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

Show HN: I built an AI art installation at home generating new pieces on the fly

github.com

Post reply on HN
Print view View original

71–80 of 161 posts

Re: Show HN: I built an AI art installation at home generating new pieces on the fly

#71

Post by mfi »

sandGorgon wrote: post #50
mfi wrote: post #45

Earlier quoted context omitted.

Thanks! Depending on how many artworks you've created, it might be difficult to train a GAN network on them (due to overfitting). What you might try is to train one network with a lot of random artworks, then use a Style-transfer network to convert the generated pieces into your style.

do you have the code for training ? i wasnt able to find it in your repo. That would be so cool!

I left it out as I wanted people to use their own generative art. Here's the implementation I used: https://github.com/taki0112/StyleGAN-Tensorflow

Re: Show HN: I built an AI art installation at home generating new pieces on the fly

#72

Post by mfi »

xrd wrote: post #62

This is awesome. Is the StyleGAN code removed (to keep it private)? I see this commit message: "Remove my ML stuff." I'm interested in understanding the StyleGAN if you are open to sharing it.

Thanks! Yeah, I removed it as I want people to use their own generative art in their own build. But if you're interested, here's the implementation I used: https://github.com/taki0112/StyleGAN-Tensorflow

Re: Show HN: I built an AI art installation at home generating new pieces on the fly

#74

Post by dheera »

mfi wrote: post #2

I just finished my latest project, building an AI art installation at home, generating 100 % unique artworks on the fly. Just push the button below the screen and another one will be displayed. When the button has been pushed, the old artwork is deleted and can't be retrieved again. Setup: * An Nvidia Jetson Xavier NX was used for all logic, machine learning inference, art kiosk GUI etc. * A StyleGAN was used to gene…

Interesting! I built a generative art frame based on "{Shan, Shui}" by Lingdong Huang

https://dheera.net/projects/einkframe/

but also planning to use it for neural-net based generative art. I wasn't planning on putting a NX in it though, I was thinking of just keeping the Pi Zero in there and have it do all computations in "the cloud" or on a Nano/Xavier box sitting elsewhere on the same network.

I'm currently working on a 3-panel version of the above:

https://imgur.com/a/3IfKpb3

I didn't make my own frame though, I designed the dimensions and had it custom-built by a frame company, which was surprisingly affordable.

Re: Show HN: I built an AI art installation at home generating new pieces on the fly

#75

Post by chorsestudios »

mfi wrote: post #41
qq4 wrote: post #40

do you find any of the generated images interesting? there is no thought behind any of them which leads me curious to how captivating they might be.

Some of them are nice, but a lot of them are trash as well. So you need to click a few times before you find something you (I) like

Any chance you have a gallery somewhere with some of the nicer images?

Re: Show HN: I built an AI art installation at home generating new pieces on the fly

#77

Post by Sn0wCoder »

mfi wrote: post #22
Sn0wCoder wrote: post #16

Very cool. I work from home in my basement and would enjoy such a device. Any plans to sell them? Or know of similar devices? I could probably build one, but most likely would end up in pieces next to my other random projects…

No, I currently have no plan to sell it. There's a lot of overhead involved when selling stuff, and I mostly enjoy building stuff like this :)

Sounds good. Like others have said an API around the generator would be cool too, then all I need is a webpage and a monitor.

Re: Show HN: I built an AI art installation at home generating new pieces on the fly

#78

Post by xrd »

mfi wrote: post #72
xrd wrote: post #62

This is awesome. Is the StyleGAN code removed (to keep it private)? I see this commit message: "Remove my ML stuff." I'm interested in understanding the StyleGAN if you are open to sharing it.

Thanks! Yeah, I removed it as I want people to use their own generative art in their own build. But if you're interested, here's the implementation I used: https://github.com/taki0112/StyleGAN-Tensorflow

I'm struggling a little bit with using StyleGANs so far. Are you available for a (paid if you prefer) call where I ask you a few questions about it? If so, xrdawson@gmail.com.

(I have a connection to Sweden, by the way. My brother lived in Eskilstuna in high school. So, I learned a little bit of Swedish when I visited him. His host brother thought it was really weird I met him and said "jag heter Chris, jag älska naturen!"). But, I would not feel comfortable talking to you in Swedish about StyleGAN. :) ).

Re: Show HN: I built an AI art installation at home generating new pieces on the fly

#79

Post by dheera »

TuringNYC wrote: post #64
mfi wrote: post #2

I just finished my latest project, building an AI art installation at home, generating 100 % unique artworks on the fly. Just push the button below the screen and another one will be displayed. When the button has been pushed, the old artwork is deleted and can't be retrieved again. Setup: * An Nvidia Jetson Xavier NX was used for all logic, machine learning inference, art kiosk GUI etc. * A StyleGAN was used to gene…

>> Nvidia Jetson Xavier NX Curious -- since you're only doing the inference/generation on the frame, and since you're not doing it all the time, did you need a Jetson or would an RPI have sufficed? Did you test inference speeds across different edge compute options?

Yeah I think the way I'd do it (personally) is have an RPi constantly generate new images in the background and cache them until storage is maxed out, then when you hit the button it just fetches the next image from cache.

That would allow the frame to be somewhat lower power and also decrease ventilation requirements -- no fan needed.

Post reply on HN