或许我们可以换个角度来看这个问题,或许不久的将来,“人机对话”会成为一门全新的学科:
比如英语老师上课时拿出来一幅画,说这次的project就是让AI画一幅画,得分高低只和AI画与原画的相似度高低有关。
PS:浅浅的了解了一下,感觉AI作画其实考验的是英语(逻辑)水平。
比如我想要AI画出下面这幅画:
我给出的文字描述如下:
正向描述(希望图片中包含的元素):a cyborg, photorealistic, hdr, detailed, fibers, perky breasts, cameltoe, pussy, articulated joints, sci-fi base background, artstation, fashion pose, (craig mullins:1.3), cinematic lighting, chromatic aberration, beauty
反向描述(不希望图片中包含的元素):(((simple background))),monochrome ,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, lowres, bad anatomy, bad hands, text, error, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, ugly,pregnant,vore,duplicate,morbid,mut ilated,tran nsexual, hermaphrodite,long neck,mutated hands,poorly drawn hands,poorly drawn face,mutation,deformed,blurry,bad anatomy,bad proportions,malformed limbs,extra limbs,cloned face,disfigured,gross proportions, (((missing arms))),(((missing legs))), (((extra arms))),(((extra legs))),pubic hair, plump,bad legs,error legs,username,blurry,bad feet
上例中的project,其实就是相当于让你反推描述文字是什么。(同样的文字并不保证生成相同的图案,但是整体风格会相似,如下二图是用相同的描述生成的)
|