A deepfake algorithm for augmented reality — it generates any character moves based on 10 secords video.

A fantastic article by Amy Goodchild about the nature of generative art. She digs into three key pillars: randomness, rules, and natural systems.

A generative encyclopedia of imaginary sea creatures. It consists of an infinite numbers of potential underwater life forms.

Brilliant thinking by Alexander Wales on how tools like DALL-E and Midjourney influence professional illustrators and artists. It'll kick the economy of these professions in the stomach for sure. However, art as self-expression will stay for sure. Erik Hoel has a similar take.

Aaron Hertzmann draws interesting parallels between today's algorithm-driven design tool boom and other branches of arts and culture for past centuries. He thinks current state is just interim and shows on-spot analogies.

This experiment shows how words like "assertive" and "gentle" are mapped to stereotypes and biases in models like Stable Diffusion and DALL-E 2 (review). Bloomberg has a good long-read article about this problem.

Matthew Ström generates Open Graph images for his blog.

‍

Graeme Fulton explores how photo stocks work with generated images. New products like Prompt Hero & GhostlyStock emerge, while classic companies are taking little steps: Shutterstock partners with DALL-E 2, Adobe Stock opened submissions with limitations (you can't copy an existing style). Another review by Alina Valyaeva.

Another tools from OpenAI creates a 3D object via a text prompt. See their other project Shap-E and similar tools like Neural3D.

Type a rough description of a scene and it will generate a short video matching this text. Google Imagen Video and Nvidia Align Your Latents are similar concepts.