←back to thread

Gemini 2.5 Flash Image

(developers.googleblog.com)
1092 points meetpateltech | 5 comments | 26 Aug 25 14:01 UTC | HN request time: 0.001s | source
Show context
adidoit ◴[26 Aug 25 15:00 UTC] No.45027540[source]▶
Very impressive.

I have to say while I'm deeply impressed by these text to image models, there's a part of me that's also wary of their impact. Just look at the comments beneath the average Facebook post.

replies(5): >>45027591 #>>45027818 #>>45027979 #>>45028381 #>>45035261 #
1. postalcoder ◴[26 Aug 25 15:18 UTC] No.45027818[source]▶
I have been testing google's SynthID for images and while it isn't perfect, it is very good, insofar that I felt some relief from that same creeping dread over what these images will do to perceived reality.

It survives a lot of transformation like compression, cropping, and resizing. It even survives over alterations like color filtering and overpainting.

replies(1): >>45027876 #
2. sigmar ◴[26 Aug 25 15:23 UTC] No.45027876[source]▶
facebook isn't going to implement detection though. Many (if not most) of the viral pictures are AI-generated. and facebook is incentivized to let their users get fooled to generate endless scrolling
replies(2): >>45027917 #>>45029284 #
3. paul7986 ◴[26 Aug 25 15:27 UTC] No.45027917[source]▶
Along with those being fooled there are many comments saying this is fake, AI trash and etc. That portion of the commenters are teaching the ignorant and soon no one will believe what they see on the Internet as real.
replies(1): >>45028553 #
4. bonsai_bar ◴[26 Aug 25 16:13 UTC] No.45028553{3}[source]▶
> soon no one will believe what they see on the Internet as real.

Now is that so bad?

5. qingcharles ◴[26 Aug 25 17:00 UTC] No.45029284[source]▶
They already did. Certainly on the backend. For a while they were surfacing it, but I think it's gone again. But Meta is definitely onto this.