alt Hacker NewsChatGPT Images 2.5
Comments
I've really enjoyed using AI to generate images. For example, Long time ago, I read an amazing five-book saga called Riverworld, and I used AI to recreate many scenes, places, and ideas from the story. Seeing the books come to life through hundreds of images was a great experience. Definitely one of the coolest things to enjoy in 2026. Try it with your favorite books.
Omg, I love how the first examples just show how easy you can fake things. Fake being at a party with your friends. Didn't make your bed, no problem, just fake it.
The sad part is my mother would love "remixing" my old child photos of me.
This is a nice showcase of what it can do but so little of it seems to be actually useful or rather odd choices. Some examples were already mentioned, but also the Gdocs presentation: apart from the terrible layout, why would one use fake photos of the sun in a "science" talk when there is an abundance of real high-res photos available? For educational purposes these are even free to use.
I'm trying to make a looping animation of a small icon, for a UI.
Does anyone here know which AI tool is good for this usecase?
I've tried Gemini and Adobe Firefly with 2 keyframes, but they cannot do looping animations, and they seem to have trouble getting icons right (they invent features that I don't want).
The "composite party photo", while impressive, shows that still the miniscule details are being lost, like the teeth structure of the guy in the middle or the fact that the guy on the left is holding the cup with three fingers. Wondering why they chose this edit for the showcase.
A big wtf at the LM Arena scores: https://arena.ai/leaderboard/text-to-image
gpt-image-2.5-sunburst: 1421
gpt-image-2.5-flare: 1399
gpt-image-2 (medium): 1381
mai-image-2.6: 1331
Even with LM Arena being flawed, this is significant. I was planning to do a writeup on the original gpt-image-2 as it crushed every complex image comprehension benchmark I had...I'm glad I procrastinated since ChatGPT Images 2.5 seems like an even better starting point to test out what these models can actually do nowadays.
Many people still think AI images output the wrong number of fingers on a regular basis. (EDIT: this was an ironic comment to make in hindsight and I own it)
Did anyone else notice that all the use cases they show here are "use ChatGPT Images to imagine all the things you'd like to have, but don't"? For some, they then show the thing being done, since just imagining it is a bit sad. But ChatGPT Images can't help you with that part. At best, it's providing creative inspiration - but that's often the most rewarding part of the process for a human... None of the examples show things where you just need an image directly, e.g. product labels, signage, sprites, textures, images for websites etc. I guess aspirational stuff sells?
In order, there's:
- Imagine you had better decorations for your fish.
- Imagine you had a tattoo of your pet.
- Imagine you had a unique candle holder.
- Imagine you had a worse haircut.
- Imagine your flowers were arranged.
- Imagine your child had a suit.
- Imagine your dog had a costume.
- Imagine you owned a scanner.
- Imagine you could hang out with friends.
- Imagine your bed was made.
There's maybe something cool at the core of this - help you ideate by seeing things in images! - but it's lost in all the other awful ways this gets used. More fake menus with food that looks nothing like the real thing. More fake book covers displacing real artists.
I can admire and enjoy the work of coding agents, which mostly just help solve problems and save me time. I can appreciate that there are creative uses for agents with text, that they could save people time, and that the environmental and safety concerns potentially have solutions.
I just can't see my way to appreciating these art agents, or any use of AI as a replacement for a human creative process. It's not because their output is bad, anymore (though sometimes it still isn't great). It's because it is bereft.
Even if I could, nobody in my life would be okay with my using them alongside my actual creative work. In fact, they'd be pretty upset if I did. And if I found out they'd been sharing stories with me written by AI, I'd be mad, too.
I'd rather just see the prompts.
The Facebook Marketplace experience for used items has depreciated considerably with the widespread adoption of LLMs. Between placing attractive models in photos to help sell items to "improving" the visual condition of items that completely misrepresent the real condition of the item, it's becoming a trickier landscape to navigate to find what you're looking for.
The introductory video is a bit... daring. Generating tattoos that clearly look AI-generated is not one of the use-cases I'd try to sell.
Great idea, get an AI art tattoo so you can always be reminded how AI art looked in 2026.
Look at the kid in a costume. The shoulders of ChatGPT’s output are just wrong. Sure, the kid looks prettier, stronger with a wider upper body, closer to society’s ideal of a child. But it’s not him. If you put that child in a suit, he’d still have a smaller upper body and the arms wouldn’t fill out the suit as nicely as the child in the AI image does.
It’s just not the same child.
I know we’re gonna get there eventually, but still, seeing as this is their first demo image on the page I just can’t help but scream inside “HOW CAN YOU NOT SEE THIS?”
It really makes me question whether the people building, or at least the people marketing this, actually understand their product. I love image generation for all kinds of use cases, but I find that particular example creepy.
Composite party photo...this is going to revolutionize tinder profiles.
The societal hurt coming out of public releases of image/video generation models must surely outweight the gain. That said, this is super impressive.
I've done a side by side comparison of the two new models across all quality levels. Versus all the previous models
https://generative-ai.review/2026/09/rush-openai-image-gen-2...
right, off to bed now
Still far too expensive.
At this point, I'm much more interested in seeing releases for models chasing down prices on "good enough" to unlock new use-cases than I am SOTA.
I've been using Grok Imagine V1 in prod for months now as its quality for my use-case is already more than enough.
I can't stop thinking that these use cases aren't real, and OpenAI is just gaslighting people. Humans don't need AI for these trivial things.
This ad feels like a science fiction, where humans can't do anything without the help of their AI assistants.
- Design a tattoo of my cat
- What hairstyle should I have
- Arrange these flowers
What next? Who should I date? Open the door?
the clothing examples are super odd because its not actually useable. the clothes will not look like that on you, it just fits them to your body.
Does it still have that distinct off-white shading of previous models though?
I'm 99% sure that that is the main tell AI sniffers rely on.
Even GPT Images 2.0 was already the best image generator that I have tried, however it has one massive disadvantage: draconian censorship. Even rendering a gun in a scene will get flagged as "violent" and I need to create a battle scene... there's no way to do that with the censorship the way it is
allllll the way at the bottom
> Pricing and availability
> Images 2.5 is rolling out today to ChatGPT, ChatGPT Work, and Codex users across all tiers on desktop, mobile, and web.
> GPT‑Image‑2.5 Sunburst and GPT‑Image‑2.5 Flare are available in the API. See pricing details here.
and the link to the pricing details is a page where i am either too dumb to find the pricing details, or they don't exist
> Arrange these flowers
What kind of person cares enough to buy flowers for an arrangement, but is uninterested in arranging them? What's next, will we buy music for our AI's to listen to? Food for them to eat?
There's a lot of drudgery that can be automated away, but this seems to be focused on automating the fun parts away.
Surprised to see no acknowledgement of how "AI Menu Slop" has become deeply associated with ChatGPT.
Everywhere I go now I see places that blatantly used ChatGPT for their menus or posters and they all look the same.
It feels almost existential to the service, I know its a bit of survivor bias but so many images you can tell immediately are ChatGPT vs other image providers, and I feel many people are sick of them.
None of the improvements are particularly useful for my principal use-case. Creating infographics to visualize how things interact and so on. But it’s always nice to see improvement here.
I hope my local kebab shops switch to this for their signs.
Can someone recommend a correct way for interior design ideas?
Yesterday tried GPT-6-Astra Light to have a kitchen remodel... well it did understand 2D space, an improvement when tried on GPT-5.6-Sol
But the image representation was way off and I was not satisfied... misplaced the window, drew a wall which was not on 2D image, cabinet size issues. Eh.
I feel it's more like a Nano Banana 2 update. It's much faster than gpt-image-2 but the quality isn't much different.
The AI tattoo. Hope you don’t have any ragrets.
Don't tap the aquarium glass man
I used it to visualise different arrangements of my furniture and it worked nicely. Personal interior designer
Is this included in the 20/month plan?
I had trouble weeding through all the marketing speak.
drink more water is a crazy thing to ai generate
I plan to try something for designing the UI of my website.
Surprised there is no mention of the Sketch feature so far. That's very powerful! I do art on the side and I know no better of getting the result I want than passing in a first draft sketch.
I super encourage others to learn just a little bit of art technique and your images are going to go to the next level. You need a little construction, perspective, gesture, anatomy, and you're pretty much off to the races.
Knowing names of illustration styles is great too. Look up "style transfer" if you are not familiar.
ChatGPT Images is for me the most impresive of all models, but also the one I hate the most, because of what it's used for: either funny wasteful use, or nefarious use, basically nothing else.
Do all Silicon Valley corporations use the same jingle for their product promotional videos? The creator must be really rich by now.
I hate so much how every food menu is now AI slop. I wish that was outlawed under false advertising.
Ah. Another 3 months delay for gemini-3.5-pro.
wtf are these comments what happened to hn.
Where is Dall-e?
feels this something backhanded
Earlier today I couldn't get ChatGPT to draw a horse on the moon. Idea taken from Stable Diffusion's wikipedia page. I tried three times with that prompt, "a photograph of an astronaut riding a horse" and again with a horse on the moon. I got it to do another image. However, the original prompt just worked, though it didn't happen to choose the moon, it didn't say the moon.
Edit: finally, I have my horse on the moon. https://chatgpt.com/share/6aa0627e-b168-83e9-98e5-d5ad5a9cad... Though the horse doesn't have a spacesuit, neither does it have one in the Stable Diffusion wikipedia page.
Edit 2: finally got the kind of result I wanted https://chatgpt.com/share/6aa06813-4818-83e9-9c19-8c8ac9a348... https://chatgpt.com/s/p_359c0c38939c81918addaaa9de196f4e
Does multi turn image consistency mean they have solved the yellow tint issue?
Fine tuned slop. It still isn’t very visually appealing, what’s the end game here?
Good, keep going.
text-to-text is a solved problem.
Trump is going to have so much fun with this!
Is this even public?
I use gpt image 2 very heavily for my current project (ai UI design tool). The biggest improvement I'm seeing with this is in speed. I've generated around 50k images with gpt-image-2 via api, the the average latency has held at around 104s.
It's wild how much of a difference this is - images are coming in at around 35-40s. Very noticable, and makes a difference when you're iterating quickly: https://jjcm.org/gpt-image-2.5-speed.mp4