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

Welcome to Waifu Labs v2: How Do AIs Create?

waifulabs.com

Post reply on HN
Print view View original

91–100 of 236 posts

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

#91

Post by Gigachad »

numpad0 wrote: post #88
jychang wrote: post #57

Earlier quoted context omitted.

Well, digital art already allows you to copy/paste a layer and stuff that traditional art never allowed for. Imagine copy pasting a statue. This is sort of the same thing on steroids. You can copy/remix previous art by feeding them into a ML model in training mode, and it will be massively utilized the same way ctrl-c ctrl-v is used, but it's a part of the toolset of art creation, not replacing it.

> You can copy/remix previous art by feeding them into a ML model in training mode, and it will be massively utilized the same way ctrl-c ctrl-v is used, Then you need attributions for said previous arts, all of it, at least going by texts of laws.

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.

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

#92

Post by numpad0 »

Gigachad wrote: post #91
numpad0 wrote: post #88

Earlier quoted context omitted.

> You can copy/remix previous art by feeding them into a ML model in training mode, and it will be massively utilized the same way ctrl-c ctrl-v is used, Then you need attributions for said previous arts, all of it, at least going by texts of laws.

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 forward.

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

#93

Post by plutonorm »

bmitc wrote: post #74

This isn't really creativity is it? I like to call stuff like this statistical copying, and indeed, the linked Wikipedia article on GANs says: > Given a training set, this technique learns to generate new data with the same statistics as the training set. There isn't a creative process here nor any creative introspection going on. While the technical results are impressive, this article does not address creativity ev…

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 it is different to the processes of the human brain? "There is some magic sauce in the human brain we do not yet understand!", well then how do you know that this magic sauce does not exist within the statistical models inside the computer?

I find it very irritating that such shallow reasoning prevails amongst intelligent people.

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

#95

Post by liuru »

ridaj wrote: post #82
liuru wrote: 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…

Fascinating... Thanks for sharing A couple questions: 1) I didn't really understand how you went about identifying what vectors of the latent space stand for various things, like pose or color. Did you train one of the AIs to that effect, or did you manually inspect a bunch of vectors, twiddling through them one by one, did to the outcome? 2) If one were to train an AI to the same level using commodity cloud services…

1) It was mostly manual, though AIs were useful in certain filtering tasks.

2) Depends on the quality you are seeking. If you only want one run of a similar, off-the-shelf model, around the 1000s is enough. But at the number of iterations you have to run to build your own and improve results, you probably need about 100k.

To tackle this problem, we built our own supercomputer off of parts we bought off of ebay, though I can't say I recommend that route, because it now lives in our living room.

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

#96

Post by liuru »

searchableguy wrote: post #44
liuru wrote: 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…

Do you plan to provide an API to generate waifu? I think I could use this for a project.

In the future, perhaps! This is a popular request, so we are thinking about ways we can do this.

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

#97

Post by liuru »

bmitc wrote: post #74

This isn't really creativity is it? I like to call stuff like this statistical copying, and indeed, the linked Wikipedia article on GANs says: > Given a training set, this technique learns to generate new data with the same statistics as the training set. There isn't a creative process here nor any creative introspection going on. While the technical results are impressive, this article does not address creativity ev…

read the bottom! The part about creativity is on the bottom :D

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

#98

Post by echelon »

aniforprez wrote: post #78
dirtyid wrote: post #62

I hope these generators expands into non waifu / pretty boy anime depictions. There's a lot anime gaijin faces out there to explore.

I would like to see how it generates late-80s/early-90s style features. The current pool of anime art styles are very generic (aside stylistic outliers) and I'd love to see Cowboy Bebop/Akira/Bubblegum Crisis type character designs

Miyazaki's style of character design and fantasy would be amazing.

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

#99

Post by the8472 »

ve55 wrote: post #8

Links to related projects in anime art generation for those interested: Waifu Labs v2, referenced in this post (generate amazing custom anime face images): https://waifulabs.com (write-up is the above link: https://waifulabs.com/blog/ai-creativity ) This Anime Does Not Exist (AI-generated anime-style artwork): https://thisanimedoesnotexist.ai (write-up https://www.gwern.net/Faces#extended-stylegan2-danbooru2019-... a…

Note that TADNE, being based on newer models, generates full images rather than only faces.

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

#100

Post by Cixelyn »

wodenokoto wrote: post #81
liuru wrote: 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.

Right now it's a small team of 6 people, and we have a bit of funding + compute credits to train models. There's a bit of revenue from some past projects and AI-consulting, but we're mostly betting big on our new AI-powerd mobile title Arrowmancer[1].

> I think the effort required for such an undertaking is vastly underestimated by readers.

Haha for sure. Hosting a real-time ML model for people to do sub 1-second inferences at HN-load scale is definitely nontrivial.

[1] https://arrowmancer.com

Post reply on HN