Hacker News new | ask | show | jobs
by minimaxir 59 days ago
Huh, that is indeed better. If ChatGPT Images 2.0/gpt-2-image is more nondeterministic than usual, than that is in itself a useful data point.
1 comments

Did you enable thinking for your experiment? Are you sure you were on the 2.0 rather than 1.5 version?
That experiment image was directly through the API on high. (no Thinking parameter like the Web UI)