in breasts, (cropped), oversaturated, extra limb, missing limbs, deformed hands, long neck, long body, imperfect, (bad hands), signature, watermark, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error”

3/ CFG Scale to range from 12.5 to 15

Example:

(80s anime style), pastel sailor moon magical girl anime screenshot, anime, intricate, sharp focus, illustration, highly detailed, digital painting, clean artstyle, concept art, matte, art by ilya kuvshinov and ruan jia and greg rutkowski, masterpiece

Negative prompt: illustration, painting, cartoons, sketch, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, ((monochrome)), ((grayscale)), collapsed eyeshadow, multiple eyeblows, vaginas in breasts, (cropped), oversaturated, extra limb, missing limbs, deformed hands, long neck, long body, imperfect, (bad hands), signature, watermark, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error