Comment Comment by nextaccountic Oh my god. This means that we can use stable diffusion to do pure text processing, like, given two textual descriptions, assess how similar they areI now expect that the next model like GPT-3 will be multi-modal like Stable Diffusion, to better account for those semantic connections parent nextaccountic 4 years ago
I now expect that the next model like GPT-3 will be multi-modal like Stable Diffusion, to better account for those semantic connections