New AI tool lets users generate hi-res images on their own computer
A new tool promises to bring low-cost, high-resolution artificial intelligence (AI) image generation to a wider audience. It can achieve this without powerful computers behind a paywall.
Up until now, to create a high-quality AI image, users had to subscribe to a service like Midjourney or DALLE-3, or buy their own very powerful computers.
DemoFusion, developed at the Surrey Institute for People-Centred AI, lets users generate a basic image using a freely-available, open source AI model like Stable Diffusion, then enhance it, adding more detail and features, at much higher resolution. The necessary computing power is available on any mid-range gaming PC or a Mac M1.
To achieve high-resolution results using ordinary, open-source AI tools, the team first generated low-resolution images, then enhanced them. This is not an upscaling method – but instead coaxes more detail out of the AI model, by working across the image in patches, improving detail and resolution by at least 16 times.
The new technique is described in a paper, “DemoFusion: Democratising High-Resolution Image Generation with No $$$” (PDF).
Featured Academics
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