What does HackerNews think of clip-retrieval?
Easily compute clip embeddings and build a clip retrieval system with them
Language:
Jupyter Notebook
#23
in
Deep learning
relevant:
https://rom1504.github.io/clip-retrieval/
https://github.com/rom1504/clip-retrieval
Ironically, the stableattribution.com authors didn't give any attribution or credit to clip-retrieval and its developer
This is a company that allows you to search for images from a training dataset that have a high cosine similarity with a given image. It appears to be the same as the open source software published by LAION.
https://github.com/rom1504/clip-retrieval
It does not appear to actually show you how images were used to train a generative AI.
Below is an OSS alternative, originating from same engineering as stable diffusion. There is other awesome work in rom1504's Github I recommend exploring as well.
https://rom1504.github.io/clip-retrieval/ (usually performant)
This gh repo makes it pretty easy to create similar tech by first embedding any images you have using the released "CLIP" model from Open AI and then creating a Faiss index over these embeds for quick retrieval/decode. You can then do text->image, and image->image semantic search.
Assuming you have an NVIDIA GPU, you can build a semantic image search engine by indexing CLIP embeds (image or text).