AI powered monster drawing tool

Artificial intelligence (AI) applied to drawing starts to create interesting image manipulation applications. I I have earlier written about an interesting AutoDraw tool in my Google’s New Program ‘AutoDraw’ Will Help Your Drawings Suck Less posting.

Now there is some other well worth to check out experiments. Create your own hellish monsters with this sketch-based AI generator article tells that artificial intelligence trained with photos of real-life things eventually learn to generate simulations of things based on sketches, at least in the case of the pix2pix project. Last Halloween MIT put up its so-called ‘Nightmare Machine,’ which uses a deep learning algorithm to transform an ordinary photo into a horror-themed one. You can try it out for yourself here. and I tried with some interesting results:

pix2pix3

pix2pix2

 

pix2pix

This AI turns your cat sketches into trippy cat photos article tells about a new Tensorflow port of pix2pix is able to take your crude cat sketches and transform them into photo-realistic cat abominations — that is, photos that look like cats at first, but upon closer inspection are instead somewhat strange looking simulated versions of real cats. The system is also able to generate fairly realistic building facades, shoes, and bags. Try it yourself.

pix2pix5

I have to say that I was somewhat amazed on all those interesting AI applications…

Related links:

Image-to-Image Demo Interactive Image Translation with pix2pix-tensorflow

https://affinelayer.com/pix2pix/

Image-to-Image Translation with Conditional Adversarial Nets

https://phillipi.github.io/pix2pix/

Image-to-image translation with conditional adversarial nets

https://github.com/phillipi/pix2pix

Tensorflow port of Image-to-Image Translation with Conditional Adversarial Nets

https://github.com/affinelayer/pix2pix-tensorflow

 

2 Comments

  1. Tomi Engdahl says:

    Tech Talk: Neural Networks
    How to design and implement convolution neural networks, and what to watch out for.
    https://semiengineering.com/tech-talk-neural-networks/

    Megha Daga, senior technical marketing manager at Cadence, talks with Semiconductor Engineering about convolutional neural networks, including the bandwidth and compute challenges associated with them.

    Reply

Leave a Reply to Tomi Engdahl Cancel reply

Your email address will not be published. Required fields are marked *

*

*