We asked a new kind of AI art tool to make 'paintings' of Australia
The images are so crafted and "painterly" that you may not realise at first they have been dreamed up by a machine in just a few minutes.
These images are the product of a new AI-generated art scene that's exploded thanks to the development of free and easy-to-use tools that require (at the very least) short text prompts to create unique pictures.
These images are hard to classify — they're part artwork, part a function of computer coding, part glimpse into some collective, online unconscious that maps the associations between images and words.
The engine behind CLIP+VQ-GAN consists of two neural networks – algorithms designed to mimic a human brain – one of which classifies images (CLIP) and one that generates images (VQ-GAN)
CLIP is trained to recognise images using a mountain of raw data drawn from the internet, where people routinely upload images and identify them with captions.
/cdn.vox-cdn.com/uploads/chorus_asset/file/24801728/Screenshot_2023_07_21_at_1.45.12_PM.jpeg)
