to everyone who is trying it -> just scaling up the system now. Please be patient and keep your tab open. The image will eventually appear :)

Clicking "Get it on canvas" takes me straight to "enter your personal information" with no clue of what's going on. Noooooooope.

Thanks for pointing this out. Actually NeuralBlender.com was not to be released to the public yet, but the topic in this thread kind of invited it. I will clarify that and improve the UX.

Great, I like the name! I'm trying it now.

Here's my result:

https://s3.amazonaws.com/ai.protogenes/art/3ed8a7fa-f60b-11e...

"a monkey riding a rocket"

I think it works well :) Which architecture is this based on? Did you consider any trips or fine-tuning to generate images that are perceptually similar to art?

It is based on VQGAN (trained on imagenet) and Open AI's CLIP. To make it more similar to art you would need to do some "prompt engineering. Try: "painting of ..." or "... painted by Van Gogh"