{"id":600076,"date":"2023-12-05T18:50:14","date_gmt":"2023-12-05T15:50:14","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/new-ai-tool-aims-to-democratise-high-res-image-generation\/"},"modified":"2023-12-05T18:50:14","modified_gmt":"2023-12-05T15:50:14","slug":"new-ai-tool-aims-to-democratise-high-res-image-generation","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/new-ai-tool-aims-to-democratise-high-res-image-generation\/","title":{"rendered":"#New AI tool aims to democratise high-res image generation"},"content":{"rendered":"
\n In the world of AI image generation, tools like DALL-E and Midjourney are holding the crown \u2014 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.<\/p>\n

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

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.<\/p>\n

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\u00d71024. DemoFusion enables 4x, 16x, or even higher increase in resolution \u2014 with a few simple lines of code and without any additional training. The only trade-off according to the team is \u201ca little more patience.\u201d We tried it at TNW and it\u2019s about six minutes.<\/p>\n

\"SDXL
Credit: University of Surrey<\/figcaption>
<\/a>On the left side: the result by SDXL. On the right side, the result by DemoFusion. Credit: University of Surrey<\/figcaption>