{"id":11320,"date":"2024-06-19T19:51:36","date_gmt":"2024-06-20T02:51:36","guid":{"rendered":"https:\/\/mattfife.com\/?p=11320"},"modified":"2024-08-31T14:21:50","modified_gmt":"2024-08-31T21:21:50","slug":"create-a-playable-game-from-a-single-image","status":"publish","type":"post","link":"https:\/\/mattfife.com\/?p=11320","title":{"rendered":"Create a playable game from a single image"},"content":{"rendered":"\n

Google researchers<\/a> have published a new artificial intelligence model that can take a text prompt, sketch or idea and turn it into a virtual world you can interact with and play.<\/p>\n\n\n

\n
\"\"<\/figure>\n<\/div>\n\n\n

Named Genie<\/a>, the virtual world model was trained on gameplay and other videos found online and is currently a research preview. The games are 2D platformer style games.<\/p>\n\n\n\n

\n

Genie can be prompted with images it has never seen before, such as real world photographs or sketches, enabling people to interact with their imagined virtual worlds-\u2013essentially acting as a foundation world model. This is possible despite training without any action labels<\/strong>. Instead, Genie is trained from a large dataset of publicly available Internet videos. We focus on videos of 2D platformer games and robotics but our method is general and should work for any type of domain, and is scalable to ever larger Internet datasets. <\/p>\n<\/blockquote>\n\n\n\n

Links:<\/p>\n\n\n\n