New AI tool aims to democratise high-res image generation

Key Takeaways:

– DALL-E and Midjourney are leading AI image generation tools
– These tools require significant investment and resources, leading to centralized services and pay-per-use access
– The University of Surrey has developed DemoFusion to democratize high-res image generation
– DemoFusion allows users to generate high-quality images without the need for a subscription or powerful computer
– It is an extension of the SDXL open-source model, enabling increased resolution with a few lines of code
– The trade-off is a slightly longer processing time
– The technique involves generating low-res images and enhancing them using progressive upscaling
– The goal is to make AI-generated images accessible to everyone
– DemoFusion is publicly available online
– It is an important step in opening up AI image generation to the public and the wider tech community.

The Next Web:

In the world of AI image generation, tools like DALL-E and Midjourney are holding the crown — and not simply because of their high-resolution performance. The training of these models requires such substantial investment and resources that it inevitably leads to centralised services and pay-per-use access.

A new AI tool developed by the University of Surrey aims to reverse this trend and democratise the technology, by opening up high-res image generation to a wider audience.

Dubbed DemoFusion, the model allows users to generate high-quality images without the need to subscribe to a service, or own a very powerful computer. In fact, the system only requires consumer-grade RTX 3090 GPU that can be found in any mid-range gaming PC or a Mac M1.

The AI is essentially a plug-and-play extension to the Stable Diffusion XL (SDXL) open-source model, which generates images at a resolution of 1024×1024. DemoFusion enables 4x, 16x, or even higher increase in resolution — with a few simple lines of code and without any additional training. The only trade-off according to the team is “a little more patience.” We tried it at TNW and it’s about six minutes.

Credit: University of Surrey