top | item 29633042

GLIDE: Photorealistic Image Generation, Editing w/ Text-Guided Diffusion Models

26 points| minimaxir | 4 years ago |arxiv.org

6 comments

order
[+] BasilPH|4 years ago|reply
I don't understand how this didn't make the front-page, it's absolutely mind-blowing. Or am I missing something and it's not that much of a revolution?
[+] sbierwagen|4 years ago|reply
It's a bigger, better version of DALL-E from earlier this year: https://openai.com/blog/dall-e/

It's good, important work, but not so new that I'd expect to see hundreds of upvotes. Also, mobile users generally won't read PDF submissions.

[+] minimaxir|4 years ago|reply
Surprisingly OpenAI did not release a blog post with this paper: I suspect that will be the one that makes the front page.