The Checkpoint issue #4 – AI art news and inspiration

May 2, 2022

News

DALLE2-pytorch – The amazing Lucidrains (Phil Wang) has started an open-source implementation of DALLE2. Still a long way to go, but very exciting news.

Pytti tools v0.10 released – Big update to my favourite notebook. New features include audio reactivity, new Clip model and more.

MyStyle – New new model from Google Research and Tel-Aviv University able to perform face-based image in-painting, super-resolution and editing.

NVIDIA NeRF – A neural rendering model that learns a high-resolution 3D scene in seconds — and can render images of that scene in a few milliseconds. Press release | Github | Colab

PHORHUM – New from Google, create fully animatable 3D human models from a single photo.

multimodal ai art @multimodalart

AI art reminds me of the evolution of console graphics. There are some generated images that last year I thought were mindblowing and revisiting I feel the same as when I revisit a PS1 game I thought ultra-realistic as a kid the difference is that we get a new console every week

Featured notebook – TortoiSe

New text-to-speech model with a focus on quality. I'm fascinated by the idea of potentially being able to explore the latent vector of sounds, for example blending between different voices mid-speech.

Get it:

Featured AI artist – @DMTFL_AI

An early adopter of VQGAN+CLIP, @DMTFL_AI creates animations and artworks that give classic 20th century abstract expressionism a Vaporwave twist.

The latest Tweets from Genovese Generatives (24 Styles by Vito Genovese) (@DMTFL_AI). est Apr 2021~ I've created 10,000+ GIFs using mainly VQGAN+CLIP and other AI-visual tools; 24 exhibit styles are in my showcase. I work in prints & commission. Tampa Bay, Florida

Thanks for reading!

If you have anything you'd like to be featured or want to get in touch, give me a shout on Twitter or via email. Please also consider supporting me on Patreon so that I can spend more time creating content like this.