| ▲ | simonw 7 hours ago |
| I just got a much better version using this command instead, which uses the maximum image size according to https://github.com/openai/openai-cookbook/blob/main/examples... OPENAI_API_KEY="$(llm keys get openai)" \
uv run 'https://raw.githubusercontent.com/simonw/tools/refs/heads/main/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" \
--quality high --size 3840x2160
https://gist.github.com/simonw/88eecc65698a725d8a9c1c918478a... - I found the raccoon!I think that image cost 40 cents. |
|
| ▲ | makira 7 hours ago | parent | next [-] |
| Fed into a clear Claude Code max effort session with : "Inspect waldo2.png, and give me the pixel location of a raccoon holding a ham radio.". It sliced the image into small sections and gave: "Found the raccoon holding a ham radio in waldo2.png (3840×2160). - Raccoon center: roughly (460, 1680)
- Ham radio (walkie-talkie) center: roughly (505, 1650) — antenna tip around (510, 1585)
- Bounding box (raccoon + radio): approx x: 370–540, y: 1550–1780
It's in the lower-left area of the image, just right of the red-and-white striped souvenir umbrella, wearing a green vest. "
Which is correct! |
| |
| ▲ | cwillu 6 hours ago | parent | next [-] | | I had one problem: finding the raccoon. Now I have two: finding the red-and-white striped souvenir umbrella, and finding the raccoon. | | |
| ▲ | makira 6 hours ago | parent [-] | | simonw posted 2 different images: make sure to look at the second one. | | |
| ▲ | cwillu 6 hours ago | parent [-] | | Yeah, I noticed that just now, but too late to delete the comment :p | | |
| ▲ | jaggederest 4 hours ago | parent [-] | | You had a meta problem, and three, in total: find the raccoon, find the umbrella, find the right link in the comments. |
|
|
| |
| ▲ | M3L0NM4N 4 hours ago | parent | prev [-] | | We would need a larger sample size than just myself, but the raccoon was in the very first spot I looked. Found it literally immediately, as if that's where my eyes naturally gravitated to first. Hopefully that's just luck and not an indictment of the image-creating ability, as if there is some element missing from this "Where's Waldo" image, that would normally make Waldo hard to find. | | |
| ▲ | nerdsniper 2 hours ago | parent [-] | | There seemed to be more space around the raccoon than most other subjects. Zoomed out it appears as almost a “halo” highlighting the raccoon. |
|
|
|
| ▲ | wewtyflakes 4 hours ago | parent | prev | next [-] |
| A startling number of people either have no arms, one arm, a half of an arm, or a shrunken arm; how odd! |
| |
|
| ▲ | davebren 7 hours ago | parent | prev | next [-] |
| The faces...that's nice that it turned a kid's book into an abomination |
| |
| ▲ | keithnz 4 minutes ago | parent | next [-] | | it's interesting, zoomed out it kind of looks ok, zoomed in.... oh my. | |
| ▲ | Filligree 2 hours ago | parent | prev [-] | | By image generation standards this is a ridiculously good result. No surprise that people instantly find the new limits, but they are new limits. | | |
| ▲ | davebren 2 hours ago | parent [-] | | It could already copy the art styles from its training data, what is the advancement here? |
|
|
|
| ▲ | mirekrusin 2 hours ago | parent | prev | next [-] |
| Can it generate non halloween version though? This lower-is-better danse macabre, nightmares inducing ratio feels like interesting proxy for models capability. |
|
| ▲ | 2 hours ago | parent | prev | next [-] |
| [deleted] |
|
| ▲ | louiereederson 7 hours ago | parent | prev | next [-] |
| The people in this image remind me of early this person does not exist, in the best way |
| |
|
| ▲ | gpt5 4 hours ago | parent | prev | next [-] |
| I tried it on the ChatGPT web UI and it also worked, although the ham radio looks like a handbag to me. https://postimg.cc/wyxgCgNY |
|
| ▲ | ireadmevs 7 hours ago | parent | prev [-] |
| I found it on the 2nd image! On the 1st one not yet... |
