WHAT NEW IN X11.02 MON

AI collections from X · 22 collections · 64,558 posts

gpt-imageIMAGE

A tell for GPT-Image-2.5 output: slogan text in the wrong places

The author says GPT-Image-2.5 often adds slogan-like text where it doesn't belong, such as unprompted "A brighter tomorrow" lines or "Wash / Dry / Fold / Repeat" on a laundry bag.

apophract
@apophractArchived 2026.09.21Originally posted 2026.09.20
A tell for GPT-Image-2.5 output: slogan text in the wrong places
apophract @apophractOriginally posted 2026.09.20
Open original on X

One of my tells for GPT-Image-2.5 generated images is slogan-y text where it doesn't really belong. In particular, the model seems to love to put in text about "A brighter tomorrow" in many situations, unprompted. Another example "Wash / Dry / Fold / Repeat" on a laundry bag.

x.com/apophract/status/2101555569567920345Archived 2026.09.21 10:11