Hacker News Reader

Comment by postalcoder | Hacker News Reader

They must have trained on GPT Image 1 outputs. The yellow tint is unmistakable.

https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/i...

GPT Image 1 ended up with a yellow tint without training on another image-generation model's output. It's just that humans like pictures with a soft sunset glow, and this is a very easy global signal for a preference model to pick up on, and for a image-generation model to imitate. So optimizing for aesthetic appeal makes everything slightly tinted by default, unless you make sure to countersteer.

Fair point!

Didnt the piss tint come after their big studio ghibli heist?

Maybe it was trained in a Mexican data center https://en.wikipedia.org/wiki/Mexican_filter

Foreign media like the BBC were actually caught applying a yellow filter to footage of China [1] [2] so maybe they trained on that lol

[1] https://www.globaltimes.cn/page/202102/1215710.shtml

[2] https://xcancel.com/thouse_opinions/status/13616465112479539...

yellow/red tint is an extremely common problem not matter the photograph source you train on

source: work at a photograph start, even training on raw images things get tinted, it is an uphill battle

AI-generated images are part of the web now, if you're doing ordinary web scraping, you can't avoid training on generated images.

You clearly haven't met a Chinese RedNote user.

Reply on news.ycombinator.com