Live data from Hacker News

Welcome to Waifu Labs v2: How Do AIs Create?

waifulabs.com

201–210 of 236 posts

Re: Welcome to Waifu Labs v2: How Do AIs Create?

#201
post #182

Earlier quoted context omitted.

Because if you are a mangaka/anime artist, you'll be pressured to add otaku stuff to boost sales.

And then -- pedophile content is ok for you? Wow.

Japanese just naturally look underage to western eyes. Opposite is also true btw. I think I’ve seen some women mention having to wear “Chinese eyed Pocahontas” makeup to be treated as a human in Western countries or else everyone looks away.

“500yo loli girl” argument might be pure BS but there is no way that age guesstimation on anime girls by someone who aren’t super familiar with local culture works either.

I mean take a look at a prehistoric clay figure, and try guessing age. I can’t.

Re: Welcome to Waifu Labs v2: How Do AIs Create?

#202
post #52

I made a waifu, then I pressed save. It wanted me to signup so I pressed back so I could just rightclick saveas but... I lost my waifu forever now :(

I mourn for your lost perfect waifu, but if it helps, your comment likely saved other waifus because we clicked [Download] instead of [Save].

Re: Welcome to Waifu Labs v2: How Do AIs Create?

#203
post #92

Earlier quoted context omitted.

No you don’t. Otherwise human artists would have to list out hundreds of attributions for every bit of art they saw that influenced their style.

Ctrl-C Ctrl-V is a career killer for human artists. Why it's not for ML? e: the argument for human artists is human inspirations are generalized and artists’ own interpretations are always added to it, and for ML it’s that their network weights are highly generalized and likewise not a copy; but IMO a more solid line has to be drawn and distinction has to be made between C-c C-v and generalization at some point forwa…

> Ctrl-C Ctrl-V is a career killer for human artists. Why it's not for ML?

Human artists use copy/paste as a tool all the time, and it doesn't kill their careers. The element you're missing here is that jychang wasn't talking about copying pieces verbatim from others' work without permission & attribution, but rather using it as a tool to manipulate your own art ("to copy/paste a layer"). Imagine being able to do the same but with an AI model working behind the scenes to adjust the object to fit the scene it's being pasted into.

Re: Welcome to Waifu Labs v2: How Do AIs Create?

#204
post #2

Hey HN, one of the team members here! I hope you all enjoy playing with the new and improved generator! We've been hard at work improving the model quality since the last time the site was posted[1] As both a professional fantasy illustrator & software engineer, I find the concept of AI creativity so fascinating. On one hand, I know that mathematically AI only can hallucinate images that fit within the distribution o…

Hello and thank you for answering questions. The following is a quote from your article: >> It is interesting to note that from this process, the AI is not merely learning to copy the works it has seen, but forming high-level (shapes) and low-level (texture) features for constructing original pictures in its own mental representation. Can you explain what you mean by "mental" representation? Does your system have a m…

Not OP, but I wonder if the process would be in some way comparable to rigging a 3D model. There is well, you usually have some high-level input parameters, which influence joints on a predefined skeleton, which in turn determines the position of individual vertices in the 3D body. Finally, the 3D shape is used to render the actual pixels.

On each step, high-level parameters are combined with predefined weights to produce a more low-level output.

Seems, a similar transformation is going on here, except that the weights and the structure are somehow learned on its own.

Re: Welcome to Waifu Labs v2: How Do AIs Create?

#205

Earlier quoted context omitted.

What makes you think human creativity is anything more than statistical modelling? What else can it be, based as it is in a physical substrate? Objections like yours are usually a sneaky way of implying that human consciousness breaks free of the physical world, cartesian dualism hidden within people's arguments. "It cannot be creative because it's only bits/cogs/linear algebra/etc/etc." Well describe to me the way i…

>> What makes you think human creativity is anything more than statistical modelling? For example, humans don't need to see millions of examples of waifu before they can draw their own. Also, humans can draw in different styles, including novel styles that look nothing like styles they have seen before. Statistical models like GANs can only draw in styles similar to the ones in their training sets. Statistical modell…

> For example, humans don't need to see millions of examples of waifu before they can draw their own.

Humans have the advantage of being trained for years on a far larger and more generalized dataset before they're asked to draw anything.

> Statistical models like GANs can only draw in styles similar to the ones in their training sets.

The intermediate states in the article's example seemed to contain a number of novel styles to me. The final results are filtered for conformance to a specific style due to the nature of the project, but that doesn't mean the GAN is incapable of drawing in other styles. (Of course, most of these alternate styles are not particularly appealing to humans, but the same is true for many of the experimental styles invented by human artists.)

> Statistical modelling can only represent the data in a training dataset and is incapable of novelty.

These AI models are generating images which never existed before, and which were not in their datasets. How is that not novelty?

Re: Welcome to Waifu Labs v2: How Do AIs Create?

#206

Earlier quoted context omitted.

> I'm guessing your referring to the "one of a kind" part of NFTs, which made me wonder, how would they validate that the created Waifu hasn't been created before? Oh, not even that, since while some data ends up on the blockchain, i find the whole ownership concept a bit nebulous at best, much like how people mock the whole "oh, just right click the image to save it" thing. What i was actually referring to was more…

Not to get too deep into NFTs as I to aren't an expert, but from what I understand the images that are used in NFTs are hosted on from a server and the owner of the NFT doesn't own the server, thus do they really own the image? I too like to collect things, my latest obsession was lingerie. But I always have the image of extreme hoarders in the back of my mind, which quite often scares me out of collecting to much. I…

The smart contract can do a content addressable way of identifying the image, with e.g. IPFS, and then, while in practice there may be a server which is hosting it for people, if anyone has the image saved, they can (if they choose to) continue act as a host for the image of the original server stops being around.

Not, uh, that NFTs for images like this aren’t silly and largely pointless,

but at least for some of them, the “there’s a server hosting the image” isn’t that much of an issue (at least provided that the person who “owns it” keeps the file locally and backed up)

Re: Welcome to Waifu Labs v2: How Do AIs Create?

#207
post #166

Earlier quoted context omitted.

One thing to consider is the number of artists employed by businesses. I dont have actual numbers but i know video game companies employs many. Businesses have different values than an individual human, and won't care if the art is made by a computer if its cheaper and passable. Theres also huge market for NSFW art. Whos going to know who or what made the image? Comparing photography to hand drawn art is silly. They…

It's no longer art if it's for commercial purposes. Those who have the courage necessary to become artists, and renounce the vulgarity of the world, will continue to do so. Those who delude themselves into thinking they're creating anything while being employed in commerce, will be managed out. The deep crevice where the two meet and manage to find compromise, will continue to be filled by wealthy, independent patron…

I think your definition of art is just a partial one. As an example, the characters drawn for an RPG are works of art. They are receiving monetary value in return for that art. So its commercial/entertainment art, and a place where many artists aspire to be.

Your definition is what I would call "culture defining art", which is art that some part of the culture identifies with (or more specifically, a person's way of communicating that they can identify with). The currency here is tribalism, i.e. it creates a way for two or more people to bond together through what they feel and think.

>Those who have the courage necessary to become artists, and renounce the vulgarity of the world, will continue to do so.

Courage is trumped by needs. If they need pay rent, buy food, support a family, pay for a car, etc, then no matter what they are sacrificing some part of their time in order to obtain those things. Thus any artist who can make money off their work would have more time for their work, and possibly grow faster.

>Those who delude themselves into thinking they're creating anything while being employed in commerce, will be managed out.

Seems like you're too attached to the idea of what an artist is and isnt?

>Ironically, if it's that important to you, why don't you start giving monetary support directly to artists?

Because Im not building something that is taking away from their dreams (e.g. living off their work/passion).

I wonder if people are aware of the consequences of automating creativity? IMO humans need human input in order to stay human. The less and less we come into contact with humanity, the less human we'll become.. and at the very end of that long path is a bag of chemical reactions that's forgotten the meaning of "how are you?" [1]

Which made me think, perhaps its the inefficiencies of life that is what makes us human

[1] This is because some company/companies will realize/have realized that tuning the machine to become most efficient at creating what the masses want will be the most profitable path.

Re: Welcome to Waifu Labs v2: How Do AIs Create?

#208
post #94

What methods are there to estimate how many unique characters a model can generate? The answer is not infinitely many, but determining when two images are of different 'characters' is fuzzy.

It's hard to say, but I think a useful measure would be to look at mode-dropping compared to the training data. Whatever the 'number of unique characters is', it clearly ought to be at least as large as the characters you see in the original training data, right?

For TADNE, Arfafax ran Danbooru2019 and a few million TADNE samples through CLIP to get the image embeddings, and clustered them; when the two sets of clusters were graphed using tsne, you could see that the TADNE StyleGAN2-ext did a lot of mode-dropping in that many smaller outlying clusters of characters/franchises/topics simply did not appear in TADNE samples. The TADNE looked like a big galaxy, while Danbooru2019 looked more like it was surrounded by archipelagos. TADNE was extensively trained on them and was a very large model, but the GAN dynamics & StyleGAN architecture mean it didn't do a good job absorbing rarer/more idiosyncratic Danbooru2019 image-clusters.

I expect newer generative models which avoid GAN losses and which use more flexible (but expensive!) architectures, like DALL-E, would perform much better in terms of mode-dropping, so you'd see a lot more unique characters/images out of them. (I'm very excited about them. As good as TADNE or Waifu Labs v2 may be, I think they are still far behind what could be done with just existing data/arch/compute.)

Re: Welcome to Waifu Labs v2: How Do AIs Create?

#209

I don't want to go all SJW on you guys, amazing work, but can you try to make sure there's an inclusive array of starting faces please? Talking about things like skin tones, thanks!

Anime has a pretty severe "representation of blackness" problem (https://www.youtube.com/watch?v=hi2_S6kBgIg is one video discussing this). I'm afraid to imagine what a model trained on that source content would generate.

Re: Welcome to Waifu Labs v2: How Do AIs Create?

#210
post #2

Hey HN, one of the team members here! I hope you all enjoy playing with the new and improved generator! We've been hard at work improving the model quality since the last time the site was posted[1] As both a professional fantasy illustrator & software engineer, I find the concept of AI creativity so fascinating. On one hand, I know that mathematically AI only can hallucinate images that fit within the distribution o…

Naïvely I thought Waifu generator was just “some guy having a laugh” fine-tuning a model off of hugging face, but reading through the comments here, it is obviously a much, much bigger enterprise. Can you talk a little about team size, work process, funding and revenue stream? I think the effort required for such an undertaking is vastly underestimated by readers.

> Naïvely I thought Waifu generator was just “some guy having a laugh”

same here. what's naive about it?

not to badmouth the undertaking, but wtf is this doing on HN?

Post reply on HN