Large Scale GAN Training for High Fidelity Natural Image Synthesis · HackerPapers discussions

Large Scale GAN Training for High Fidelity Natural Image Synthesis — mentioned by gwern

Wed, 23 Aug 2023 16:17:00 GMT

If you're wondering how it's so fast and cheap and they can generate variants so easily, it's because they're using GANs (see the footer). GANs are way faster than diffusion models because they generate the image in a single forward pass and their true latent space encoding makes editing a breeze. (And if you're wondering how it can look so good when 'everyone knows GANs don't work because they're too unstable', a widespread myth, repeated by many DL researchers who ought to know better, GANs can scale to high-quality realistic images on billion-image scale datasets, and become more, not…

Paper and discussion history. A mention is not an endorsement.

Large Scale GAN Training for High Fidelity Natural Image Synthesis — HN submission

Tue, 02 Oct 2018 14:37:33 GMT

Learning Large Scale GAN Training for High Fidelity Natural Image Synthesis

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Large Scale GAN Training for High Fidelity Natural Image Synthesis — HN submission

Mon, 01 Oct 2018 01:39:53 GMT

Large Scale GAN Training for High Fidelity Natural Image Synthesis

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.