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

11–20 of 236 posts

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

#11

Post by liuru »

darkengine wrote: post #7
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…

Is the code or any of the models available to the public? I'd love to mess with this on a local GPU cluster.

Not at the moment! A similar project that I really admire is public, though!

https://www.thiswaifudoesnotexist.net/

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

#12

Post by dimgl »

liuru wrote: post #10
dimgl wrote: post #5

Earlier quoted context omitted.

You mention it took two weeks to get to the point that we see in the article. Does this mean two weeks of development, or two weeks to generate the images we're seeing? Or maybe did you train the model for two weeks? That point just wasn't exactly clear for me.

2 weeks to train the model! Development took on-and-off roughly 2 years to achieve the quality you see today.

Cool! Might want to clarify that. This is crazy impressive!

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

#13

Post by Gigachad »

hypertele-Xii wrote: post #4
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…

Why do stuff like this never come down from the web? I'd pay for a program I could download and use with my own image files.

They tend to require specific hardware like a NVIDIA GPU. As well as having an ever evolving large model file which they will want to frequently update. Some tools certainly have had offline versions but I guess not many people are interested in setting it all up and are happy with an instant web ui

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

#14

Post by zozbot234 »

hypertele-Xii wrote: post #4
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…

Why do stuff like this never come down from the web? I'd pay for a program I could download and use with my own image files.

You just need to code up your own model architecture and then train it on your data using some established ML framework. The first step is where well-chosen priors can make a real difference wrt. your end results.

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

#15

Post by 2bitencryption »

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…

Firstly, amazing work.

My question is, how do you figure out how to parameterize "Same character, different pose" / "Same character, different eyes" / "Same character, different gender" / etc?

My (super limited) understanding of GANs is that they slowly discover these features over time simply from observation in the data set, and not from any labels.

So how could you make e.x. a slider for head position, style, pose, etc? How do you look at the resulting model and figure out "these are the inputs we have to fiddle with to make it use a certain pose"?

You mention it a bit in this section, but I didn't fully understand: "By isolating the vectors that control certain features, we can create results like different pose, same character"

And I assume the same step needs to be done every time the model is retrained or fine-tuned, because possibly the vectors have shifted within the model since they are not fixed by design?

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

#16

Post by liuru »

2bitencryption wrote: post #15
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…

Firstly, amazing work. My question is, how do you figure out how to parameterize "Same character, different pose" / "Same character, different eyes" / "Same character, different gender" / etc? My (super limited) understanding of GANs is that they slowly discover these features over time simply from observation in the data set, and not from any labels. So how could you make e.x. a slider for head position, style, pose…

Yes, your understanding is correct!

You can think of it like coordinates on a many-dimensional vector grid.

We craft the functions the functions that will illuminate sets of those points based on a combination of observation, what we know about our model architecture, and how our data is arranged.

And yes, when the model is retrained, we have to discover them again!

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

#17

Post by liuru »

hypertele-Xii wrote: post #4
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…

Why do stuff like this never come down from the web? I'd pay for a program I could download and use with my own image files.

While our model is not public, there are good resources online for playing with your own images!

Like this one by fast.ai!

https://docs.fast.ai/vision.gan.html

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

#20

Post by rackjack »

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…

I LOVE that "horror". Reminds me of some of the art I've seen on album/single covers. Any chance of letting people access that kind of intermediate step? (Though I know it's a niche as hell use case).
Post reply on HN