Lenovo licenses fast, private image-generation model developed through Surrey collaboration

An AI image-generation model that will bring high-quality, private image creation to Lenovo’s upcoming on-device AI has been developed by researchers at the University of Surrey’s Institute for People-Centred AI in collaboration with artificial intelligence company Stability AI. The technology, called Stable Diffusion 3.5 Flash (SD3.5-Flash), enables fast, unlimited text-to-image creation to run directly on consumer devices without relying on cloud connection. 

Unlike conventional AI diffusion models that require 30 to 50 processing steps, SD3.5-Flash can generate images in just four, making it both significantly faster and lightweight enough to run on mobile phones, tablets and laptops – while also reducing the energy and water demands associated with cloud-based AI.  

Lenovo has now licensed the model from Stability AI for integration into its upcoming Personal Ambient Intelligence platform, Qira. 

The model was created by Surrey doctoral researcher, Hmrishav Bandyopadhyay, during a university placement internship at Stability AI, with the core idea shaped through work in the SketchX Lab at the Surrey Institute for People-Centred AI (PAI).  

Hmrishav said: 

“Our SD3.5-Flash model allows users to create images from text descriptions entirely on their device, with no data leaving their hardware. Achieving this level of efficiency is technically challenging, as it requires compressing a diffusion model to run in only a few steps while maintaining quality. It’s a great example of how academic research and industry collaboration can push the field forward, and it’s incredibly rewarding to know the technology will be used by millions of people worldwide.” 

The work builds on the team’s SD3.5-Flash research paper, which outlines how large diffusion models – generative AI that creates images – can be compressed into highly efficient versions without compromising image quality. It forms part of a wider programme of research within PAI’s SketchX Lab to make generative AI faster and more practical for real-world use, following earlier projects such as NitroFusion that explored high-fidelity single-step diffusion. 

Professor Yi-Zhe Song, Director of SketchX Lab and Co-Director of the University of Surrey’s Institute for People-Centred AI, said:  

“At Surrey, we believe AI shouldn’t be limited to data centres and cloud infrastructure; it should run locally on the devices people use every day. SD3.5-Flash puts a powerful creative tool directly in users’ hands while keeping their data private and reducing the energy demands associated with cloud processing. For AI to be genuinely useful and responsible, it needs to be local, efficient and accessible to everyone.” 

Professor Adrian Hilton, Founder and Director of the Surrey Institute for People-Centred AI, added:  

“The model reflects the University of Surrey’s people-centred approach to AI, which focuses on designing technologies that are trustworthy, inclusive and easy for people to use in their everyday lives. This approach helps ensure that advanced AI tools are not only powerful, but also transparent, energy-efficient and accessible to a much wider range of people, supporting greater trust and confidence in how AI is deployed” 

The work also highlights the opportunities available to Surrey students to gain hands-on industry experience during their studies, contributing to real-world projects while developing the technical and professional skills needed for future careers that serve society.  

[ENDS] 

Notes to editors 

• Professor Yi-Zhe Song and Hmrishav Bandyopadhyay are available for interview; please contact mediarelations@surrey.ac.uk to arrange. 

• The full paper can be found here: https://arxiv.org/abs/2509.21318