(资料图片仅供参考)
唯一没开源的基于SD模型的二次元AI模型NovelAIDiffusion“被动”开源了。试了下,再webUI本地化部署已经能够和它网站的效果一样了。以下全是txt2img,没有垫图
就这样吧,以下机能少女的词换个三连过分吗?
full body three sides view concept art of sci-fi girl,grey blue hair,working in labroom,yellow cyber lasr hooded jacket.detailed cute eyes.head equipment,nylon belts.cyborg mask, hi-tech sneaker.rim light,soft lighting.looking at viewer.mole, cyberpunk print skirt.solo twintails.realism light effect.credentials.8k
Negative prompt: mutated, two persons, bad quality, 2 girls, 2 faces, 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 ,disfigured
最后,还是想说。AI必将进入美术的工作流程,早琢磨,不心慌。共勉。