Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

  • Hacker News
  • Still can't make sprite sheets :(
  • Interesting. I'm surprised they haven't prioritised/deliberately trained for this more because of how useful it is to ask codex to generate some images/assets/sprites when building sill games. It would dramatically enhance how polished it's games were.

    That said for single images the old model was already okayish for prototypes

  • No but it can write a tool that can.
  • It's better to use a specialized model for that https://retrodiffusion.ai
  • Shameless plug, but I built an image generation app with tools for sprite sheet and cutting out the sprites automatically.

    Added support for GPT 2.5

    http://batchbanana.com/

  • >"Still can't make sprite sheets :("

    The key is making them one frame at a time, rather than asking for the whole sheet. Adherence frame-to-frame with a reference image is really good, so just prompt with the previous + direction. I finally got Nano Banana to make fairly decent fluid animations that way.

  • You can get semi-decent sprite work out of GenAI models, but you still have to put in some manual work (scale normalization, palette reduction, grid alignments, etc). It's definitely not "out-of-the-box" yet.

    https://mordenstar.com/other/hobbes-animation

  • 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.

  • As a software user, I feel just as frustrated and disappointed when I look at a projects website, code, and commit history and it’s slop, why in the world would I use this garbage when I can just prompt my model to make my own?

    Realize the people using this to make slop menus and book covers feel the same way, wow this is useful and saves me so much time/money!

  • I am building an app and I need illustrations. Hiring someone is out of the question.

    Previously, I would either not have illustrations or try to fit a stock image to my use case.

    Now I can just generate illustrations that fit my use case well, and it takes very little effort.

    Mine is just one out of thousands of conceivable use cases for image generation and editing. I appreciate that this capability is now available to everyone.

  • I'm a solo coder. I love coding. Never used (or trusted) AI to generate code, only to review.

    But good art and especially animation, beyond basic UI and logos, is a full-time commitment that requires giving up coding while you're working on the visuals (yes many great solo devs did their own art, but I prefer using the extra time on other shit, like making music and getting on with life)

    Getting a good meat-based artist to hop on my Awesome Game Idea #458235 is easier if I can show them a running gameplay example, so they can see what the actual game will be like.

    Up until recently I was just using free third-party asset packs like Kenney's: https://kenney.nl/assets/1-bit-pack

    That works well but carries a risk of "painting yourself into a corner"; the longer you test a game in a particular art style (or music) the more you subconsciously tend to develop the rest of the game around that style! At least for me

    AI-generated PLACEHOLDER art lets me iterate on a game closer to how I envision the final product to look like, right from Day 1.

    I'd still hire/kidnap an actual artist before publishing.

  • AI art is making me realise that through my whole artistic career, the reason it's so hard to convince people that they need good design is because no one really appreciates good art and design other than people who have studied art and design.
  • Great idea, get an AI art tattoo so you can always be reminded how AI art looked in 2026.
  • Lots of people have tattoos of what cutting edge video game graphics looked like in 1992.
  • 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.
  • It hit me just now that people might actually getting tattooed with AI slop. That’s… depressing
  • 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.
  • I just saw a Twitter thread of someone calling out realtors with absolutely egregious editing examples. Think pools and landscaping being added to backyards, a background being changed to a mountainous region, and furniture being “staged” in an attic space that definitely couldn’t fit that furniture.

    A realtor in the comments said they legally need to also post the same images but unedited, but I’m sure when you’re doing this the first 50 are the edited ones and the last 50 are the unedited. How many people make it to the unedited?

  • 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.
  • 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.

  • > 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"?

    What else could they highlight? The other major use case for these models for normal people (generating NSFW images) is explicitly blocked by them.

  • If someone shows me a picture of a haircut, or a dress and asked me if it would look good on them, I can't imagine it. My mind does not work like that. I just can't visually see it.
  • > 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 think this is because recently there has been extreme backlash to this sort of thing.

  • I think you've picked the most cynical interpretation for each one. More charitably, you could say:

    - Ideate on things you can build for your fish tank

    - Iterate quickly on ideas for a tattoo

    - Get inspiration for a new metalworking (or 3D printing?) project

    - Get a sense for what a new haircut might look like, before you commit

    - Iterate on arrangements for a bouquet of flowers

    - Do silly things with childhood photos

    - Do silly things with pet photos

    - Clean up low-res, damaged, or weirdly formatted photos

    - Do some creative storytelling with your long-distance friends

    - Okay yeah fine they should just make the damn bed, but I can imagine small tweaks being useful for staging a home (easy to abuse though)

  • 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)

  • I mean there's literally one of their example images with hands with the wrong number of fingers.
  • > Many people still think AI images output the wrong number of fingers on a regular basis.

    Last time I used a frontier image model it made me a seal with three hands so…

  • > Many people still think AI images output the wrong number of fingers on a regular basis.

    There's literally an image of a dude with 3 fingers in the Composite Party Photo.

    by yawn
  • 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.
  • The guy’s arm is also extremely long.
    by nojs