Hacker News Reader

You can use the code in https://github.com/krea-ai/prompt-search to do so. You first want to compute the CLIP embeddings of each prompt, index them using something like K-Nearest Neighbors (so you can get search for similarities fast), and then, given an input prompt, you will be able to find other indexed prompts that share their semantics.

View on HN

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 are

I now expect that the next model like GPT-3 will be multi-modal like Stable Diffusion, to better account for those semantic connections

This is a very interesting point. It's like using Fourier Transforms/Laplace Transforms to do operations or comparisons that are way easier in those spaces.

Reply on news.ycombinator.com