press release
Published: 10 December 2024

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.  

Nitro_Fusion

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. 

NitroFusion represents a paradigm shift in making AI accessible to everyone, eliminating the need for large compute resources and the long waiting times between prompt and result that are common with most image generation platforms. Professor Yi-Zhe Song, Co-Director Surrey Institute for People-Centred AI; Programme Lead of MSc in Artificial Intelligence

Typically, similar technology is available only to corporate giants with vast computing resources. 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. The almost instant creation of images allows rapid artistic iterations and greater control over the generated imagery.  

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. The system's flexible architecture allows users to optionally use between one to four refinement steps, providing direct control over the balance between generation speed and image quality." Dar-Yen Chen, the PhD researcher who helped to develop the project at PAI
With NitroFusion, we're not just releasing another image generation model – we're pioneering an entirely new approach which democratises AI interaction.

Following our DemoFusion release last year, which provided a new way to upscale AI-generated images, this innovation further establishes our position at the forefront of making powerful AI technology accessible to all. Professor SonG added

This breakthrough delivers multiple leaps for the users and industry: 

  • Instant image generation that responds as users type – a first in the field – enabling rapid iteration, greater control and better experimentation 
  • Improved sustainability through greatly reduced energy consumption 
  • Consumer-grade affordable hardware requirements (e.g. a single high-performance GPU) that mean individuals and small studios can create imagery affordably 
  • Open-source availability enables global innovation, adaptation and variations 
  • No cloud dependencies or subscription fees. 
We believe we're the first in the world to achieve interactive image generation at this scale and efficiency. This opens up access to state-of-the-art AI for image generation and is just the beginning of our commitment to democratising creative AI tools. Our Institute will continue to develop open-source, groundbreaking technologies that put professional-grade AI capabilities into the hands of creators everywhere.

We're particularly proud of the great work that our SketchX Lab, creating new concepts and advancing the science of generative AI. Our research is focused on ensuring that the future of creative AI technology is inclusive, responsible and accessible to all, and we're keen to continue to work with organisations that share this ethos. Professor Adrian Hilton, Director Surrey Institute for People-Centred AI | Director of Centre for Vision, Speech and Signal Processing

The technology is available immediately through https://chendaryen.github.io/NitroFusion.github.io/, with comprehensive documentation and community support resources. 

Notes to editors 

About the Surrey Institute for People-Centred AI (PAI) 

Taking a different approach to much AI activity in the UK, the Surrey Institute for People-Centred AI puts the needs of individuals and society at the very heart of everything it does: we believe that the starting point for AI should be people rather than technology.   

This people-centred approach drives our research and enables us to design AI technologies and systems that are ethical, responsible, and inclusive. The pan-University Institute brings together Surrey's core AI-related expertise in vision, speech and signal processing, computer science, and mathematics, with its domain expertise across engineering and physical sciences, human and animal health, law and regulation, business, finance and the arts and social sciences. 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.   

To find more details, visit surrey.ac.uk/ai or follow @peoplecentredai 

About SketchX  

SketchX is a world-leading computer vision and AI research group within the Institute for People-Centred AI and the Centre for Vision, Speech and Signal Processing at the University of Surrey.  The group is led by Prof. Yi-Zhe SonG and specialises in pioneering AI technologies that push the boundaries of creative and interactive applications. About the Surrey Institute for People-Centred AI. 

Share what you've read?

Featured Academics

Yi-Zhe Song

Prof Yi-Zhe Song

Co-Director Surrey Institute for People-Centred AI; Programme Lead of MSc in Artificial Intelligence
Adrian Hilton

Prof Adrian Hilton

Director Surrey Institute for People-Centred AI | Director of Centre for Vision, Speech and Signal Processing

Media Contacts

External Communications and PR team
Phone: +44 (0)1483 684380 / 688914 / 684378
Email: mediarelations@surrey.ac.uk
Out of hours: +44 (0)7773 479911