Pix2Pix is another good web tool for making horrifying autofill images
Google’s open-source machine learning project Tensorflow is probably used all the time for helpful things that advance the cause of mankind or something. But in my experience, what it has been best used for is making horrifying auto-generated images out of simple line drawings. I’m referring to edges2cats, which turned any line drawing into a cat. It was a whole thing! Everyone was trying it out, then posting pictures of really demented cats to Twitter for others to laugh at.
Today the same thing has happened, except it’s not cats. It’s human heads. And instead of Google’s project, Dutch Public Broadcaster NPO created its own artificial intelligence system that had only been fed thousands of images of one of its anchors, Lara Rense. As reported by the popular Tumblr prostheticknowledge, the web tool is called Pix2Pix.
You draw a face, and Pix2Pix uses a neural network to create what looks like an approximation of an oil painting of that face (made up of pieces of Rense’s face). Obviously the results mostly look like monsters, especially the pig-baby monster from the first season of American Horror Story. Also thumbs.
The auto-detected edges of your line drawing are probably only helpful if you are really good at drawing and can draw a lifelike face. For example, this is a total disaster, by me:
Anyway, have fun!
It looks horrible and fun XD
What do you think of this one
ahah
Congratulations @ayeshald! You have completed some achievement on Steemit and have been rewarded with new badge(s) :
You published your First Post
You made your First Vote
You got a First Vote
Award for the number of upvotes
Award for the number of comments
Award for the number of upvotes received
Click on any badge to view your own Board of Honnor on SteemitBoard.
For more information about SteemitBoard, click here
If you no longer want to receive notifications, reply to this comment with the word
STOP
By upvoting this notification, you can help all Steemit users. Learn how here!