images = pipe(
prompt = "A ultra detailed portrait of a sailor moon girl smiling, color digital painting, highly detailed, digital painting, artstation, intricate, sharp focus, warm lighting, attractive, high quality, masterpiece, award-winning art, art by Yoshitaka Amano, and Brian Froud, trending on artstation, trending on deviantart, Anime Key Visual, anime coloring, (anime screencap:1.2),(Graphic Novel),(style of anime:1.3), trending on CGSociety",
negative_prompt = "cut off, bad, boring background, simple background, More_than_two_legs, more_than_two_arms, (3d render), (blender model), (((duplicate))), ((morbid)), ((mutilated)), [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, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), ((extra arms)), ((extra legs)), mutated hands, (fused fingers), (too many fingers), ((long neck)), lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist's name",
height = 1024,
width = 512,
num_inference_steps = 100,
guidance_scale = 8.5, # попробуйте поменять этот параметр самостоятельно
num_images_per_prompt = 1
).images
Спасибо за статью. Познавательно.
Аренда такого сервера 40к в месяц, правда. Для некоммерческого проекта "на поиграться" многовато. Хотя может кто-то знает, как это монетизировать...