It's weird how consistent the 'ai art style' is for each medium. You really only need a glance at the right frame in these to know immediately. (https://www.aventos.dev/our-work) Not looking for errors or anything, just style. The ramen one is markedly subtler about it than the others at least. I always assumed this was due to people using 'default' styling by not specifying anything in particular, but these people claim to have a pretty in-depth process that presumably would nudge away from that. When I look at old pictures of dall-e 2 or midjourney v3, the hands are all mangled and stuff, but they're not in the 'ai style'.
The end result[1] looks quite impressive! The animation feels like it's quite high quality--very smooth. However, some things seem off: bad lip sync, minor animation errors, discontinuous scene-to-scene feel. Given that these are supposed to be their best examples, meant as advertisements, I would guess these errors are hard to fix using only the models.
So my verdict is that AI-only anime is still not there yet (although it would be cool to have a world where one dedicated and talented artist could make a high quality anime). But at the same time, anime studios will probably start incorporating AI into their workflow, getting high-quality-looking scenes for very cheap.
As the quality of each scene might someday surpass the budget of entire shows, anime can be infinitely more animated and creating something new in the process. What would a “multi-billion-dollar” episode look like? Hope we find out soon. Exciting times.
I have to admit that people interpreting current affairs/hot moments in real life through the lens of anime tropes really tickles in a way I never believed possible.
The aha moment was when people made ones over the Pam Bondi DOW over 50k meme but the recent World Cup ones have been very amusing too
> One, fans here actually get to make anime in the US. Instead of needing to fly to Japan, speak Japanese, and preferably be Japanese to break into the industry.
Does this come off as wildly tone deaf to anybody else? "We love your product and what you do, but could we get it without associating with or paying you in any way?"
> ...Smaller and faster means more financially feasible so we can give better wages for artists and enable a new industry to thrive in the US.
I've been in Asia this week, speaking to artists and creators. The traditional systems do create challenges, but this just sounds like a U.S. AI-based company giving itself carte blanche to steal the cultural output of another country, wrap it up in and American style business, and eventually push existing artists or long standing studios out of the space.
No, I don't think I want a smaller team of artists and animation professionals doing art and animation. That feels like a very sloppy outlook to me.
[Edit: While I'm sure the process is interesting for some, the introduction especially just leaves me wondering who thought this writing sounded good? Maybe the target market for this is AI investors or people who aren't actually interested in the artistic part of things, and that's why I find it such a turn-off.
E.g. "We could license good music," implying their music is bad? Maybe it would be less jarring if they didn't specifically call out the importance of writing?]
What I love about this post showing is that it admits up front that the quality of a given entertainment medium is in the writing.
Staff writers are not respected and treated as less than in Hollywood.
Yet the classics of any given medium have emotionally resonating entertainment medium have unique or paradigm-shifting results on audiences, and the medium itself (novel, comic book, TV show, miniseries, film, video game) has influence, but ultimately, it's the writing that is the single most important element of an entertainment IP's value.
An entertainment product that makes you feel emotions beyond boredom is doing its job. True crime/horror bring emotions of fear, mystery, and danger. Sci-Fi/Fantasy bring wonder, curiosity, and discovery, with genre-specific forms of each of those emotions. Mysteries and thrillers bring, well, mysteries and thrills.
So a slice of life AI anime, if it can properly portray from its writing a sense of growing mutual trust, awkwardness of growing up, combined with hope for a better tomorrow, it will have done its job as an entertainment product.
I'm procrastinating working on a fantasy novel which I started in 2012 and need to finish it. It has to hold up in today's neon flashing lights tiktok world as a book. But then there's no reason I couldn't use AI tools to direct adaptations of the source material to an anime or manga or TV show or web series.
Do I wish I could hire and pay and create an anime with a dedicated studio of practitioners who are pros and passionate about the medium beyond my wildest dreams? Sure! Is that likely to happen in 100 million lifetimes? Nope! So if I want to have my IP appear as an anime or TV show, my only realistic option with my one life on earth would be to try to do a similar process to how this animation studio works.
Bravo for them for advancing the medium for this, to find what works and what doesn't. Maybe some day if I will just finish my actual novel and get it eviscerated, after I've figured out how much it will take to pay Michael Kramer and Kate Reading to do an audiobook for it, I can find wild business success such that I could commission an anime series for the IP as my creative vision directs, and have humans do the interesting parts, and let the AIs do the boring inbetweens and tedium work.
But until then, I'll be keeping an eye on aventos to see where they go with this potential.
I have seen a few samples of AI anime, and it is impressive how far the technology has come; the only thing that really stands out are the cuts every few seconds, because video generation currently can't produce anything longer. However it's definitely enough to tell a story, particularly one that's nearly 100% fast-paced fighting scenes.
Honestly these look pretty good, I think run-of-the-mill anime is a strong target since it's highly formulaic and one of the more stylistically derivative genres.
I don't think this tech is quite "full length movie" watchable yet (maybe other uses), but seems only a matter of time where it would be "good enough" for common use.
I wonder if it would be better to work on models thst can produce the 3D scenes in Blender that can be rendered to an anime style. That technique is already common, but if you could get AI to generate it in that format you could more easily ammend issues in the output or more easily add artistic direction, detail and the human touch.
> [we did this so anime production companies would] pay the employees(artists) better
I mean, has pay gone up in other fields where AI has taken over a lot of jobs?
In any case, I think the reason pay is awful in anime is the same reason as in gamedev: if people get into it for passion, the companies can pay less and still have employees.
> I think the reason pay is awful in anime is the same reason as in gamedev: if people get into it for passion, the companies can pay less and still have employees
Partially, but also outsourcing. First it was South Korea, then China, and now Vietnam and India.
Toei Animation's (Dragon Ball, One Piece, Sailor Moon, Mononoke) VISION 2030 [0] is interesting if you want to deep dive into how the industry is thinking medium-to-long terms
> has pay gone up in other fields where AI has taken over a lot of job
dunno, I've seen worse and some of the scenes if you asked me if it was AI or not I probably couldn't tell you. most egregious thing I saw was at the 27 second mark where the girl is inside the table.
At the current level of tech it feels like it would be a pretty dull full length Anime, and hard to squeeze all the bugs out but for something shorter like a commercial or FMVs for like a video game seems good enough.
0:19 - the bowl has soup in it, despite coming from the middle of the stack.
0:19 - [same time] several bowls are just sloppified, e.g., having two bottoms
0:45 - last of the soup phases out the bottom of the bowl
Continuity errors with the smock. (Is there a logo on the pocket, or no? Does it have a pocket?)
("How Asians Pay for the Bill" … what a title)
0:29 - a water drop drops off the ice cube and falls to the next ice cube … inside the water?
The cards are never quite the same; sometime the contacts are misplaced, sometimes they're missing.
But things like the girl phasing in the table, the soup phasing through the bowl … these are things a human would never animate, because they've lived their entire life understanding the physics of soup. Or, like with the card … they'd get a reference.
One consistent tell is in hair. The most obvious manifestation is how long hair splits and merges back into itself (as at 0:27).
AI hair often doesn't follow proper "form" and looks like overcomplicated, random tufts that can clash and overlap. It might not be obvious on a first glance, but you can learn to tell the difference pretty quickly.
I see people trying to make 5 - 10 minute clips of 80s anime inspired stuff, and it usually looks fine as a still, but when things move its off and when scenes change theres a vast inconsistency with previous scenes. I tend to block most of these creators even tho I should really be in the target audience.
This is pretty cool. I could see a future where these kinds of techniques become the norm, and the role of "animator" becomes less about hand drawing animations and more stylistic and taste choices, with I guess the occasional involvement by hand to get the exact result the animator wants. Still, the boundary between art and slop is super fine here.
It's weird how consistent the 'ai art style' is for each medium. You really only need a glance at the right frame in these to know immediately. (https://www.aventos.dev/our-work) Not looking for errors or anything, just style. The ramen one is markedly subtler about it than the others at least. I always assumed this was due to people using 'default' styling by not specifying anything in particular, but these people claim to have a pretty in-depth process that presumably would nudge away from that. When I look at old pictures of dall-e 2 or midjourney v3, the hands are all mangled and stuff, but they're not in the 'ai style'.
The characters on those video resemble alot certain mainstream works, isn't this very problematic?
As Hayao Miyazaki put it, it's "an insult to life itself"
The end result[1] looks quite impressive! The animation feels like it's quite high quality--very smooth. However, some things seem off: bad lip sync, minor animation errors, discontinuous scene-to-scene feel. Given that these are supposed to be their best examples, meant as advertisements, I would guess these errors are hard to fix using only the models.
So my verdict is that AI-only anime is still not there yet (although it would be cool to have a world where one dedicated and talented artist could make a high quality anime). But at the same time, anime studios will probably start incorporating AI into their workflow, getting high-quality-looking scenes for very cheap.
[1] https://www.aventos.dev/our-work
As the quality of each scene might someday surpass the budget of entire shows, anime can be infinitely more animated and creating something new in the process. What would a “multi-billion-dollar” episode look like? Hope we find out soon. Exciting times.
I have to admit that people interpreting current affairs/hot moments in real life through the lens of anime tropes really tickles in a way I never believed possible.
The aha moment was when people made ones over the Pam Bondi DOW over 50k meme but the recent World Cup ones have been very amusing too
> One, fans here actually get to make anime in the US. Instead of needing to fly to Japan, speak Japanese, and preferably be Japanese to break into the industry.
Does this come off as wildly tone deaf to anybody else? "We love your product and what you do, but could we get it without associating with or paying you in any way?"
> ...Smaller and faster means more financially feasible so we can give better wages for artists and enable a new industry to thrive in the US.
I've been in Asia this week, speaking to artists and creators. The traditional systems do create challenges, but this just sounds like a U.S. AI-based company giving itself carte blanche to steal the cultural output of another country, wrap it up in and American style business, and eventually push existing artists or long standing studios out of the space.
No, I don't think I want a smaller team of artists and animation professionals doing art and animation. That feels like a very sloppy outlook to me.
[Edit: While I'm sure the process is interesting for some, the introduction especially just leaves me wondering who thought this writing sounded good? Maybe the target market for this is AI investors or people who aren't actually interested in the artistic part of things, and that's why I find it such a turn-off.
E.g. "We could license good music," implying their music is bad? Maybe it would be less jarring if they didn't specifically call out the importance of writing?]
What I love about this post showing is that it admits up front that the quality of a given entertainment medium is in the writing.
Staff writers are not respected and treated as less than in Hollywood.
Yet the classics of any given medium have emotionally resonating entertainment medium have unique or paradigm-shifting results on audiences, and the medium itself (novel, comic book, TV show, miniseries, film, video game) has influence, but ultimately, it's the writing that is the single most important element of an entertainment IP's value.
An entertainment product that makes you feel emotions beyond boredom is doing its job. True crime/horror bring emotions of fear, mystery, and danger. Sci-Fi/Fantasy bring wonder, curiosity, and discovery, with genre-specific forms of each of those emotions. Mysteries and thrillers bring, well, mysteries and thrills.
So a slice of life AI anime, if it can properly portray from its writing a sense of growing mutual trust, awkwardness of growing up, combined with hope for a better tomorrow, it will have done its job as an entertainment product.
I'm procrastinating working on a fantasy novel which I started in 2012 and need to finish it. It has to hold up in today's neon flashing lights tiktok world as a book. But then there's no reason I couldn't use AI tools to direct adaptations of the source material to an anime or manga or TV show or web series.
Do I wish I could hire and pay and create an anime with a dedicated studio of practitioners who are pros and passionate about the medium beyond my wildest dreams? Sure! Is that likely to happen in 100 million lifetimes? Nope! So if I want to have my IP appear as an anime or TV show, my only realistic option with my one life on earth would be to try to do a similar process to how this animation studio works.
Bravo for them for advancing the medium for this, to find what works and what doesn't. Maybe some day if I will just finish my actual novel and get it eviscerated, after I've figured out how much it will take to pay Michael Kramer and Kate Reading to do an audiobook for it, I can find wild business success such that I could commission an anime series for the IP as my creative vision directs, and have humans do the interesting parts, and let the AIs do the boring inbetweens and tedium work.
But until then, I'll be keeping an eye on aventos to see where they go with this potential.
I have seen a few samples of AI anime, and it is impressive how far the technology has come; the only thing that really stands out are the cuts every few seconds, because video generation currently can't produce anything longer. However it's definitely enough to tell a story, particularly one that's nearly 100% fast-paced fighting scenes.
Honestly these look pretty good, I think run-of-the-mill anime is a strong target since it's highly formulaic and one of the more stylistically derivative genres.
I don't think this tech is quite "full length movie" watchable yet (maybe other uses), but seems only a matter of time where it would be "good enough" for common use.
A clip going for a few seconds is probably faster than a human, who can only hand draw one frame at a time
They mean how long a single continuous and contiguous scene is when played back, not how long it takes make the scene.
I wonder if it would be better to work on models thst can produce the 3D scenes in Blender that can be rendered to an anime style. That technique is already common, but if you could get AI to generate it in that format you could more easily ammend issues in the output or more easily add artistic direction, detail and the human touch.
I must admit, the short sample for “How Asians Pay the Bill” was kinda fun :)
> [we did this so anime production companies would] pay the employees(artists) better
I mean, has pay gone up in other fields where AI has taken over a lot of jobs?
In any case, I think the reason pay is awful in anime is the same reason as in gamedev: if people get into it for passion, the companies can pay less and still have employees.
Theyre basically saying trust us to pay our employees fairly no?
Wheres the accountability? What happens when investors demand more shareholder value and the founders comply?
> I think the reason pay is awful in anime is the same reason as in gamedev: if people get into it for passion, the companies can pay less and still have employees
Partially, but also outsourcing. First it was South Korea, then China, and now Vietnam and India.
Toei Animation's (Dragon Ball, One Piece, Sailor Moon, Mononoke) VISION 2030 [0] is interesting if you want to deep dive into how the industry is thinking medium-to-long terms
> has pay gone up in other fields where AI has taken over a lot of job
Depends on the industry [1]
[0] - https://corp.toei-anim.co.jp/en/ir/main/00/teaserItems1/0112...
[1] - https://www.bls.gov/opub/ted/2025/ai-impacts-in-bls-employme...
Pretty cool overview of the process even if I would rather claw my eyes out than view the result.
https://www.aventos.dev/our-work
dunno, I've seen worse and some of the scenes if you asked me if it was AI or not I probably couldn't tell you. most egregious thing I saw was at the 27 second mark where the girl is inside the table.
At the current level of tech it feels like it would be a pretty dull full length Anime, and hard to squeeze all the bugs out but for something shorter like a commercial or FMVs for like a video game seems good enough.
0:19 - the bowl has soup in it, despite coming from the middle of the stack.
0:19 - [same time] several bowls are just sloppified, e.g., having two bottoms
0:45 - last of the soup phases out the bottom of the bowl
Continuity errors with the smock. (Is there a logo on the pocket, or no? Does it have a pocket?)
("How Asians Pay for the Bill" … what a title)
0:29 - a water drop drops off the ice cube and falls to the next ice cube … inside the water?
The cards are never quite the same; sometime the contacts are misplaced, sometimes they're missing.
But things like the girl phasing in the table, the soup phasing through the bowl … these are things a human would never animate, because they've lived their entire life understanding the physics of soup. Or, like with the card … they'd get a reference.
One consistent tell is in hair. The most obvious manifestation is how long hair splits and merges back into itself (as at 0:27).
AI hair often doesn't follow proper "form" and looks like overcomplicated, random tufts that can clash and overlap. It might not be obvious on a first glance, but you can learn to tell the difference pretty quickly.
I see people trying to make 5 - 10 minute clips of 80s anime inspired stuff, and it usually looks fine as a still, but when things move its off and when scenes change theres a vast inconsistency with previous scenes. I tend to block most of these creators even tho I should really be in the target audience.
[delayed]
This is pretty cool. I could see a future where these kinds of techniques become the norm, and the role of "animator" becomes less about hand drawing animations and more stylistic and taste choices, with I guess the occasional involvement by hand to get the exact result the animator wants. Still, the boundary between art and slop is super fine here.
1. Theft