Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AniSora: Open-source anime video generation model

komiko.app

Post reply on HN
Print view View original

221–230 of 232 posts

Re: AniSora: Open-source anime video generation model

#221

Post by latexr »

wodenokoto wrote: post #213
latexr wrote: post #96

Earlier quoted context omitted.

I disagree with the positive characterisation. Those videos have a funny schtick of exaggerating anime tropes for a couple of minutes and that’s the extent of it. The animation is all over the place, reactions, expressions, mouth movements often fail, style changes from frame to frame. It maybe kind of works precisely because it’s a short exaggerated parody and we have a high tolerance for flaws in comedy, but even t…

I think it’s a successful creative endeavor for two reasons: They took the weaknesses of last years style transfer models and used them as a style, working around and with it’s shortcomings and weaknesses. That is a far cry from “type a prompt and be do e with it”. Secondly I think the story is fun and the whole thing is fun, not in a will smith eats spaghetti kind of why but fun as in an actually fun short film. I t…

> I think it’s a successful creative endeavor

Fair. But I wouldn’t say that automatically translates to “absolute great” or that it “by all accounts be called art”. Though there is a high degree of subjectivity there, which why I simply said I disagree.

> actually fun short film

Sure, you like what you like, no judgement. But again, “it’s a short exaggerated parody and we have a high tolerance for flaws in comedy”. Had they tried to make something more substantial, serious, provocative, emotional, or slower paced, I believe they would’ve fallen flat.

> I think it shows that AI can be a tool that empowers creativity and creative work

Plenty of actual artist disagreed, though. And the backlash wasn’t just limited to the end product, but Corridor Crew’s attitude to it (creator intentions matter a lot when defining something as art) and lack of understanding on the very real and very negative impacts on the industry.

https://www.youtube.com/watch?v=GOwxXj1EIXM

Re: AniSora: Open-source anime video generation model

#222

Post by throwawayk7h »

aspenmayer wrote: post #205
throwawayk7h wrote: post #174

Earlier quoted context omitted.

The percentage of anime I like is low and has always been low. I find a new anime I like comes along about every three years (I have to dig for it though.) In general, I care about the writing and story more than the visuals. So with a great increase in the amount of anime a single writer can create, shouldn't this allow for more well-written sloppy-visuals anime to exist? I'm excited to see.

How do you typically find anime you end up enjoying now?

It comes down to identifying what I dislike about the anime I dislike.

I find I don't like "fanservice" (boob jokes etc.), or at least find it to be a signifier of poor quality. So I use animefeminist.com for recommendations, since it's pretty effective at filtering out (or at least warning of in advance) that kind of red flag, and also for their ranking of seasonal anime. (If you use this method, make sure to look for their "recommendation," "digest," and "three-episode check-in" articles specifically). This improves things from about 1% chance of enjoyment to probably 1-in-15 chance of enjoyment. On average, each season has an anime I find is not bad, but only every 2-3 years or so is there an anime I unabashedly love.

(Of course, there may be shows the site rules out which I really loved -- for instance, my all-time favourite anime is Attack on Titan, which is blacklisted on anifem because someone once wrote an article on polygon about how its overtly pro-jewish anti-fascist allegory is anti-semitic somehow. I think that's a load of bull, but probably not enough of a problem for me to stop using this method of finding anime.)

Re: AniSora: Open-source anime video generation model

#223

Post by aspenmayer »

throwawayk7h wrote: post #222
aspenmayer wrote: post #205

Earlier quoted context omitted.

How do you typically find anime you end up enjoying now?

It comes down to identifying what I dislike about the anime I dislike. I find I don't like "fanservice" (boob jokes etc.), or at least find it to be a signifier of poor quality. So I use animefeminist.com for recommendations, since it's pretty effective at filtering out (or at least warning of in advance) that kind of red flag, and also for their ranking of seasonal anime. (If you use this method, make sure to look f…

I think Attack on Titan is a good anime, but I read the allegory as being a Japanese one, and in that reading it comes off as somewhat apologist toward fascism. I think many readings are present in the work and more besides can be read into it, so I don’t claim that any interpretation is right or wrong, because that would probably involve spoilers.

Have you seen Psycho-Pass? I wonder what your site has to say about it, as it seemed kind of a feminist work to me.

You might find this site interesting:

https://cyberfeminismindex.com/

Re: AniSora: Open-source anime video generation model

#224

Post by idiotsecant »

collingreen wrote: post #167
idiotsecant wrote: post #146

Earlier quoted context omitted.

My prediction: It will be like furniture. A long time ago, every piece of furniture was handmade. It might have been good furniture, or crude, poorly constructed furniture, but it was all quite expensive, in terms of hours per piece. Now, furniture is almost completely mass produced, and can be purchased in a variety of styles and qualities relatively cheaply. Any customization or uniqueness puts it right back into t…

This prediction implies that people will value consuming tailored media, knowing 100% that it was generated because they wanted it (as opposed to because someone wanted to express something), with no deeper story or connection or exploration to it. If people instead care about the creation story and influences (the idea of "behind the scenes" and "creator interviews" for on demand ai generated media is pretty funny)…

I think the proportion of people who care about 'the making of' type content is vanishingly small. Almost everyone is looking for a dopamine hit and that's it.

Re: AniSora: Open-source anime video generation model

#225

Post by throwawayk7h »

aspenmayer wrote: post #223
throwawayk7h wrote: post #222

Earlier quoted context omitted.

It comes down to identifying what I dislike about the anime I dislike. I find I don't like "fanservice" (boob jokes etc.), or at least find it to be a signifier of poor quality. So I use animefeminist.com for recommendations, since it's pretty effective at filtering out (or at least warning of in advance) that kind of red flag, and also for their ranking of seasonal anime. (If you use this method, make sure to look f…

I think Attack on Titan is a good anime, but I read the allegory as being a Japanese one, and in that reading it comes off as somewhat apologist toward fascism. I think many readings are present in the work and more besides can be read into it, so I don’t claim that any interpretation is right or wrong, because that would probably involve spoilers. Have you seen Psycho-Pass? I wonder what your site has to say about i…

I love Psycho-Pass, it's a classic Urobuchi. Can't find a proper review on the site though, likely since it predates the site's launch. (They're doing reviews of previous years as well, but slowly.)

Regarding the Japanese interpretation of the allegory -- I don't think it's apologist toward fascism really, because essentially every side in the conflict has fascist elements. In that sense, it's more "some situations just don't have any good solutions." But what's clear to me is that the situation itself has fascist roots. Regardless, the Polygon article in question has a much more surface-level reading -- it is clearly stating that it's antisemitic, which I simply can't see at all. Spoilers rot13: vg'f gehr gur gvgnaf ner ~wrjf, ohg guvf vtaberf gung gurl ner gur perngvbaf bs ~anmv rkcrevzragf, naq nyfb gung nyy gur cebgntbavfgf ner ~wrjf nf jryy.

I don't understand what I'm looking at with the site you linked, but I am intrigued.

Re: AniSora: Open-source anime video generation model

#226

Post by TeMPOraL »

gregw2 wrote: post #192
TeMPOraL wrote: post #135

Earlier quoted context omitted.

That makes no sense, neither legally nor philosophically. > Language developed independently of translators. And it also developed independently of writers and poets. > Artists shape the space in which they’re generating output. Not writers and poets, apparently. And so maybe not even artists, who typically mostly painted book references. Color perception and symbolism developed independently of professional artists,…

If you think memes are art too and we lack shared consumption of art due to personalization, you clearly don't have kids into YouTube or Minecraft or Frozen, or ...

I actually have kids, two of them in kindergarten. I can already see this problem affecting them, because beyond Frozen and Paw Patrol and a couple others, everyone also has their own favorite series on YouTube that few other kids heard of, and I can see kids trying and failing to bond over those.

I never thought I'd be thankful for global, toy-pushing franchises, but they at least serve as a social object for kids, when the current glut of kids videos on YouTube doesn't.

Re: AniSora: Open-source anime video generation model

#227

Post by aspenmayer »

throwawayk7h wrote: post #225
aspenmayer wrote: post #223

Earlier quoted context omitted.

I think Attack on Titan is a good anime, but I read the allegory as being a Japanese one, and in that reading it comes off as somewhat apologist toward fascism. I think many readings are present in the work and more besides can be read into it, so I don’t claim that any interpretation is right or wrong, because that would probably involve spoilers. Have you seen Psycho-Pass? I wonder what your site has to say about i…

I love Psycho-Pass, it's a classic Urobuchi. Can't find a proper review on the site though, likely since it predates the site's launch. (They're doing reviews of previous years as well, but slowly.) Regarding the Japanese interpretation of the allegory -- I don't think it's apologist toward fascism really, because essentially every side in the conflict has fascist elements. In that sense, it's more "some situations j…

V ernq vg nf na nyyrtbel sbe ubj Wncna gubhtug bs vgfrys qhevat JJ2, nf n qvfgvapgyl qvssrerag enpvny urevgntr sebz znvaynaqref va Znapuhevn naq bgure cnegf bs Puvan. Guvf fhccbfrq enpvny fhcrevbevgl bs Wncna bire bgure Nfvna angvbaf jnf hfrq nf whfgvsvpngvba sbe frvmvat pbny naq bgure angheny erfbheprf nf rneyl nf 1937. Ivrjrq va guvf senzvat, gur fubj pbzrf bss nf ncbybtrgvpf sbe gur uhzna rkcrevzragf gung Wncna pbaqhpgrq nf jryy nf gur ngebpvgvrf gurl pbzzvggrq. Ubjrire, V trg gur frafr gung nyy bs gur snfpvfz va gur fubj unq bppheerq va gur cnfg, naq gur rpubrf naq nsgrerssrpgf ner gur onpxfgbel sbe gur pbagrkg sbe gur fubj, qrcvpgvat ubj gur puvyqera bs jne naq rzcver svtug qrfcrengryl gb birepbzr srne, gura funzr bs xabjvat gurve cnfg, abg whfg nf ybfref va n jne, ohg uhzna rkcrezragf jub orpnzr jung gurl srnerq, qrngu vgfrys, qverpgrq abg whfg vajneqyl, ohg bhgjneqyl nf jryy.

> I don't understand what I'm looking at with the site you linked, but I am intrigued.

It’s kind of like an interactive bibliography with commentary?

https://cyberfeminismindex.com/about/

https://en.wikipedia.org/wiki/Cyberfeminism_Index

Re: AniSora: Open-source anime video generation model

#228

Post by omeid2 »

Nevermark wrote: post #216
omeid2 wrote: post #99

Earlier quoted context omitted.

> There are very few laws that are not giant ambiguities. Where is the line between murder, self-defense and accident? There are no lines in reality. These things are very well and precisely defined in just about every jurisdiction. The "ambiguities" arise from ascertaining facts of the matter, and whatever some facts fits within a specific set of set rules. > Something must change regarding copyright and AI model tr…

> These things are very well and precisely defined in just about every jurisdiction. Yes, we have lots of wording attempting to be precise. And legal uses of terms are certainly more precise by definition and precedent than normal language. But ambiguities about facts are only half of it. Even when all the facts appear to be clear, human juries have to use their subjective human judgement to pair up what the law says…

It seems like your concerns is about how easy it is going to be to create derivative and similar work, rather than a genuine concerns for copyright. Do I understand correctly?

Re: AniSora: Open-source anime video generation model

#229

Post by Nevermark »

omeid2 wrote: post #228
Nevermark wrote: post #216

Earlier quoted context omitted.

> These things are very well and precisely defined in just about every jurisdiction. Yes, we have lots of wording attempting to be precise. And legal uses of terms are certainly more precise by definition and precedent than normal language. But ambiguities about facts are only half of it. Even when all the facts appear to be clear, human juries have to use their subjective human judgement to pair up what the law says…

It seems like your concerns is about how easy it is going to be to create derivative and similar work, rather than a genuine concerns for copyright. Do I understand correctly?

No, I am just narrowing down the problem definition to the actual damage.

Which is a very fair use and copyright respecting approach.

Taking/obtaining value from works is ok, up until the point where damage to the value of original works happen. And that is not ok. Because copyright protects that value to incentivize the creation and sharing of works.

The problem is that models are shipping that inherently make it easy to reproduce copyrighted works, and apply specific styles lifted from single author's copyrighted bodies of work.

I am very strongly against this.

Note that prohibiting copying of a recognizable specific single author's style is even more strict than fair use limits on humans. Stricter makes sense to me, because unlike humans, models are mass producers.

So I am extremely respectful of protecting copyright value.

But it is not the same thing as not training on something. It is worth exploring training algorithms that can learn useful generalities about bodies of work, without retaining biases toward the specifics of any one work, or any single authored style. That would be in the spirit of fair use. You can learn from any art, if it's publicly displayed, or you have paid for a copy, but you can't create mass copiers of it.

Maybe that is impossible, but I doubt it. There are many ways to train that steer important properties of the resulting models.

Models that make it trivial to create new art deco works, consistent with the total body of art deco works, ok. Models that make it trivial to recreate Erte works, or with an accurately Erte style specifically. Not ok.

Re: AniSora: Open-source anime video generation model

#230

Post by omeid2 »

Nevermark wrote: post #229
omeid2 wrote: post #228

Earlier quoted context omitted.

It seems like your concerns is about how easy it is going to be to create derivative and similar work, rather than a genuine concerns for copyright. Do I understand correctly?

No, I am just narrowing down the problem definition to the actual damage. Which is a very fair use and copyright respecting approach. Taking/obtaining value from works is ok, up until the point where damage to the value of original works happen. And that is not ok. Because copyright protects that value to incentivize the creation and sharing of works. The problem is that models are shipping that inherently make it ea…

> The problem is that models are shipping that inherently make it easy to reproduce copyrighted works, and apply specific styles lifted from single author's copyrighted bodies of work. > I am very strongly against this. > Note that prohibiting copying of a recognizable specific single author's style is even more strict than fair use limits on humans. Stricter makes sense to me, because unlike humans, models are mass producers.

This sounds like gate-keeping rather than genuine copyright concerns.

> Models that make it trivial to create new art deco works, consistent with the total body of art deco works, ok. Models that make it trivial to recreate Erte works, or with an accurately Erte style specifically. Not ok.

Yeah, again, sounds like gate-keeping more than an economic and incentives argument which are, in my opinion, the only legitimate concerns underpinning copyright's moral ground.

Every step of progress has made doing things easier and easier to the point that now arguing with some strange across the world seems trivial, almost natural. Surely there are some arguments to curtail this dangerous machinery that undermines the control of information flow and corrupts the minds of the naive! we must shut it down!

Jokes aside, "making things easier/trivial" is the name of the game of progress. You can't stop progress. Everything will be easier and easier as the time goes on.

Post reply on HN