ChatGPT Images 2.0 • Hacker News Board

Re: ChatGPT Images 2.0

#21

Post by incognito124 » Tue, Apr 21, 2026, 7:37 PM UTC

zb3 wrote: post #14

Image generation? Hmm, would be cool if OpenAI also made a video-generation model someday..

If only there was a social network with solely AI generated videos, I would pay literal money for it...

Re: ChatGPT Images 2.0

#22

Post by simonw » Tue, Apr 21, 2026, 7:37 PM UTC

makira wrote: post #18

simonw wrote: post #15

I've been trying out the new model like this: OPENAI_API_KEY="$(llm keys get openai)" \ uv run https://tools.simonwillison.net/python/openai_image.py \ -m gpt-image-2 \ "Do a where's Waldo style image but it's where is the raccoon holding a ham radio" Code here: https://github.com/simonw/tools/blob/main/python/openai_imag... Here's what I got from that prompt. I do not think it included a raccoon holding a ham radio…

> though the problem with Where's Waldo tests is that I don't have the patience to solve them for sure I see an opportunity for a new AI test!

I've actually been feeding them into Claude Opus 4.7 with its new high resolution image inputs, with mixed results - in one case there was no raccoon but it was SURE there was and told me it was definitely there but it couldn't find it.

Re: ChatGPT Images 2.0

#23

Post by rqa129 » Tue, Apr 21, 2026, 7:38 PM UTC

Can it generate Chibi figures to mask the oligarchy's true intentions on Twitter and make them more relatable?

Re: ChatGPT Images 2.0

#24

Post by tptacek » Tue, Apr 21, 2026, 7:39 PM UTC

simonw wrote: post #15

I've been trying out the new model like this: OPENAI_API_KEY="$(llm keys get openai)" \ uv run https://tools.simonwillison.net/python/openai_image.py \ -m gpt-image-2 \ "Do a where's Waldo style image but it's where is the raccoon holding a ham radio" Code here: https://github.com/simonw/tools/blob/main/python/openai_imag... Here's what I got from that prompt. I do not think it included a raccoon holding a ham radio…

5.4 thinking says "Just right of center, immediately to the right of the HAM RADIO shack. Look on the dirt path there: the raccoon is the small gray figure partly hidden behind the woman in the red-and-yellow shirt, a little above the man in the green hat. Roughly 57% from the left, 48% from the top."

(I don't think it's right).

Re: ChatGPT Images 2.0

#25

Post by ritzaco » Tue, Apr 21, 2026, 7:40 PM UTC

simonw wrote: post #15

I've been trying out the new model like this: OPENAI_API_KEY="$(llm keys get openai)" \ uv run https://tools.simonwillison.net/python/openai_image.py \ -m gpt-image-2 \ "Do a where's Waldo style image but it's where is the raccoon holding a ham radio" Code here: https://github.com/simonw/tools/blob/main/python/openai_imag... Here's what I got from that prompt. I do not think it included a raccoon holding a ham radio…

haha took me a while to notice that one of the buildings is labelled 'Ham radio'

Re: ChatGPT Images 2.0

#26

Post by rqa129 » Tue, Apr 21, 2026, 7:43 PM UTC

esafak wrote: post #17

https://openai.com/index/introducing-chatgpt-images-2-0/

Thanks, all displayed images look horrible and artificial. This will fail like Sora.

Re: ChatGPT Images 2.0

#27

Post by simonw » Tue, Apr 21, 2026, 7:43 PM UTC

Suggest renaming this to "OpenAI Livestream: ChatGPT Images 2.0"

Re: ChatGPT Images 2.0

#28

Post by ritzaco » Tue, Apr 21, 2026, 7:43 PM UTC

tptacek wrote: post #24

simonw wrote: post #15

I've been trying out the new model like this: OPENAI_API_KEY="$(llm keys get openai)" \ uv run https://tools.simonwillison.net/python/openai_image.py \ -m gpt-image-2 \ "Do a where's Waldo style image but it's where is the raccoon holding a ham radio" Code here: https://github.com/simonw/tools/blob/main/python/openai_imag... Here's what I got from that prompt. I do not think it included a raccoon holding a ham radio…

5.4 thinking says "Just right of center, immediately to the right of the HAM RADIO shack. Look on the dirt path there: the raccoon is the small gray figure partly hidden behind the woman in the red-and-yellow shirt, a little above the man in the green hat. Roughly 57% from the left, 48% from the top." (I don't think it's right).

I tried

> please add a giant red arrow to a red circle around the raccoon holding a ham radio or add a cross through the entire image if one does not exist

and got this. I'm not sure I know what a ham radio looks like though.

https://i.ritzastatic.com/static/ffef1a8e639bc85b71b692c3ba1...

Re: ChatGPT Images 2.0

#29

Post by arealaccount » Tue, Apr 21, 2026, 7:43 PM UTC

simonw wrote: post #15

I've been trying out the new model like this: OPENAI_API_KEY="$(llm keys get openai)" \ uv run https://tools.simonwillison.net/python/openai_image.py \ -m gpt-image-2 \ "Do a where's Waldo style image but it's where is the raccoon holding a ham radio" Code here: https://github.com/simonw/tools/blob/main/python/openai_imag... Here's what I got from that prompt. I do not think it included a raccoon holding a ham radio…

I see the raccoon

Re: ChatGPT Images 2.0

#30

Post by louiereederson » Tue, Apr 21, 2026, 7:43 PM UTC

The image of the messy desktop with the ASCII art is so impressive - the text renders, the date is consistent, it actually generated ASCII art in "ChatGPT", etc. I was skeptical that it was cherry-picked but was able to generate something very similar and then edit particular parts on the desktop (i.e. fixing content in the browser window and making the ASCII dog "more dog like"). It's honestly astounding, to me at least.