AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Is Stable Diffusion a New Type of Programming Primitive?
A lot of your efforts thus far have been on shrinking the model. Do you see a pull towards larger models or do you think it's a different paradigm altogether where there's not going to be that kind of drive to make the model bigger and bigger? I think it'll be a mixture of things again, like what we saw with the deep mind chachella paper was that the scaling laws weren't necessarily appropriate. But this is also like you can think of these models like stable diffusion one was a precocious kindergarten.