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.

	▲	postalcoder 15 hours ago \| parent \| next [-]
		Fair point!
	▲	Grimblewald 15 hours ago \| parent \| prev [-]
		Didnt the piss tint come after their big studio ghibli heist?

▲

cousinbryce 6 hours ago | parent | prev | next [-]

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

	▲	porphyra 2 hours ago \| parent [-]
		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...

▲

hugmynutus 11 hours ago | parent | prev | next [-]

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

▲

dannyw 14 hours ago | parent | prev | next [-]

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

▲

greyb 10 hours ago | parent | prev [-]

You clearly haven't met a Chinese RedNote user.