Show HN: LatComp – Compress your image into a small and reversible format

huggingface.co

4 points · decodingchris · 7 days ago

While taking the fast.ai course, I was learning about Variational Autoencoders (VAE) and began to wonder:

Is it possible to represent the latent space as an image, and then reconstruct the original image from that representation?

Well, here's the answer.

2 comments
ThatGuySam · 7 days ago
I feel like it’s only a matter of time before we get AI-enabled image formats to supersede AVIF and WEBP.

Hopefully we can get some meaningful wins on mobile web performance.

Show replies