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

This logo constantly redraws itself. Designer Talia Cotton wanted to create an unbiased logo, so she put an algorithm to work.

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

Hannah Johnston compares principles of popular prompt-based image generators like DALL·E, Midjourney & Google Collab models. How they work and what artists think about it.

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

It helps to generate 3D objects for virtual worlds. You can get a whole series of cars, animals, furniture, or other items that are varied, but still a part of a family.

Artists can search machine learning databases for links to their work and flag them for removal. It's a part of a bigger Spawning initiative — they're building tools for artist ownership of their training data, allowing them to opt into or opt out of the training of large AI models, set permissions on how their style and likeness is used, and offer their own models to the public.

The tool creates realistic photos and illustrations from a text description based on GPT-3. It started simple, but then became one of the hottest movements. Its simplified version exploded into a meme generator (see also Wordle mashup). There are prompt generators for better results (more like that), although these personal explorations (another one) are amazing. There are similar concepts like Google Imagen or Disco Diffusion. Professional illustrators discuss risks & possibilities, but not all of them are worried. Microsoft put a serious bet on it and included DALL-E into Azure Cloud.

It helps to autocomplete code. It's built into popular IDEs like Visual Studio Code and JetBrains; you can voice-control it too. They analyzed GitHub repositories for training (however, it's controversial to sell open source work results — which led to a class-action). CopilotX is even more powerful.

Abstract art generator via text prompt. It's one of the most spectacular and it's launched before DALL-E-like models.