>>3025302Well it's already usable, it's just not enough on its own. Makes it so much easier to set up complex scenes and poses. And then you have to do another pass over the image with illu/noob, to add character details and change style.
Say you're doing race queens, it gets the scale and pose right and knows individual car brands, even specific models. Or you're doing something more complex
>>>/h/8774392 it knows left/right/up/down and can count.
