[HN Gopher] Show HN: AI game animation sprite generator
___________________________________________________________________
Show HN: AI game animation sprite generator
I tried to build AI game animation generator last year (
https://news.ycombinator.com/item?id=40395221), a lot of people
were interested, but it failed, mainly because the technology was
not good enough. 1 year passed, there were a lot of developments
in video/image generation. I tried it again, I think it works super
well now. Actually beyond my expectation. You can generate all
kinds of game character animation sprites with only 1 image. 1,
upload your image of your character 2, choose the action you want
3, generate! Support basic actions like Run, Jump, Punch and
complicated ones like: Shoryuken, Spinning kick, etc. High quality
sprite sheet will be directly generated to use in Unity and any
game engine. If you are an indie game developer, you don't need to
high an artist or animator to develop you game. For studios, it's
10x cost saving and 10x efficiency as no more creating animations
for 100 NPCs 100 times. Please check it out, looking forward to
your feedback!
Author : lyogavin
Score : 133 points
Date : 2025-06-06 19:30 UTC (1 days ago)
(HTM) web link (www.godmodeai.cloud)
(TXT) w3m dump (www.godmodeai.cloud)
| doublerabbit wrote:
| The privacy pages and legal pages don't link. They all return to
| the homepage.
|
| Without them I am hesitant in uploading my concept art from my
| project for testing.
|
| Otherwise it is a cool concept and I would potentially look in to
| if it turns out you don't go all evil villain and claim ownership
| over the sprites.
|
| Enabling a preview set of sprites without having an account would
| do no harm neither.
|
| But creating an account without any legal documentation is a no
| from me as I don't know whats happening with my IP which leaves
| me uncomfortable.
|
| Even if it's not a ratified legal document; some draft is better
| than nothing.
| lyogavin wrote:
| sorry, just fixed it.
| WithinReason wrote:
| Hope someone makes a celebrity Mortal Kombat game from this:
| https://www.youtube.com/watch?v=DjYfFDvtZ5s
| 9283409232 wrote:
| It's cool but you can tell the sprites are low quality and AI
| generated. They have that trademark AI "fuzziness." It's possible
| that players would think it is a design choice but it is
| noticable.
| lyogavin wrote:
| will add a quality upscale model to fix it. thanks.
| iandanforth wrote:
| All AI tools I've tried have failed to generate animations for
| slimes in my experiments. (Including Veo3) I'm hesitant to even
| try this, any chance it would work?
| kevingadd wrote:
| You're going to have a much harder time getting good animations
| generated for something that isn't a humanoid, since the
| training sets won't have much to work from. It's possible with
| a really good prompt for 'slime' you could get something but
| this doesn't seem to allow prompt customization.
|
| If you're after monsters like slimes I would not drop money on
| this.
| Madmallard wrote:
| Lol it's not functional for most things.
|
| I uploaded a photo of a pixel art electrician and it just
| completely ruins it and looks nothing like my guy and forces
| it into a particular style where it looks like a cheap mobile
| game playable ad and somehow Mario at the same time. Not to
| mention, the actual animation is wrong too.
| Aeolun wrote:
| I really want to see an example with a slime. I'm sure it'd
| butcher it, but it would be _so_ funny.
| educasean wrote:
| The example sprites aren't loading for me. I see original panda
| and the female ninja graphics, but the 6 sprite boxes are empty.
| lyogavin wrote:
| thanks for letting me know. I'll put some CDN to the videos.
| huhtenberg wrote:
| Curious idea, but doesn't seem to working for me. It's been
| sitting in "Your job is in queue" state for 10 minutes, and
| that's it. Reloaded the page just now and it just reset itself.
| lyogavin wrote:
| sorry, I didn't expect so many requests all queued up too long.
| I've added some servers it should start to process.
|
| When your request finish it'll send you an email notification.
| genewitch wrote:
| Three things are known. Slashdot and HN effect and the
| gervais effect.
|
| Don't really get the mean-spirited comments. Not everyone has
| the means to exascale their project.
| mclau157 wrote:
| really the space for 16x16 sprites with AI has not been done very
| well so far
| Dwedit wrote:
| miaomiaoPixel_v11 can generate sprites that small. Specify a
| size of 128x128, and that corresponds to an actual size of
| 16x16. Use an image editor to shrink the sprite down to 16x16,
| then reduce the palette as needed to remove the near-matching
| colors.
|
| 16x24 sprites end up looking a lot nicer though.
| elpocko wrote:
| What model(s) does this use? Is it built using open source models
| and tools? I couldn't find any mention of models in the FAQ (who
| even asked those questions?) or elsewhere. I doubt you trained
| your own diffusion model.
|
| The GitHub cat in the footer does not link to GitHub either.
| DrSiemer wrote:
| Settings page does not work. Profile page does not work. I've
| been waiting for my first test for 30 minutes now. Not a great
| first impression...
| lyogavin wrote:
| fixed setting and profile.
|
| sorry for the long waiting, I didn't thought there would be so
| many requests. Added more powerful GPUs.
| ofjcihen wrote:
| You wouldn't happen to have vibe coded this would you? I can't
| get a response from multiple pages.
| doctorpangloss wrote:
| There is a lot of negativity on Hacker News.
|
| Staying focused: the panda is wearing gloves, but then when it
| does the Hadouken and the Hurrican Kicks, it loses the gloves.
|
| Bigger picture this seems like a focus on product stuff like
| pricing and demos and navbars that don't really matter to artists
| or game developers. Your feelings are correct that people here -
| the root motivation of the negativity - are questioning your
| sincerity. With AI art this is acutely true, people don't view AI
| art as a sincere art endeavor. I don't doubt your sincerity. But
| spending more time on the art thing, and making it free or open
| source, it's going to look and feel more authentic.
| themanmaran wrote:
| I think the negativity is overkill.
|
| I've been toying around with the exact same idea the last
| couple weeks. It's mostly GPT 4o image => some image cleanup,
| but honestly a lot more finicky than I originally expected.
| Lots of prompt engineering. So OP probably put in a fair bit of
| effort here.
|
| Also each animation probably costs $1-$2 in GPT costs to make
| [1], so not something that's easy to throw a free tier on.
|
| [1]
| https://openai.com/api/pricing/#:~:text=Image%20Generation%2...
| highway900 wrote:
| > This isn't putting anyone out of work. The games simply would
| not be made in the first place.
|
| The opposite is also true. Games that should never be made are
| being made due to the rubbish that can be generated by these
| tools. Observe the generated samples on the landing page, they
| are literally just copying street fighter. These tools are so
| useless without ripping off the hard work of humans. The deluge
| of slop is a signal to noise problem.
| imatworkyo wrote:
| This is awesome, good luck with this tool. Can it do isometric
| and top down views?
| lyogavin wrote:
| working on adding those
| bitwize wrote:
| Hand-drawn animation, whether for video games or television or
| other media, is one of those artistic fields where I can see AI
| being a huge win for everybody. The reason why is because drawing
| the in-betweens in an animation is tedious, time-consuming,
| costly, and, in most 2D animation productions, outsourced to
| sweatshops abroad. And yet it's _most_ of the work that goes into
| an animation. I think most animators would rather just do the
| keyframes and leave the tweens in the hands of the machine. It 'd
| make traditional animation as easy and fast as Flash animation,
| and create a flourishment of even more indie animations from solo
| creators with even higher quality.
| spacechild1 wrote:
| Adobe has been working on some real cool stuff like this. IMO,
| AI should be a tool to support the creative process, and not to
| replace it.
| imetatroll wrote:
| I would like to know what sort of AI is trained to do this.
| banner520 wrote:
| I operated for 30 minutes, but it didn't achieve the result I
| wanted
| lyogavin wrote:
| sorry, there were way too more requests than the compute power
| i prepared for. New GPUs are added. you can give it a try
| Madmallard wrote:
| I'm surprised posts like this aren't instantaneously flagged and
| removed. The tools for doing this are readily available for free
| as it is.
|
| This is basically another "throw AI in it" CRUD app that wants
| your money. They're all really low effort grifts that do not
| deserve to see the light of day.
|
| They work for a subset of animations that go in commonplace game
| types. Anything creative or new or different? No chance you'll
| get a satisfactory result. They are all subtly wrong in ways that
| anyone can easily spot and will likely get your game filtered out
| and harshly criticized publically on Steam or other platforms.
|
| This right here too is so egregious:
| https://www.godmodeai.cloud/plans
| bigcat12345678 wrote:
| Hmm The payment link does not require login And I paid and the
| credits vanished into thin air ...
|
| To the poster, please find the customer service to fix
|
| https://buy.stripe.com/cNicN59Bqf6K4q92Qrbwk00?prefilled_ema...
|
| Also, I cannot find my queuing job after closing the page.
| lyogavin wrote:
| checking
| lyogavin wrote:
| sorry for the inconvenience.
|
| I've fixed it.
|
| ALso given your account 2x more credits.
| taytus wrote:
| Shouldn't it be more like 5x credits? That's what I would
| have given to a paying early adopter dealing with these
| annoying issues.
| menzoic wrote:
| Calm down it's a 1 person company. The entitlement is over
| the top
| thrance wrote:
| The samples on the landing page are... not good, by any metric.
| The background jitters, details go missing from frame to frame,
| and the animations that should cycle (run, walk...) don't look
| like they do.
|
| This is a prototype, at best. I would be ashamed of asking money
| for providing such a sloppy service.
|
| Also, in your faq you have "You own the rights to your generated
| content.", which I don't think is true. AFAIK, you can't
| copyright AI art.
| palmfacehn wrote:
| Great progress. Bookmarked.
|
| For purposes of generative worlds, I have an additional
| requirement for interchangable equipment and weapons. I.e. a
| single sword or armor sprite should fit with all humanoid
| characters, in all animations. I suspect this could be achieved
| by training against "clipping" tests.
|
| As a start, there should be projections for all four cardinal
| directions.
|
| Limit the output to palettes of a given size, for classic
| recolors via GL shaders.
| lyogavin wrote:
| Thanks for so many valuable points and ideas. Will do.
|
| I like the "interchangable equipment and weapons." idea, very
| cool. And yes. it's doable. many ways possible could work. I'll
| experiment.
| okkdev wrote:
| I hate this. It's cool that it's possible, but I hate it.
| Generating art solves no real problem and only suppresses a
| struggling profession without which this wouldn't even be
| possible...
| makerofthings wrote:
| Have to agree. I don't think we should stop ai progress, just
| that I think we built a bad thing along the way. I will never
| buy a video game that I know has ai generated content, I want
| to see some art, not a soulless prediction of what art might
| look like.
| petesergeant wrote:
| > I will never
|
| Bet you $10 that in five years' time you will have.
| makerofthings wrote:
| It's not really practical but I would take the bet that I
| will never /intentionally/ buy a game with AI generated
| assets. I just don't see that AI generated art has any
| value to it. I'm sure you could sneak some past me, it's
| getting harder to spot all the time.
| petesergeant wrote:
| My guess is that in five years' time there won't be any
| games that don't include any, and also people will really
| have stopped caring so much
| miohtama wrote:
| The problem is that in the indie game market, where most 2d
| sprites are drawn, there is not enough money going around
| making many studios profitable. By reducing cost of manual 2d
| animation, more studios can be profitable and able to deliver
| better, more finished, games. Then studios can pay decent
| salaries to employees.
| yreg wrote:
| > Generating art solves no real problem
|
| It definitely does solve a problem. This tool provides
| affordable custom sprites with fast delivery.
|
| If it didn't solve any problem there would be zero demand for
| it and no reason for you to care about it.
| Aeolun wrote:
| I think the problem is that the profession is struggling
| because you pay a lot of money for work that is often of very
| dubious quality.
|
| I can't ask a anyone that claims to be a pixel artist for
| sprites because the chance of getting garbage is just too high.
|
| Btw, if anyone does know someone good, I'm open to paying xD
| graynk wrote:
| > solves no real problem
|
| this is very obviously not true.
| Minor49er wrote:
| I guess we should also delete Stack Overflow while we're at it
| because programmers should write everything from scratch for
| the same reason
| Cloudef wrote:
| Not sure about professional quality. All the results seem to need
| quite bit of hand editing to look good. Also the examples only
| show animations ripped from street fighter.
| sambeau wrote:
| This is so depressing.
|
| Also, why does the female ninja suddenly grow a penis?
| nkrisc wrote:
| It's sad how the existing corpus of artists' works are being used
| against them.
|
| The only reason this can generate images like these is because
| artists previously created artwork like this. And then in return
| they get:
|
| > you don't need to high an artist or animator to develop you
| game.
|
| Unless you created all the training material yourself, any model
| like this is highly unethical, in my opinion.
| Aeolun wrote:
| Unless you didn't want people to see and use it, maybe you
| shouldn't have made it public? I don't think training AI is
| fundamentally different from humans learning from things they
| see, and we don't restrict that either.
| wrasee wrote:
| The fundamental difference is that computers can do this at a
| pace and scale that humans could never aspire to. There is a
| natural limit to the extent a single individual can be
| informed by previous works. It sets a natural pace to
| innovation that is sustainable for both the artist and
| derivative works.
|
| Computers have no such limitation and can consume almost the
| entirety of a subject's work in a few weeks or months. I
| think that alone is enough to say that yes, it is
| fundamentally different.
| jason_oster wrote:
| Automated assembly lines have the same properties. Same
| with transportation. Buses, trains, airplanes, ships. These
| all work tirelessly at a pace that humans cannot match.
|
| There is no fundamental difference.
| wrasee wrote:
| I think you missed the point. The claim is that AI
| training from public information is no different from
| humans learning from public information.
|
| My argument is precisely that the mechanisation of
| information is fundamentally different from the scale at
| which a human can learn. One immediate consequence being
| there is no longer a natural brake on the scale of what
| can be sourced for use in a derivative work.
|
| To be clear this is not a value judgement, just to point
| out that it _is_ different, just as driving is
| fundamentally different from what one can do with one's
| own feet. Of course the mechanisation of transport is
| history and seems daft to argue against. But it is
| different. Whether that's good or bad is a much harder
| question.
| bnop wrote:
| 1. These models have been trained on private data many a time
| without permission
|
| 2. Making something public isn't always a choice made by the
| creator
|
| 3. Making something public does not denote fair use, this is
| why copyright (albeit arguably a poor solution) exists
|
| 4. These LLMs consolidate wealth into a small group using
| outputs from a larger, often less wealthy group (creatives)
| without fair compensation
| dr_dshiv wrote:
| These LLMs primarily distribute intellectual and creative
| wealth from media conglomerates to anyone on earth with
| $20. (Without fair compensation, agreed)
| fourside wrote:
| When it's big copyright holders we have very specific, very
| granular definitions of what constitutes fair or allowed use.
| But when it comes to smaller creators the answer is that it's
| their fault for trying to promote their work and make a
| living.
| nkrisc wrote:
| AI isn't human.
| Lerc wrote:
| This is true, but not an argument in itself.
|
| AI is also not American, A puppy, or a cardboard box full
| of fairies.
|
| Your underlying presumption is that there is some property
| of Humans that makes the distinction important. Without
| identifying that property it impossible to evaluate the
| merit of any claim about it.
| archerx wrote:
| As someone who is an artist and also a programmer I find the
| differences between both very different. I never see
| programmers crying over A.I. chiming "they stole our code so
| it's evil and I'll never use it and neither should you!" Like
| the artist seem to do.
|
| I don't really care if the image gen models are trained on my
| renders or photos as long as they are open source.
|
| Also I have been making the assets for my game which needs at
| least 2,000 sprites and honestly it's very tedious and I'm
| looking to automate as much of the pipeline as I can so I
| welcome anything that removes the the tedium and pain from the
| process.
| davidweatherall wrote:
| I think there's a big difference with how designers and
| programmers can use AI to enhance their work, and how
| exploited the average person's work has been. A lot of
| designers publish their work on social media, or it's visible
| on their websites etc., which AI models have used to train
| with. But with coding, most people's code only exists in
| private repos, or is compiled to a format that LLMs cant
| easily be trained on.
| archerx wrote:
| There is so much code on github and all the other repos
| that it can compare with the amount of art that is out
| there. Also all of your Javascript code is public once your
| site is published.
|
| There is nothing stopping artists from using A.I. to
| improve their work. The sketch to image work flows are
| great, the variation work flows can save from the tedium
| and inpainting can help fix and improve images.
|
| Text to image is lazy and is the cause of most of the slop
| but no one is saying artist should replace their Wacom
| tablets with text prompts. I feel like there is a lot of
| hurt egos going on. I remember back in the day on CGtalk,
| there was so much elitism and in hindsight it probably held
| a lot of people back, myself included.
| nkrisc wrote:
| I'm not opposed to generative AI, in principle, it's how it's
| being employed that bothers me.
| archerx wrote:
| Please elaborate.
| davidclark wrote:
| From a recent blog shared on HN, among a list of reasons they
| can't or won't use LLMs:
|
| >The training data for LLMs is stolen. I don't mean like
| "pirated" in the sense where someone illicitly shares a copy
| they obtained legitimately; I mean their scrapers are
| ignoring both norms and laws to obtain copies under false
| pretenses, destroying other people's infrastructure.
| [footnotes omitted]
|
| "I think I'm done thinking about GenAI for now"
| https://news.ycombinator.com/item?id=44193018
| archerx wrote:
| I do agree that the scraping is annoying and I had to set
| up some anti scraping measures on one of my image heavy
| sites. However I am for the freedom of data especially if
| the models are open source. I only use local models and
| haven't used Claude or ChatGPT since last year and it's
| pretty awesome.
| asddubs wrote:
| people did complain about it stealing GPL code scraped off
| github etc and then license laundering a lot, especially
| during the earlier days. I think now people are just worn
| down to have the conversation again.
|
| I do also think the threat is bigger to artists. Sloppy code
| will cause problems, and at some point you'll need someone
| who knows what's going on to step in. Sloppy art, a lot of
| people accept.
| bandoti wrote:
| I'm not sure over time people will continue to accept
| sloppy art.
|
| The "glitchiness" of the AI sprites can be quite unsettling
| because one can feel the something-quite-wrong that is
| difficult to place.
|
| This is a worse state than using even rough illustrations
| by actual artists.
|
| If one must use AI for this I would recommend having an
| artist in the pipeline who uses AI to create assets but
| then makes sure they are seamless.
| archerx wrote:
| That's why artist should incorporate gen ai into their
| workflows. They have the artistic eye and separate the slop
| from the gold better than non artistic people. Also knowing
| composition and etc helps getting better results from
| Stable Diffusion, Flux and etc.
|
| I remember when 3D CG was new and it got so much hate for
| not being "real art". I heard the same drama happened when
| Photoshop and Illustrator hit the market, they weren't
| considered "real art".
| akritrime wrote:
| Imagine if writers complained that stuff they wrote were being
| used in literature classes that teaches people how to read and
| write because how sentences they once toiled over for hours
| would now be used in mundane letters.
|
| AI can't take away an artists creativity, just like how
| photography didn't kill painting. Yes, it closes up certain
| avenues on how artists make money but it will most probably
| make up for that by making them more productive.
| Draiken wrote:
| Comparing teaching other humans to "teaching" a model is
| absurd.
|
| AI can't take their creativity but it will take their means
| of survival so a few companies can profit instead. Yeah,
| great trade-off.
| akritrime wrote:
| The point isn't about comparing teaching and training. The
| point is about how humans use tool to improve and advance.
| It is more about comparing AI to books as an aggregate of
| knowledge. Just like how humans uses recorded writing in
| the form of books to analyze and adapt better ways of
| communication, humans can also use AI to be productive in
| fields that was previous out of their reach.
| Lerc wrote:
| >Comparing teaching other humans to "teaching" a model is
| absurd.
|
| Bold conclusion, but why is it absurd?
|
| New ways of making thinks has always had an impact on the
| old ways of making things. Are you proposing we should seek
| no new ways of making things? I have been described as a
| creative person by some. The notion of restricting what
| people can make and how they can make them does not gel
| with my idea of creativity.
|
| I am sympathetic to those who might have their source of
| income affected. That is not a problem with the current
| change, it has been a problem with all change throughout
| history. If the welfare of people is really your concern
| then your issue is not with the change but how society
| supports people effected by that change.
| user____name wrote:
| > Yes, it closes up certain avenues on how artists make money
| but it will most probably make up for that by making them
| more productive.
|
| How?
| akritrime wrote:
| In a few years as image generation consistency improves,
| any video game artist can go from just creating characters
| for some other game dev to creating full-on animated
| sprites directly. Instead of having to depend on someone
| else to code their ideas, they can directly create that
| game. And the inverse will also be true, game devs can use
| AI to create generic arts for their game and work faster,
| create games that depends more on tech than art. Both
| flavors of games will bring something unique and doesn't
| invalidate the work of the other as useless.
| snackbroken wrote:
| It's already happening in the movie industry. Things like
| painstakingly hand-tracking an actor's face onto a body
| double vs using deepfake face replacement. A single vfx
| artist can now do this work much more quickly, pushing down
| the cost to do it. This in turn opens up new opportunities
| for work which were previously not economically viable,
| like splicing in retakes or making mouth movements match
| the voiceover dialogue.
| bayarearefugee wrote:
| Even as someone who leans generally anti-corp I would love to
| see Capcom come in and sue over this since there's no way to
| look at those demo animations and not see the "training" was
| entirely lifted from the Street Fighter series.
| brookst wrote:
| Can you point me to these artists who created new work out of
| nothing, without learning from other art themselves? Because
| every artist I know has worked hard and learned from what's
| gone before.
| MasterScrat wrote:
| Congrats on shipping!
|
| I'd love to hear a bit about the ML side of things: what was your
| experience with various models? Do you see a clear cost vs
| quality tradeoff with current state of the art models? How do
| open vs closed models compare?
| zoba wrote:
| I'm curious if you know of a similar tool for generating tilesets
| for top down RPG like games? I've tried Midjourney, which makes
| nice art, but it can't be used in a game.
| lyogavin wrote:
| we'll add top down, isometric and other views
| nurettin wrote:
| It kind of does what it says on the can, but you will have to
| edit the result frame by frame in order to make the lost scales
| and equipment consistent across all animations. Still, a huge
| time boost.
| akritrime wrote:
| Is this using OpenAI's GPT-image or something different?
___________________________________________________________________
(page generated 2025-06-07 23:01 UTC)