Can’t emphasize this enough. I was locked out of Pro image gen due to a deployment bug (fixed just tonight), and it’s much better. The old intuition says model choice and image quality are unrelated because it all funnels to a txt2img tool call, and that intuition is now wrong.
@goodside
-
ChatGPT Images 2.0: FF6-style 16-bit JRPG Boss in Chipotle, Byrne vs. Fischer Chess Position
By
–
ChatGPT Images 2.0 generates a boss fight from a 16-bit JRPG in the style of FF6, but they're in a Chipotle and the boss is just the board position from Byrne vs. Fischer (1956) right after Byrne captures Fischer's queen.
-
Pro image generation fails, falls back to code-generated PNG
By
–
Image generation in Pro isn’t working for me right now actually — the reasoning trace notes it has no imagegen ability, so for unambiguous image requests it spins for a while and eventually settles for making a downloadable PNG with code. Is this just me hitting usage quotas?
-
Using temporary helper images as multimodal input for generation
By
–
Internally it appears to create temporary “helper images” (presumably using code here) and then uses those outputs as multimodal input for the final generation.
-
ChatGPT Images 2.0 generates game die with Wikipedia QR codes
By
–
ChatGPT Images 2.0 generates a game die but instead of numbers it has working QR codes for each of their Wikipedia articles
-
ChatGPT Images 2.0 generates an 11-petal crocheted doily
By
–
ChatGPT Images 2.0 generates a crocheted doily with 11 petals—i.e. order 11 radial symmetry. (I was unable to find any 11-petal doilies via Google Image Search, and the reasoning trace included seven iterations before this result, so I’m confident it’s somewhat original.)
-
Image generation confirmed: Easy fix for numbers, but mistake left for honesty.
By
–
Yes — this also proves it's imagegen, i.e. it didn't just literally generate the whole thing via code. Fixing this was as easy as saying "Fix the numbers in the lower right." I did do this but decided it was more honest to leave the mistake in.
-
Creating helper images via tools then img2img on result
By
–
From the reasoning trace it seems to be creating "helper images" via tools and then does img2img on the result.
-
Helper images created by code, then turned into worksheets with imagegen.
By
–
Yes. It appears to create what it calls "helper images" by writing code to produce the maze itself, and then turns it into a worksheet using imagegen (adding the title, the name in cursive, etc.)
-
School maze worksheet with blue pen solution and ChatGPT Images 2.0
By
–
"School worksheet with maze, 32 wide by 48 tall, rows and columns numbered, no unreachable rooms, solution in blue pen, name field reads 'ChatGPT Images 2.0' in cursive at top" Note the fusion of code and imagegen this task requires.