Live data from Hacker News

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

1–3 of 3 posts

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

Post by decodingchris » Sat, Nov 30, 2024, 2:43 PM UTC

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.

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

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

Post by ThatGuySam » Sat, Nov 30, 2024, 5:14 PM UTC

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.

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

Post by Shynobi » Sat, Nov 30, 2024, 5:50 PM UTC

ThatGuySam wrote: post #2

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.

Definitely see that happening

Post reply on HN