←back to thread

Gemini 2.5 Flash Image

(developers.googleblog.com)
1092 points meetpateltech | 7 comments | 26 Aug 25 14:01 UTC | HN request time: 0.231s | source | bottom
Show context
skybrian ◴[26 Aug 25 16:55 UTC] No.45029197[source]▶
Like most image generators, it didn’t pass the piano keyboard test. (Black keys are wrong.)

https://aistudio.google.com/app/prompts?state=%7B%22ids%22:%...

replies(9): >>45029266 #>>45029269 #>>45029353 #>>45029404 #>>45029503 #>>45029767 #>>45029823 #>>45029961 #>>45032710 #
joombaga ◴[26 Aug 25 16:59 UTC] No.45029269[source]▶
What is the piano keyboard test? Your link requires granting AI Studio access to Google Drive, which I do not want to do.
replies(1): >>45029407 #
1. raincole ◴[26 Aug 25 17:08 UTC] No.45029407[source]▶
Just ask it to generate a correct piano keyboard. It's something the current gen of image generator AIs fail at.
replies(1): >>45031084 #
2. ZiiS ◴[26 Aug 25 19:26 UTC] No.45031084[source]▶
Do most humans pass?
replies(3): >>45031284 #>>45031551 #>>45031760 #
3. adzm ◴[26 Aug 25 19:38 UTC] No.45031284[source]▶
2-2-1-2-2-2-1
replies(1): >>45031583 #
4. phainopepla2 ◴[26 Aug 25 19:56 UTC] No.45031551[source]▶
Presumably most humans with a camera do
5. polynomial ◴[26 Aug 25 19:58 UTC] No.45031583{3}[source]▶
I still feel like most humans would fail, haha.
replies(1): >>45034829 #
6. raincole ◴[26 Aug 25 20:13 UTC] No.45031760[source]▶
Most humans fail at 4 digits multiplication, or drawing a cube in perspective.
7. twodave ◴[27 Aug 25 02:29 UTC] No.45034829{4}[source]▶
Maybe, but anyone who knows what a chromatic scale is should be able to reason it out. E# == F, B# == C, so no black keys between those.