The Checkpoint issue #4 – AI art news and inspiration
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.

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.
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.