//=time() ?>
Text-to-image with OpenAI's CLIP is getting more and more surreal. Here is "A banquet hall"
Amazing results on text-to-image generation by DALL-E. Seems like language interface is the future of HCI. https://t.co/hv900VtDvG
These are from a StyleGAN-encoder trained on my WikiArt paintings model.
Work-in-progress notebook in Eden: https://t.co/mk7XEI5tQ3
Here’s a few more recognizable images regenerated by the model
3D rigid body transformations programmed into GANs. Innate knowledge is not dead in deep learning https://t.co/9oRbcTWYWK
once you train a GAN you have this brilliant latent space to play with, but it's hard to do much more than search through it. with optimization-based methods, you get back some of the compositional abilities that generative artists are used to
another Kandinsky texture loop, but this one using Perlin noise distortion. it's a little clumpy, but i like it