News for hackers. Stuff that matters.

A comment on AI-generated sad girl with piano performs the text of the MIT License. Parent comment

Re:AI-generated sad girl with piano performs the text of the... by n4r9 on Friday April 05, 2024 @03:47AM (#39939732)
Generative text-to-image models based on neural networks have been developing since around 2015. Dall-E was the first to gain widespread attention in 2021. Then later models like Stable Diffusion and Midjourney.

"Quadrupled" is a very specific and quantitative word. What measure are you basing that on?

[ Parent | on HN ]
Re:AI-generated sad girl with piano performs the text of the... by hhjinks on Thursday April 11, 2024 @04:01AM (#39999539)
The recommended resolution went from 512x512 to 1024x1024 in that time span :)
[ Parent | on HN ]
Re:AI-generated sad girl with piano performs the text of the... by n4r9 on Tuesday April 16, 2024 @12:06PM (#40053764)
Ah right. But that's only tangentially related to being able to distinguish AI-generated images. There are tells that are completely separate to resolution, such as getting the correct spacing of black keys on a piano.
[ Parent | on HN ]