user avatar
Rivers Have Wings
@RiversHaveWings
AI/generative artist. Writes her own code. Absolute power is a door into dreaming.
Joined June 2016
Posts
  • Pinned
    user avatar
    Humanity is going to make all parts of the world touched by humans beautiful. We are going to create beauty too cheap to meter. And not just an enforced-from-above standard of beauty either, everyone will be able to make their own domain beautiful in the manner of their choosing.
  • user avatar
    00:00
  • user avatar
    I'm doing AI NFTs now. :) Our main product is called Control The Soul. It's a 1k piece collection meant to make cool Twitter avatars. The theme is wizards, eldritch artifacts, and weird landscapes. Most items 3-4 XTZ. Check out the gallery at chainbreakers.kath.io
  • user avatar
    "🌹 fractal" StyleGAN XL + CLIP
    00:00
  • user avatar
    "A vision of paradise, Unreal Engine" StyleGAN XL + CLIP
    00:00
  • user avatar
    "the gateway between dreams, trending on ArtStation" (CLIP guided YFCC diffusion, 968M parameter model, it's not done training yet)
  • user avatar
    "The Rise Of Consciousness" StyleGAN XL + CLIP
    00:00
  • user avatar
    Stable Diffusion weights are out for academic research purposes upon request: github.com/CompVis/stable…! Good job, everyone! :)
  • user avatar
    d i s s o l v e (config-r edition, not a full dissolve) #StyleGAN3
    00:00
  • user avatar
    If Stable Diffusion 2.0 doesn't know your favorite artist, you can search for similar artists on rom1504.github.io/clip-retrieval and try prompting with them instead. For instance here are several Rutkowski-like artists: Raphael Lacoste, Andreas Rocha, Titus Lunter, Richard Anderson.
  • user avatar
    I've trained a latent diffusion upscaler for the Stable Diffusion autoencoder (and anything you feel like feeding into it if you can tolerate a little artifacts) in collaboration with @StabilityAI. Try the Colab written by @nshepperd1 here: colab.research.google.com/drive/1o1qYJcF…
  • user avatar
    I have a new Colab notebook, “Reinforcement Learning from AI Feedback” (colab.research.google.com/drive/1sRKX3fM…), which fine-tunes a language model (Pythia 160M) using natural language criteria for its sampled outputs. Standalone version for larger models below. Have fun, report bugs! :)
  • user avatar
    Hourglass + Diffusion = ❤️ We introduce a new transformer backbone for diffusion models that can directly generate megapixel images without the need for multiple stages like latent diffusion. Read here! → arxiv.org/abs/2401.11605 Project page → crowsonkb.github.io/hourglass-diff…
  • user avatar
    a propaganda poster for building a space elevator