Kyle Steinfeld

@ksteinfe

UC Berkeley Department of Architecture; he/his

UC Berkeley
Vrijeme pridruživanja: rujan 2008.

Tweetovi

Blokirali ste korisnika/cu @ksteinfe

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @ksteinfe

  1. proslijedio/la je Tweet
    22. sij

    If I had to pick a favorite old-school algorithmic artist, I'd probably go with Roman Verostko:

    Poništi
  2. proslijedio/la je Tweet
    22. sij

    Had to try a few Piranesi etchings in Veduta degli avanzi di antiche fabbriche alle falde dell'Aventino sulla strada detta di Marmorata Veduta della vasta Fontana di Trevi anticamente detta l'Acqua Vergine Veduta della Basilica di S. Giovanni Laterano

    Poništi
  3. proslijedio/la je Tweet
    26. lis 2019.

    This is an example of the DeepSDF network learning the shape of a single chair:

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    16. sij

    Latent depths revisited in Stacked interpolation frames with opacity inverse to brightness Historic floor plan dataset × StyleGAN

    Poništi
  5. 18. pro 2019.
    Poništi
  6. 14. pro 2019.

    A bananagram from NeurIPS creativity workshop

    Poništi
  7. proslijedio/la je Tweet
    12. stu 2019.

    Tonight! Come learn more about the new@UC Berkeley MDes •-november-12

    Poništi
  8. proslijedio/la je Tweet
    12. lis 2019.
    Poništi
  9. proslijedio/la je Tweet

    Wow, this is cool: The duck-rabbit illusion apparently works on Google Cloud Vision. The system interprets it one way or the other, depending on the orientation of the image.

    Prikaži ovu nit
    Poništi
  10. 22. lis 2019.
    Poništi
  11. 22. lis 2019.
    Poništi
  12. proslijedio/la je Tweet
    4. lis 2019.

    The 19-stroke SPIRAL agent for the oil paint simulator is now available on ! Enjoy 🎨🖌🤖 For usage instructions see The pre-trained snapshot is here:

    Poništi
  13. proslijedio/la je Tweet
    24. ruj 2019.
    Poništi
  14. proslijedio/la je Tweet
    20. ruj 2019.

    I encourage everyone to use the 'Wizard' tag on -- eventually tags will be turned into 'genes' that can added or removed to any image. The flowing robes, the posture, the creepy faces; I think we all know how to tag a wizard. More:

    Poništi
  15. proslijedio/la je Tweet
    6. ruj 2019.

    For all the lovers out there: I made a notebook to convert low-res models to higher resolution checkpoints so you can continue training! Who likes low-res anyway?😋

    , , i još njih 5
    Poništi
  16. proslijedio/la je Tweet

    Inverse search for a previously generated image across the entire 1128-dimensional latent space starting from a random vector.

    Prikaži ovu nit
    Poništi
  17. 10. srp 2019.
    Poništi
  18. 6. srp 2019.

    A closer look at those animated walks through the latent space of Streetview imagery I've been posting recently.

    Poništi
  19. proslijedio/la je Tweet
    3. srp 2019.

    Introducing Zizi, the AI generated drag persona! 💋💅🌈 Part of an upcoming performance project thinking about a queer AI & lack of representation in datasets.

    Prikaži ovu nit
    Poništi
  20. 2. srp 2019.

    Instrumentalizing our collective gaze: synthetic 3d rendered scenes trained on tourist photos of European monuments.

    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·