post pictures your computer has generated ( algorithmic art )

[william_kent]

ouroboros, photograph by hans bellmer

 

[william_kent]

Cthulhu on crutches by Hans Bellmer

 

[william_kent]

dogging hotspot, photograph by Hans Bellmer

 

[catalog]

we'll make that last one into a print for wash for xmas

 

[WashYourHands]

Technically retired but cheers!

 

[william_kent]

create GAN / AI art on your smartphone

I've not tried this yet. Advertised along the lines of "generate NFTs in minutes"..

 

[catalog]

downloaded, im in the queue to make an image.

 

[Clinamenic]

@catalog @william_kent do we know if there is a way to have audio speech converted to text and fed into a GAN in real time? I’d like to read aloud passages from Gravity’s Rainbow.

 

[Clinamenic]

That would seem to be a good programming project to get the hang of neural networks.

 

[william_kent]

@catalog @william_kent do we know if there is a way to have audio speech converted to text and fed into a GAN in real time? I’d like to read aloud passages from Gravity’s Rainbow.

that would entail a bespoke, expensive setup - but I'd love to view the results

 

[Clinamenic]

Expensive in terms of compute? I figured I could do it in short batches, still using Collab. I’d imagine I could reconfigure some of the VQGAn+CLIP code, and implement some code someone else has written for converting speech to text, but it would have to be input into the GAN in a real time fashion (or close enough thereto).

Although actually it wouldn’t need to be real time at all. It would just need to be dynamic, I.e having the text input parameter cycle forward with the ongoing speech, if even with a time delay.

That is, we may need each iteration to run on a different sequence of words, in a continuous fashion.

 

[william_kent]

I'm presuming you'll be reading while reclining in a leather armchair, with electrodes attached to your skull taking EEG readings which provide the noise prompts?

 

[Clinamenic]

Maybe we could stagger our the portions of text across a few different GAN runs, then line all the mp4s up into a grid and play that in parallel with the speech recording, so the viewer can track the speech in relation to the partitioned GAN runs that are each running different portions of the excerpt.

 

[Clinamenic]

or I could manually take a page of GR and take a ten word input, do a few iterations of that, then shift the ten-word sequence forward by one word, do another few iterations, and so on and so on.

I would have to calibrate the iteration length to the average time duration per word, in order to sync the visuals to the speech.

 

[catalog]

I'm not sure it's possible, but it's surely around the corner. It's actually what I what the tree thing to become. I want the ability to look at a tree, speak to it via the phone and on the phone screen comes the image yoh are seeing, with the augmentation you want.

The technical capacity is there, it just needs to be joined up.

 

[WashYourHands]

Robert Lowe uses plants as modular synths

 

[WashYourHands]

The mind of God Unreal engine



Artstation



Hyperreal

 

[william_kent]

the Unreal Engine one is like the final boss fight setting

 

[william_kent]

I've been trying to get hypnogram to generate tarot cards today


The Devil | tarot card | in the style of Remedios Varo

 

[WashYourHands]

Waiting saw this one fly past

Nature of existence in the universe