Get the latest tech news
AI model for near-instant image creation on consumer-grade hardware
Surrey announces world's first AI model for near-instant image creation on consumer-grade hardware A groundbreaking AI model that creates images as the user types, using only modest and affordable hardware, has been announced by the Surrey Institute for People-Centred Artificial Intelligence (PAI) at the University of Surrey. The model, NitroFusion, represents a world first and has been made open source by its developers – SketchX, a lab within PAI – a move that fundamentally transforms access to AI-enabled image creation models for creative professionals.
However, NitroFusion runs on a single consumer-grade graphics card – marking a decisive step forward in bringing advanced AI capabilities to individual creators, small studios, and educational institutions. NitroFusion leverages a novel dynamic adversarial framework that works like a panel of specialised art critics, each evaluating different aspects of the generated image to ensure high quality in a single step. With this distinctive approach, PAI builds on Surrey's track record of collaboration with industry, the public sector, government and other relevant institutions to develop solutions to shared challenges.
Or read this on Hacker News
