News for hackers. Stuff that matters.
Re:Introducing Images 2.6 by vunderba on Wednesday November 04, 2026 @08:04PM (#50373694)
Decided to try out one of the new features in GPT Image 2.6: the ability to natively generate animated GIF files.

I didn't have high expectations, and I still think you can probably get better results by doing a First-Last-Frame using something like Minimax H3 but I was still rather surprised that it could do it at all.

Here are some of the results. The last one shows its ability to take an existing image and convert it into an animated GIF. It's a picture of my husky inside a snow globe.

https://imgpb.com/OzSMKJ

Re:Introducing Images 2.6 by minimaxir on Wednesday November 04, 2026 @08:09PM (#50373729)
The splotchiness on that simple chess animation makes this GIF feature a nonstarter.
Re:Introducing Images 2.6 by MattDamonSpace on Wednesday November 04, 2026 @08:12PM (#50373751)
Yeahhhh but that’s like saying Dall-E isn’t good enough

Ain’t wrong buuuuut…

Re:Introducing Images 2.6 by vunderba on Wednesday November 04, 2026 @08:23PM (#50373834)
That's a bit hyperbolic. The windmill one is honestly not terrible (slight flicker on the door).

Honestly, you have to think about the use case. GIFs are going to be little throwaway things that you're pasting into Discord or meme-ing.

Nobody's reaching for a GIF if they're looking for professional results.

Re:Introducing Images 2.6 by brian-armstrong on Wednesday November 04, 2026 @08:27PM (#50373867)
Everyone is highly sensitive to slop, and it still looks like slop.

If you actually want something that looks decent, it feels like tool use would at least help cover the obvious blunders. Building layers to composite would go a long way to removing some slop here.

Re:Introducing Images 2.6 by bigyabai on Wednesday November 04, 2026 @08:39PM (#50373970)
The windmill's axis shifts clearly and doesn't rotate at a uniform speed throughout the animation.

It's substantially worse than than an animated SVG of the same thing, and I don't think anyone can pretend otherwise.

Re:Introducing Images 2.6 by MrNeon on Thursday November 05, 2026 @02:52AM (#50376362)
Slight flicker on the door? The axle jumps to the right.
Re:Introducing Images 2.6 by vunderba on Thursday November 05, 2026 @09:36AM (#50379599)
Right - the results seems to be inconsistent (it did a much better job with the eagle). Unsurprising IMHO given that you're essentially asking for a zero-shot of up to 16 coherent frames.
Re:Introducing Images 2.6 by gpugreg on Thursday November 05, 2026 @04:47AM (#50377229)
Yeah, what's up with those splotches? Are those watermarks? I am sure they weren't there a few months ago.
Re:Introducing Images 2.6 by noahjk on Thursday November 05, 2026 @09:17AM (#50379348)
I've noticed it's worse when repeatedly generating against output. Ex. in the ChatGPT app, I'll ask the agent to use the original source image for refinements (if modifying a non-generated image) rather than just prompting for changes, otherwise the mottling gets bad.