Weird that they restrict the resolution so much. Does it fall apart with more detail (when zoomed in) or does the cost just skyrocket?
vunderba 6 minutes ago [-]
It's usually based on what they've been trained on. There aren't very many models that'll do higher resolutions outside of Seedream but adherency is worse.
throwaway2027 1 hours ago [-]
I know people like to dunk on ChatGPT and Gemini and say Claude is or used to be better, but you can still use worse models when you're out of usage AND make use of Nano Banana and and ChatGPT Image generation with separate limits for your subscription. I think it could make it a more package as a whole for some people (non-programmers). I do like having the option and am excited for which improvements they've done to ChatGPT Image generation because in the past it had this yellow piss filter and 1.5 it sort of fixed it but made things really generic with Nano Banana beating it (altough Gemini also had a too aggressively tuned racial bias which they fixed), it seems the images ChatGPT generates have gotten better.
Ok, I can hear the sound of entire industries crumbling right now.
samiwami 1 hours ago [-]
do they have anything similar to SynthID, or are they just pretending that problem doesn't exist?
I know this is probably mega cherry-picked to look more impressive, but some of the images are terrifyingly realistic. They seem to have put a lot of effort into the lighting.
alextheparrot 30 minutes ago [-]
> Integrating an imperceptible, robust, and content-specific watermark
From the system card someone linked elsewhere in the discussion
Legend2440 55 minutes ago [-]
I think we are just going to have to accept that realistic images can be easily fabricated now.
Seeing is not believing anymore, and I don't think SynthID or anything like it can restore that trust in images.
louiereederson 43 minutes ago [-]
The image of the messy desktop with the ASCII art is so impressive - the text renders, the date is consistent, it actually generated ASCII art in "ChatGPT", etc. I was skeptical that it was cherry-picked but was able to generate something very similar and then edit particular parts on the desktop (i.e. fixing content in the browser window and making the ASCII dog "more dog like"). It's honestly astounding, to me at least.
Melatonic 13 minutes ago [-]
We were afraid it would be Skynet and instead we got the ultimate meme generator !
...buuuuuuuuut the price per image has changed. For a high quality image generation the 1024x1024 price has increased? That doesn't make sense that a 1024x1024 is cheaper than a 1024x1536, so assuming a typo: https://developers.openai.com/api/docs/guides/image-generati...
The submitted page is annoyingly uninformative, but from the livestream it proports the same exact features as Gemini's Nano Banana Pro. I'll run it through my tests once I figure out how to access it.
strongpigeon 8 minutes ago [-]
> That doesn't make sense that a 1024x1024 is cheaper than a 1024x1536, [...]
I think you meant more expensive, right? Because it would make sense for it to be cheaper as there are less pixels.
ieie3366 15 minutes ago [-]
It's great. Also doesn't seem to have any "slop" standard look, the images it produces are quite diverse.
I would imagine this will hit illustrators / graphics designers / similar people very hard, now that anyone can just generate professional looking graphical content for pennies on the dollar.
thevinter 52 minutes ago [-]
Every time a new image gen comes out I keep saying that it won't get better just to be surprised again and again. Some of the examples are incredible (and incredibly scary. I feel like this is truly the point where understanding if something is AI becomes impossible)
lehmacdj 26 minutes ago [-]
So do you think there will be a better image model in a year?
GPT Image 2
GPT Image 1direct pdf https://deploymentsafety.openai.com/chatgpt-images-2-0/chatg...
I know this is probably mega cherry-picked to look more impressive, but some of the images are terrifyingly realistic. They seem to have put a lot of effort into the lighting.
From the system card someone linked elsewhere in the discussion
Seeing is not believing anymore, and I don't think SynthID or anything like it can restore that trust in images.
API Pricing is mostly unchanged from gpt-image-1.5, the output price is slightly lower: https://developers.openai.com/api/docs/pricing
...buuuuuuuuut the price per image has changed. For a high quality image generation the 1024x1024 price has increased? That doesn't make sense that a 1024x1024 is cheaper than a 1024x1536, so assuming a typo: https://developers.openai.com/api/docs/guides/image-generati...
The submitted page is annoyingly uninformative, but from the livestream it proports the same exact features as Gemini's Nano Banana Pro. I'll run it through my tests once I figure out how to access it.
I think you meant more expensive, right? Because it would make sense for it to be cheaper as there are less pixels.
I would imagine this will hit illustrators / graphics designers / similar people very hard, now that anyone can just generate professional looking graphical content for pennies on the dollar.