AI制图全面进化:: Midjourney更新Image2text功能 – 输入/describe命…

CLIP-Interrogator: huggingface.co/spaces/fffiloni/CLIP-Interrogator-2

命令1：卡通模特

new animation character girl in white turtleneck, in the style of hyper-realistic oil, cartoonish innocence, soft color blending, realistic lighting, gongbi, commission for, thick texture –ar 58:77 –v 5

命令2：美少女战士

sailor moon art girl on the moon, in the style of cyberpunk futurism, light violet and gold, lilia alvarado, shang dynasty, andrzej sykut, bold, vibrant colors, close up, vray –ar 2:3 –niji 5 –v 5 –q 2 –v 5

命令3: 动漫人物
parameters
(extremely delicate and beautiful:1.2),1girl, sexy dress,bangs, red eyes, blurry, blurry background, bow, long black hair, closed mouth, from side, hair between eyes, hair bow, lantern, light particles, long sleeves, looking at viewer, medium hair, night, red bow, solo, star (symbol), upper body,smile,red lips
Negative prompt: (worst quality, low quality, loli, child, infant, baby:1.4), lowres, blurry, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, (signature, watermark, username,letter, letterboxed, copyright name, copyright, chinese text, artist name, name tag, company name, name tag, text, error:1.5)
Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 8, Seed: 3020542659, Size: 512×768, Model hash: 3e9211917c, Model: YesMix_yesmix_v16Original, Denoising strength: 0.6, Clip skip: 2, ENSD: 31337, Hires upscale: 1.7, Hires steps: 25, Hires upscaler: Latent

#midjourney #图生文 #stablediffusion #prompt提取 #Image2text #人工智能 #AI绘图 #Prompt生成 #提示词