YHK - yet another hacker news clone

Introducing Images 2.6

32 points davidbarker 56 minutes ago 10 comments

rarisma 30 minutes ago | parent

FOUR BILLION IMAGES PER WEEK???

fractorial 7 minutes ago | parent

How depressing.

minimaxir 29 minutes ago | parent

Using the grid trick for animations to generate the individual frames has been around for awhile and not specific to ChatGPT: I'm surprised it took this long for one of the official providers to make it explicit. However, adherence between frames is generally tricky, and even in the examples there is a lot of noise between frames although that could be due to compression.

SVG support is interesting but I suspect shenanigans are afoot since that's not how image generation models work, and it would likely strip any SynthID watermarks. It's possible OpenAI has pipelined a raster-to-vector tool that does the conversion automatically. (I developed a similar pipeline and it works extremely well; I'll open source it at some point)

OpenAI claims 50% faster generation with Images 2.6 but curiously price is the same as Image 2.5.

sroussey 25 minutes ago | parent

https://chatgpt.com/share/6aebc6f8-d660-83e8-9cb3-49bdf8caa7...

I guess I should have been careful about “half”?

These models have a hard time imagining men with naturally blond hair getting grey.

minimaxir 18 minutes ago | parent

I would caution against using the webapp to test the quality of this new model because OpenAI does not indicate which image model and effort is being used to generate the image, to my continued frustration.

That said, I gave it one of my more difficult image prompts and the model now surprisingly passes (without plagiaristic cheating): https://chatgpt.com/share/6aebcbcd-6b8c-83e8-b52b-dbedf20ce4...

ipsum2 18 minutes ago | parent

Still has the gross artifacts (visible watermarking) that the other GPT-Image-2.* has. Google's Nano banana watermarking is practically invisible.

SVG is cool though, I wonder how good it is.

jansan 13 minutes ago | parent

Do they have an example of an SVG image created by the new model somewhere?

algoth1 7 minutes ago | parent

Can it finally do pixel art?

minimaxir 4 minutes ago | parent

That depends on your definition of pixel art. (people are exceptionally pedantic about this)

With the right prompt engineering, it (and similar quality models) can indeed do relevant pixel art, but due to the existence of blotchiness/SynthID watermarks you'll need to do some sort of postprocessing regardless.

momojo 2 minutes ago | parent

What's the state of the art for image gen? I'm far removed and pretty happy with the free Gemini tier but its notable to me that I rarely see boasting about being "the best image generator yet" and I wonder if that's because they're all just good enough?