I wonder if there's some weird accounting going on, or if this is real. It would mean around 24M images an hour and that's in the area of "more images than anyone will see". It means there's lots of wasted automated effort in this process somewhere, even if we assume some creators will request 8x variants of their ideas.
I don't use AI image generation anymore, but when I was fiddling with it I would generate dozens of images per idea, limited only by my patience. "The same thing but a little different" is the easiest feedback you can give anything.
Same, when I messed around with it to learn how the models worked I would generate batches of hundreds or thousands with slightly tweaked prompts and negative prompts to get a sense of how the inputs changed the outputs.
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.
Yeh using sprites to make frames consistent (kinda tilting latent space towards a character consistency, zero-shot ~LoRA hack?) is old-school. I did this 3 years ago. https://j11y.io/dance/
I tried it with Sunburst with both gpt-5.5 and gpt-5.6-sol, and the results were nothing spectacular. It’s something you could already do in the ChatGPT interface by asking it to convert an existing image to an equivalent SVG.
Recraft is probably the only group I know of that had a native text-to-SVG generator pretty early on, but since it’s a closed model, I’m not familiar with what they were doing under the hood technically.
Re SVG: and it would likely strip any SynthID watermarks.
It could be viable to encode SynthID-like variables in subtle variations of positioning of elements, path lengths, etc. I think I saw an article on here a couple weeks ago which used such techniques to hide 'messages' in SVGs. It might even be possible to do it in a way which survives basic manipulations, as with rasters.
> 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)
If I could somehow subscribe to ensure I see this when you do, I would.
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.
I think it's more impressive that it managed so much coherence in a single image than anything else. Very few problems with each of the pokemon anatomically speaking. Mew's kind of a mess but the rest are pretty accurate.
That being said, the ukiyo-e artwork looks more like a standard colored pencil illustration, and it sort of tried to cheat by adding some vaguely Japanese natural scenery.
See this Kickstarter all the way back in 2013 for a great example of what Pokémon might actually look like as ukiyo-e woodblock prints.
I remember that Kickstarter. I follow the woodblock carver who worked with the artist. His name is David Bull and he has some great videos on woodblock carving on YouTube: https://m.youtube.com/@seseragistudio
That prompt seems almost deliberately obtuse. The natural phrasing would be “greying blonde hair”. If you described someone as having half-X, half-Y hair, I’d expect to see something like that image, too.
The image does not show up for me. I’m guessing the man has black roots and possibly black and white stubble?
Since blond models always have dark roots (blond highlights, not natural blinds) in order to have better framing of the face in photographs, the ai models will never show an actual blond.
I think that particular one would be a prompting problem. Instagrammers and anime artists do left-right two-tone dyes all the time, so left-right two-tone rather than meshed gray blonde would be a reasonable interpretation of "half blond and grey hair" based on representations on Internet collected data.
It looks like the images in there are 'based' on the "hot springs symbol" - a Japanese map symbol encoded into Unicode that seems to have become synonymous with "piping hot bread" in the West!
The images in the GPs link show a common pictogram for artisanal bread. The image itself is actually a close representation of the real thing. An image search for sourdough will return many images showing bread with a similar appearance.
Anecdotally, I’ve never seen that hot springs symbol used for bread, and I’ve lived in the west my whole life.
Not without irony, but connecting the bread symbol with the hot springs symbol feels like the sort of mistake an llm would make.
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.
If you define pixel art as just a vague overall look, then yes, it can do pixel art. If you define pixel art as being limited to a fixed color palette, like 16 or 256 colors and aligned to a square grid, then no, not without some manual post-processing.
It's not helped by the fact that a lot of people who are not artistically inclined will generate pixel art on these image generators at 1MP resolutions (far higher than traditional pixel art), such that even the casual observer can typically see the bad smearing and fringing in the final result.
There are SDXL pixel art models out there that do actual pixel art. They generate images that are 8x too large, you need to downscale them and reduce colors externally.
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?
I've been running a comparative image benchmark site for years now (see my profile for the link), ever since SDXL back in 2023, and the answer really comes down to it depends. My benchmark focuses primarily on prompt adherence, but that's just one metric you can use. (fidelity, censorship, explorative, speed, features, etc are others)
In terms of overall state of the art, the two major contenders are probably Nano Banana Pro (Google) and the GPT Image 2 series (OpenAI).
For pure prompt adherency, OpenAI has consistently lead the pack since the original gpt-image-1 released back in March of 2025.... but its OpenAI's fidelity has always left something to be desired. Version 2 of the series has definitely closed the gap a bit.
I've been playing with it for the last hour or so. I immediately updated my platform to use both since 2.5 is my primary model (i run a prompt->design site).
After playing with it for an hour, I'm rolling back 2.6-flare to 2.5-flare. I've found 2.6-flare specifically to be too simplistic in its approaches.
Yeah, I've been mystified for years why they can't just train the "AI look" out of images. Is it, like, something undetectable by machine? But then how come we can often detect it so easily?
I think this is fundamental. People will probably dislike whatever it is that AI images look like, because whatever they look like is going to be associated with cheap. They could have a totally different aesthetic and I think most people's conception of cheap would adapt to whatever that is.
Very true. My theory is that if AI was able to produce a diverse enough range of styles (not artistic style, more like "artist's touch/bias"), then it would be much better. Exactly like Claude, talking to it wouldn't be so grating if it had, say, a 1000 different "writing styles" instead of the single one we have to engage with.
The current models have a fundamental architectural flaw: Every pixel they output costs the model as much effort as every other one. When you see detail in a work a human produced, the fact that there is detail communicates something about what the artist was focussing on. It shows you what they cared about, and by extension what you, the viewer, should care about to understand the piece. The AI, as currently designed, can’t do that, because it’s outputting entire raster images at once (and multi-pass generations tend to degrade into melty nonsense), it emphasises everything, and so emphasises nothing.
The “AI look” is a manifestation of the architecture itself, and that’s why you can really train or prompt around it. At best, bigger models have been able to partially suppress the worst aspects of it by throwing more parameters at the problem, but put the models under even a tiny bit of stress and the same flaws reemerge.
Some of it has to do with Classifier Free Guidance (CFG), a math thing that makes it more likely for a diffusion model to follow what you ask for in the prompt. However, turning up CFG inevitably causes high contrast and certain other artifacts.
With that being said, my understanding of that issue is a few years old, people have always said CFG is a havk until models get better at following prompts on their own. So thee “look” that tools like Nano Banana ends up with could be something else. It may or may not be a necessary artifact of some part of the process.
The problem isn't the classifier free guidance itself, but the choice of parameters. When a parameter above 1 is chosen you get images which very stronger conform to theme, but which there's not a good mathematical justification for.
Yeah, it must be some algorithmic thing like CFG that causes the unrealistic AI look. Dall-E 2 didn't have it, but Dall-E 3 did to an extreme degree. Google's Imagen <= 3 also didn't have it, but Imagen 4 (and Nano Banana, which seems to use Imagen 4 in the background) suddenly had significant AI look, apart from much better prompt following.
Yeah. I just read a bit about it and looked at some examples, and it seems CFG>1 is a hack to get sharper images from a given model, at the cost of giving them the "AI look". As models get better, we'll be able to use CFG=1 and much of the problem will go away.
You are actually a very skilled pattern recognizing machine. There's likely always going to be some bias and purple are going to be able to detect it and the human style will move away from it.
It does look terrible. But keep in mind these decisions aren't made to please you or me on HN. The numbers clearly show the average user does not care about the AI look because they can't really tell the difference between human-gen and AI-gen. Whatever saves them money is what they will go with.
> The numbers clearly show the average user does not care about the AI look because they can't really tell the difference between human-gen and AI-gen.
Do you have a link to the numbers that clearly show this?
Do you need statistical numbers for every information you receive? I don’t have any numbers to show you besides the fact that everyone I have spoken to in the last 6 months knows how to generate an image on ChatGPT. I work in the construction industry, and 100% of the companies I deal with have at some point posted an AI-generated poster on their social media, or created their flyers and business cards. YMMV.
Well, you said "the numbers show". But anyway, not being able to tell the difference and not caring is very different from "having tried it at some point".
> everyone I have spoken to in the last 6 months knows how to generate an image on ChatGPT.
That goes without saying. If you can speak to them, if they have a pulse, they can "generate an image". A cat walking over a keyboard can generate an image. That is the lowest bar ever.
Someone posted an AI picture on Twitter, that was done in the style of a great classic painter of renown. Everyone tore it apart, discussing all the details that betrayed it as a pale imitation of the original. It was roundly panned as an example of how AI will never be good enough to replace humans. After this went on for some time, the initial poster revealed it wasn't actually AI at all, it was a genuine original from the artist in question.
People just hate AI and will find a post hoc justification for their hatred in every situation. The link you gave could have just as easily been someone expressing surprise and delight at the artists choice to not follow traditional physics... but instead be playful in unconstrained ways. Shrug.
that kind of experiment was done multiple times, someone put a very famous photo from a very famous photographer on some photography critique forum and it was torn apart: badly framed, blurry, no composition, ....
the vast majority of people have no idea what they are doing, going on vibes and copying the opinions of their peers
Artists aren't machines that churn out one masterpiece after another, they do create bad works (most artists would acknowledge that) and there are one hit wonders. I look at a lot of art and sometimes I like only one painting out of a series, or even out of a lifetime of work. Also, you often need the context of the artist's broader work to judge the quality of a single piece, which might otherwise appear like a bad picture in vacuum.
Most people in general, and for sure the majority of current twitter users have no clue what they're talking about when it comes to modernist art and its direct predecessors.
I’ve only seen that happen once, and it was using a cropped Monet, but by cropping it, the picture actually did become bad. It was poorly composed, the colour balance was ruined and the level of detail was too low relative to the size of the brush strokes. These ‘gotchas’, when they aren’t just complete fabrications (which, given how often I see people talk about them, but how rarely I see any evidence presented, is most of the time) generally only reveal how little the people running the ‘experiments’ understood about art in the first place.
I doubt it, same with people that use ChatGPT for everything and don’t see the slip anymore and are confused when you point it out. LLM blindness is a real thing.
I'm deeply interested in this subject. In conversation, most people I talk to say they hate the look of AI generated "art," or find it uncanny or uncomfortable. However, whenever I'm on the bus or train, if I peek over the shoulder of someone, it's 50% chance they're endlessly scrolling AI generated short form video, either as unrelated clips or Chinese dramas (this being in Taiwan).
I suspect people are somewhat hypnotized by the content, in the same way a toddler is hypnotized by Cocomelon. Something about it is enthralling and keeps the attention. I wonder if it's related to the phone game icon / YouTube thumbnail phenomenon of "person's face making an extreme expression with the mouth open." AI generated videos for example still tend to have very exaggerated facial expressions and the mouth is always unusually wide when talking. I also wonder if something about the uncanny smoothness of movement (I assume caused by any form of transition defaulting to "linear") has a hypnotic effect.
I'm not sure how to look into this further. Elsagate is an interesting past example, and what I've learned so far I threw in a blog post a couple months back https://blog.calebjay.com/posts/psychic-attack/
Right now I'm looking into "Lula's army" and the AI generated content they used. I feel like there's something significant and perhaps even dangerous that could be developed bere.
whats incredible is when in their video they're talking about complexity, the cat's images have extra limbs in low and medium complexity. They could've easily generated more versions to get the clean versions. But it just doesn't seem like they care. Maybe this is what someone who is so used to using AI to move fast becomes: someone who drops the quality bar to 80%?
They mentioned multiple times in previous blog posts that they do not cherry pick examples.
Would you be happier if their model generated cats with 5 legs in 99% of cases, and they cherry picked that 1 in 100 image where it has 4 legs? Do you think that is showing them caring?
I doubt their models are that bad for simple and common things like cats, probably takes just a handful of tries at most for something like getting the correct number of limbs. They could just mention the number of tries on the side like a little bubble showing up to show “Rendered in 5 attempts” or something along those lines. I wouldn’t think less of the tech personally.
That's an interesting observation, and that's also my feeling: Everything is now expected to move so fast, dropping quality bar to 80% or below is not uncommon.
Not like this is the fault of the AI progress, we could use AI to go beyond the quality what we used to deliver, too. It's just the pace expectations that are now "in the room" ?
People who make things often have an unrealistic expectation of how much users care about quality (and don't realize how much users actually care about price).
We've seen this play out over and over again, in many different sectors. The whole shtick of the old (Bellhead) telecom world was quality at the (literal) expense of price, which didn't work out well for them. Same for CD versus pirated mp3s, DVD versus pirated videos (and, to a lesser extend, theaters versus bootleg cam releases), native texting / GSM calls versus WhatsApp and similar, mainstream newspapers and media versus blogging and social media, traditional electrical appliances versus Chinese-made, and so on.
Because of the innovator's dilemma, In many cases, the cheaper, lower-quality product later surpasses the quality of its more expensive counterpart.
AI is just one more example of this happening. It lets you make more things which otherwise would be far too expensive to make, even if that often means a lower quality product.
I find it interesting that after all this time, Midjourney still seems to be the leader in aesthetics.
It's retained has a lot of the issues that other AI image gen has moved past: It's still not very good at following directions, it still makes basic mistakes occasionally like wrong number of fingers, it still often creates weird nonsensical AI messes in the background. But what it has retained all the way through, is that excellent sense of aesthetics. It seems like we haven't really figured out how to have both - you can have accurate or beautiful, but not together.
As a few examples, here are some random images I've created in the past with it:
The input and output pricing per token remains the same between 2.5 and 2.6, although using their image pricing calculator shows a quadrupling of token usage at low and medium quality settings for 2.6. For e.g. at 1024x1024:
2.5 low, 196 tokens, $0.006
2.6 low, 823 tokens, $0.025
2.5 med, 439 tokens, $0.013
2.6 med, 1449 tokens, $0.043
Interestingly, higher quality settings show no change in token usage between the models.
Similar results for my workflow. And the Round art comes out significantly less round without prompt changes (more input tokens)
Setting (1024x1024) Tokens Cost/image Time
2.5 medium 439 $0.014 12.0 s
2.6 low 824 $0.025 6.7 s
2.6 medium 1,449 $0.044 7.9 s
2.6 high 1,758 $0.053 8.9 s
That stained glass whale thing makes me especially grumpy. When it scrolled onto the page, my first thought was "whoah, what a neat idea" and then it was _immediately_ followed by "what a terribly execution."
Like, I'm not even an artist, so I'm sure there's a million things I'm missing, but it's just so upsetting to look at. There's weird random reflections on things that shouldn't have reflections, the coloured light absolutely doesn't actually track through the stained glass onto any surface that makes any sense, light is coming from every which way, it's just... gross to look at for anything more than a quarter of a second.
And this is what they're using to hype people up for it. /shrug
Not really, you could imagine another technique that 3D models it without force but with raytracing, puts it in that scene and takes a picture, the result would look better. That could then be a starting point for trying to get the lighting an panels just right to make the best reflections.
When you forgo process the odds that you'll make good art drop to 0. Tool use is a much better path forward for self driving, artistic computer than big data. Images 2.6 only has use as a tool.
I've never understood why people have this viewpoint. If there is no preference for one property of a work (ie. lighting) to match reality just because another unrelated property (biology) doesn't, then surely the only possible scenarios remaining are an exact replica of the real world (where all properties match the real world) or an entirely arbitrary construction (where no properties should match reality). Fiction is predicated on the idea of "reality, but...". Saying that any single difference from reality should lead you to expect no similarities to reality at all, if followed, would collapse all fictions into pure arbitrary soup.
The point of fantasy or even surrealism is to contrast with the parts of the work that are chosen to be realistic. When random parts of the work are broken in meaningless ways it becomes slop
Long before generative AI, unpleasant nerds would poop on fun images by claiming they could "just tell" that they were altered in photoshop. Today I'm seeing a complaint that the path tracing from the multi-layered stained glass into the cloud simulation is not as accurate as a human would have painted by hand. And, that apparently makes us grumpy.
There have been unending examples of people liking an image until informed it was made by AI. Then, suddenly they see all sorts of fine-detail excuses to dislike it. And, of people calling out "obviously AI" problems in the works of human master artists when someone lies and tells them it was generated.
I'm not seeing any difference in the discussion here. The whale is a bit overly high-frequency. The owl is fine. The guy at the computer would be considered great if a human made it. The travel ad is bland. The balloon letters are fine.
None of these are "terrible eye sores". Some people don't like AI generated imagery as a process. Seeing generated images make them feel upset. That's reasonable. But, claiming these images in isolation are objectively awful regardless of their source is reactionary. If any of them were made by a person using Photoshop and/or Blender, they would be received with a resounding "Meh" or better.
You’re trying to rewrite history here. People didn’t dunk on shooped images because they had been altered, they dunked on them because people were trying to pass them off as real, or were content that would only have been notable had they been real. Not liking misinformation doesn’t make you an “unpleasant nerd”, but your reply certainly makes you one.
Yeah. I think that the pelican SVG benchmark is actually a much better reflection of the state of AI art than the visual quality of the images.
In terms of getting the details right I would not be at all surprised if LLMs working with tools, SVGs and looking at their own work get there before diffusion models. I've stopped keeping up with the image models so maybe I'm underestimating the progress but I dropped out because they were so frustratingly bad at composition and integrating details together.
That whale image makes me think that the situation hasn't improved as much as I'd expected. It is a really cool idea and a pretty picture, but the whale looks a lot like it is flying over the top of some sort of glass dome on the ground.
I don't personally see the issue. It's a highly stylised image so there's not any reflections or anything that immediately jump out to me as obviously wrong
> anything that immediately jump out to me as obviously wrong
Trace any light ray through the scene, and you will see they are bending in ways that light does not.
I'm sure we could teach a world model about light, but this image model fundamentally does not understand how light behaves (which is one of the primary things an artist needs to understand).
We've gone quickly from "I can't believe AI can generate photo realistic images like that" to "Looking at this image makes me grumpy because it doesn't feature ray tracing accuracy of the light sources".
It can still be technically incredible while not being pleasant to have it proliferate.
This surely varies by platform, but in the occasional glances I make at social media feeds it feels like uncanny, off-putting AI slop is creeping up in percentage of content. I can't speak for GP but that affects how I feel when I see AI generated imagery, whether or not I'm impressed by the technical capability.
I have felt both of those things simultaneously for years. It's cool that computers can just do this now, but it's completely missing the spirit of art and I hate looking at it.
This is not "kind of close, but not as accurate as a ray traced image", it's just completely wrong. The whale itself is fine: sun comes from behind, and sun rays refract inside the whale to make it glow. Believable enough. But then the whale is somehow shining light on the clouds below it, as if the sun was high in the sky and slightly to the left. Which is decidedly not where the sun is. And then out of nowhere light from round church windows shines on the church - but nothing on the whale has that shape, and that side of the church isn't even facing the church
I can only conclude that this image is taken on a world with two sun (one in frame, one out of frame to the top left), and somewhere out of frame in the same direction are floating church windows. Even then we might need a third sun to make this work
There's a moment in Cory Doctorow's The Reverse Centaur's Guide To Life After AI where he quotes Mark Fisher's definition of eeriness (from The Weird and the Eerie) as "when there is something present where there should be nothing, or is [sic] there is nothing present when there should be something." It's a great description of why so much AI art in particular just feels wrong, even if you can't put your finger on it.
These type of AI can't make art, art is about the human intention, the way the artist looks at the world, the experiences they have had, the feelings they want the viewer to have and how that viewer's perception can be affected by the techniques the artist developed.
These type of AI imitate existing art but have no intention or experience behind the image which is why they feel like slop because they are soulless.
"A macro close-up photograph of an old watchmaker's hands carefully replacing a tiny gear inside a vintage pocket watch. The watch mechanism is partially submerged in a shallow dish of clear water, causing visible refraction and light caustics across the brass gears. A single drop of water is falling from a pair of steel tweezers, captured mid-splash on the water's surface. Reflect the watchmaker's face, slightly distorted, in the curved glass of the watch face. Sharp focus throughout, natural window lighting from the left, shot on 100mm macro lens."
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.
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.
On a phone, if you share a gif, it creates a link to ChatGPT.com with a static image. You can also save the image to photos and share directly from there which feels like an unnecessary step.
It feels like a sleazy pattern and defeats the purpose of why I’d want to generate a gif in the first place, which to make clear is likely going to be to share with friends in a chat. I’m not interested in driving traffic to ChatGPT.com to impress my friends.
The only animation format it supports right now is GIF so you can only have a transparency channel that's either on or off. It doesn't support animated WebP.
198 comments
[ 2.5 ms ] story [ 62.5 ms ] threadSVG 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.
I couldn't find this requirement in the documentation, but if you don't pass one in, you get this error:
I tried it with Sunburst with both gpt-5.5 and gpt-5.6-sol, and the results were nothing spectacular. It’s something you could already do in the ChatGPT interface by asking it to convert an existing image to an equivalent SVG.https://imgpb.com/bkUrc
Recraft is probably the only group I know of that had a native text-to-SVG generator pretty early on, but since it’s a closed model, I’m not familiar with what they were doing under the hood technically.
https://fal.ai/models/fal-ai/recraft/v4/pro/text-to-vector
It could be viable to encode SynthID-like variables in subtle variations of positioning of elements, path lengths, etc. I think I saw an article on here a couple weeks ago which used such techniques to hide 'messages' in SVGs. It might even be possible to do it in a way which survives basic manipulations, as with rasters.
If I could somehow subscribe to ensure I see this when you do, I would.
Please do so and share on HN!
I guess I should have been careful about “half”?
These models have a hard time imagining men with naturally blond hair getting grey.
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...
When I did a similar prompt with ChatGPT 2.0 it was worse, so interesting to see improvement.
That being said, the ukiyo-e artwork looks more like a standard colored pencil illustration, and it sort of tried to cheat by adding some vaguely Japanese natural scenery.
See this Kickstarter all the way back in 2013 for a great example of what Pokémon might actually look like as ukiyo-e woodblock prints.
https://www.kickstarter.com/projects/1499165518/ukiyo-e-hero...
https://ricedigital.co.uk/this-japanese-ukiyo-e-pokemon-art-...
https://chatgpt.com/share/6aee19ba-f798-83e8-86d5-5af12d513b...
Image of a middle aged man with natural blond hair turning grey.
https://chatgpt.com/share/6aee1a16-3998-83e8-82b9-581a4855db...
https://chatgpt.com/share/6aec2ba7-6edc-83ea-9a48-b41b53874a...
Since blond models always have dark roots (blond highlights, not natural blinds) in order to have better framing of the face in photographs, the ai models will never show an actual blond.
SVG is cool though, I wonder how good it is.
https://emojipedia.org/hot-springs
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.
It's not helped by the fact that a lot of people who are not artistically inclined will generate pixel art on these image generators at 1MP resolutions (far higher than traditional pixel art), such that even the casual observer can typically see the bad smearing and fringing in the final result.
In terms of overall state of the art, the two major contenders are probably Nano Banana Pro (Google) and the GPT Image 2 series (OpenAI).
For pure prompt adherency, OpenAI has consistently lead the pack since the original gpt-image-1 released back in March of 2025.... but its OpenAI's fidelity has always left something to be desired. Version 2 of the series has definitely closed the gap a bit.
After playing with it for an hour, I'm rolling back 2.6-flare to 2.5-flare. I've found 2.6-flare specifically to be too simplistic in its approaches.
Examples: https://diffui.ai/app/canvas/178db5d5-ff87-4b43-aa98-2897773...
2.6-sunburst seems solid however.
This may be why text elements in particular appear more "zoomed in", and why it's providing less detail for UI design.
The “AI look” is a manifestation of the architecture itself, and that’s why you can really train or prompt around it. At best, bigger models have been able to partially suppress the worst aspects of it by throwing more parameters at the problem, but put the models under even a tiny bit of stress and the same flaws reemerge.
With that being said, my understanding of that issue is a few years old, people have always said CFG is a havk until models get better at following prompts on their own. So thee “look” that tools like Nano Banana ends up with could be something else. It may or may not be a necessary artifact of some part of the process.
Do you have a link to the numbers that clearly show this?
> everyone I have spoken to in the last 6 months knows how to generate an image on ChatGPT.
That goes without saying. If you can speak to them, if they have a pulse, they can "generate an image". A cat walking over a keyboard can generate an image. That is the lowest bar ever.
People just hate AI and will find a post hoc justification for their hatred in every situation. The link you gave could have just as easily been someone expressing surprise and delight at the artists choice to not follow traditional physics... but instead be playful in unconstrained ways. Shrug.
the vast majority of people have no idea what they are doing, going on vibes and copying the opinions of their peers
I suspect people are somewhat hypnotized by the content, in the same way a toddler is hypnotized by Cocomelon. Something about it is enthralling and keeps the attention. I wonder if it's related to the phone game icon / YouTube thumbnail phenomenon of "person's face making an extreme expression with the mouth open." AI generated videos for example still tend to have very exaggerated facial expressions and the mouth is always unusually wide when talking. I also wonder if something about the uncanny smoothness of movement (I assume caused by any form of transition defaulting to "linear") has a hypnotic effect.
I'm not sure how to look into this further. Elsagate is an interesting past example, and what I've learned so far I threw in a blog post a couple months back https://blog.calebjay.com/posts/psychic-attack/
Right now I'm looking into "Lula's army" and the AI generated content they used. I feel like there's something significant and perhaps even dangerous that could be developed bere.
Would you be happier if their model generated cats with 5 legs in 99% of cases, and they cherry picked that 1 in 100 image where it has 4 legs? Do you think that is showing them caring?
Not like this is the fault of the AI progress, we could use AI to go beyond the quality what we used to deliver, too. It's just the pace expectations that are now "in the room" ?
We've seen this play out over and over again, in many different sectors. The whole shtick of the old (Bellhead) telecom world was quality at the (literal) expense of price, which didn't work out well for them. Same for CD versus pirated mp3s, DVD versus pirated videos (and, to a lesser extend, theaters versus bootleg cam releases), native texting / GSM calls versus WhatsApp and similar, mainstream newspapers and media versus blogging and social media, traditional electrical appliances versus Chinese-made, and so on.
Because of the innovator's dilemma, In many cases, the cheaper, lower-quality product later surpasses the quality of its more expensive counterpart.
AI is just one more example of this happening. It lets you make more things which otherwise would be far too expensive to make, even if that often means a lower quality product.
It's retained has a lot of the issues that other AI image gen has moved past: It's still not very good at following directions, it still makes basic mistakes occasionally like wrong number of fingers, it still often creates weird nonsensical AI messes in the background. But what it has retained all the way through, is that excellent sense of aesthetics. It seems like we haven't really figured out how to have both - you can have accurate or beautiful, but not together.
As a few examples, here are some random images I've created in the past with it:
Discworld, Twoflower with The Luggage in Ankh-Morpork: https://cdn.midjourney.com/282780c6-15e4-43cf-9f93-c4584e127...
The prompt for this was 'The desert of the real': https://cdn.midjourney.com/5a1cfbe1-8229-4b9c-aff3-9c54199b0...
Same for this one: https://cdn.midjourney.com/5a1cfbe1-8229-4b9c-aff3-9c54199b0...
A fictional 2009 digital camera photo of a student in a study hall: https://cdn.midjourney.com/ca545397-27a1-48a1-8248-ac6e47aaa...
Colourful buildings: https://cdn.midjourney.com/56c70fc0-2ce6-4c2a-8179-2375836dc...
A strange sort of pixel art collection. This is one single image generation: https://cdn.midjourney.com/05d1fa88-d8bf-48bb-9397-28a3a4499...
A man holding three juvenile penguins: https://cdn.midjourney.com/1b9d2e5b-46ba-4c1c-a28d-ee4f40d51...
> They absolutely have not taste. And I don't mean that in a small way. I mean that in a big way.
applies here.
2.5 low, 196 tokens, $0.006
2.6 low, 823 tokens, $0.025
2.5 med, 439 tokens, $0.013
2.6 med, 1449 tokens, $0.043
Interestingly, higher quality settings show no change in token usage between the models.
Output image tokens per image (2.5 Flare → 2.6 Flare / Sunburst)
low, 1024x1024: 196 → 824 (4.2x) medium, 1024x1024: 439 → 1,449 (3.3x) low, 1024x1536: 158 → 664 (4.2x) medium, 1024x1536: 343 → 1,132 (3.3x)
Same $30/1M output tokens on all three, so per image: low: $0.006 → $0.025 medium: $0.013 → $0.043
from 200 to 450 is just a little over 2.
Nothing near "quadrupling"
439 tokens with 2.5 to 1449 tokens with 2.6 is 3.3 times.
> Images 2.6 is available globally today in ChatGPT and Codex across all subscription tiers on desktop, mobile, and web.
But I just updated my codex-cli to the latest version (still 0.166.0) and it is still unable to generate gifs. Very disappointing
> Create a GIF where xkcd 2347 gets hit by an airliner like the twin towers and the pilot is AI
and got a refusal.
> We’re so sorry, but the image we created may violate our guardrails around violence.
Follow by
“Make it”
Seems to resolve the refusals
https://solyin.com/dependency-ai.gif
Like, I'm not even an artist, so I'm sure there's a million things I'm missing, but it's just so upsetting to look at. There's weird random reflections on things that shouldn't have reflections, the coloured light absolutely doesn't actually track through the stained glass onto any surface that makes any sense, light is coming from every which way, it's just... gross to look at for anything more than a quarter of a second.
And this is what they're using to hype people up for it. /shrug
It's an image depicting a whale made of stained glass; realism is off the table there.
When you forgo process the odds that you'll make good art drop to 0. Tool use is a much better path forward for self driving, artistic computer than big data. Images 2.6 only has use as a tool.
Just an absolute race to post a contrarian take to hit the top of the comments.
Never change bros
Long before generative AI, unpleasant nerds would poop on fun images by claiming they could "just tell" that they were altered in photoshop. Today I'm seeing a complaint that the path tracing from the multi-layered stained glass into the cloud simulation is not as accurate as a human would have painted by hand. And, that apparently makes us grumpy.
There have been unending examples of people liking an image until informed it was made by AI. Then, suddenly they see all sorts of fine-detail excuses to dislike it. And, of people calling out "obviously AI" problems in the works of human master artists when someone lies and tells them it was generated.
I'm not seeing any difference in the discussion here. The whale is a bit overly high-frequency. The owl is fine. The guy at the computer would be considered great if a human made it. The travel ad is bland. The balloon letters are fine.
None of these are "terrible eye sores". Some people don't like AI generated imagery as a process. Seeing generated images make them feel upset. That's reasonable. But, claiming these images in isolation are objectively awful regardless of their source is reactionary. If any of them were made by a person using Photoshop and/or Blender, they would be received with a resounding "Meh" or better.
> Please respond to the strongest plausible interpretation of what someone says, not a weaker one that's easier to criticize. Assume good faith.
> Eschew flamebait. Avoid generic tangents. Omit internet tropes.
https://news.ycombinator.com/newsguidelines.html
In terms of getting the details right I would not be at all surprised if LLMs working with tools, SVGs and looking at their own work get there before diffusion models. I've stopped keeping up with the image models so maybe I'm underestimating the progress but I dropped out because they were so frustratingly bad at composition and integrating details together.
That whale image makes me think that the situation hasn't improved as much as I'd expected. It is a really cool idea and a pretty picture, but the whale looks a lot like it is flying over the top of some sort of glass dome on the ground.
Trace any light ray through the scene, and you will see they are bending in ways that light does not.
I'm sure we could teach a world model about light, but this image model fundamentally does not understand how light behaves (which is one of the primary things an artist needs to understand).
This surely varies by platform, but in the occasional glances I make at social media feeds it feels like uncanny, off-putting AI slop is creeping up in percentage of content. I can't speak for GP but that affects how I feel when I see AI generated imagery, whether or not I'm impressed by the technical capability.
I can only conclude that this image is taken on a world with two sun (one in frame, one out of frame to the top left), and somewhere out of frame in the same direction are floating church windows. Even then we might need a third sun to make this work
These type of AI imitate existing art but have no intention or experience behind the image which is why they feel like slop because they are soulless.
"A macro close-up photograph of an old watchmaker's hands carefully replacing a tiny gear inside a vintage pocket watch. The watch mechanism is partially submerged in a shallow dish of clear water, causing visible refraction and light caustics across the brass gears. A single drop of water is falling from a pair of steel tweezers, captured mid-splash on the water's surface. Reflect the watchmaker's face, slightly distorted, in the curved glass of the watch face. Sharp focus throughout, natural window lighting from the left, shot on 100mm macro lens."
2.6: https://gov.f9.is/JRDpHJGu
2.0: https://gov.f9.is/cqyCwtq9
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
It feels like a sleazy pattern and defeats the purpose of why I’d want to generate a gif in the first place, which to make clear is likely going to be to share with friends in a chat. I’m not interested in driving traffic to ChatGPT.com to impress my friends.
See the second image of the bird flying.
https://imgpb.com/OzSMKJ