Elsewhere I put my pal Seamus (who’s presently sawing logs on the couch next to me) through NVIDIA’s somewhat wacky GANimal prototype app, attempting to mutate him into various breeds—with semi-Brundlefly results. 👀
On Monday I mentioned my new team’s mind-blowing work to enable image synthesis through typing, and I noted that it builds on NVIDIA’s StyleGAN research. If you’re interested in the latter, check out this two-minute demo of how it enables amazing interactive generation of stylized imagery:
This new project called StyleGAN2, developed by NVIDIA Research, and presented at CVPR 2020, uses transfer learning to produce seemingly infinite numbers of portraits in an infinite variety of painting styles. The work builds on the team’s previously published StyleGAN project. Learn more here.
It’s cool to see these mobile creativity apps Voltron-ing together via the new Adobe Design Mobile Bundle, which includes the company’s best design apps for the iPad at 50% off when purchased together. Per the site:
Photoshop: Edit, composite, and create beautiful images, graphics, and art.
Illustrator: Create beautiful vector art and illustrations.
Fresco: Draw and paint with thousands of natural brushes.
Spark Post: Make stunning social graphics — in seconds.
Creative Cloud: Mobile access to your Creative Cloud assets, livestreams, and learn content.
Then, there are live oil brushes in Fresco that you just don’t get in any other app. In Fresco, today, you can replicate the look of natural media like oils, watercolors and charcoal — soon you’ll be able to add motion as well! We showed a sneak peek at the workshop, and it blew people’s minds.
Apropos of nothing, check out 60 lovingly rendered seconds commissioned by YouTube:
Maciej Kuciara writes,
MECHA – the love letter to our youth. Watching anime classics as kids left a mark that stayed with us to this day. So we felt it’s due to time to celebrate our love to mecha and pay proper homage with this piece we did for YouTube.
What happens if you train an ML model from hundreds of thousands of 2D renders of 3D creature models? Glad you asked!
Today, we present Chimera Painter, a trained machine learning (ML) model that automatically creates a fully fleshed out rendering from a user-supplied creature outline. Employed as a demo application, Chimera Painter adds features and textures to a creature outline segmented with body part labels, such as “wings” or “claws”, when the user clicks the “transform” button.