San Francisco: Chip maker Qualcomm has showcased the world’s first demonstration of Stable Diffusion on an Android gadget to additional enhance its efforts in working with AI.

Stable Diffusion is a deep studying, text-to-image basis mannequin, first created in 2022 and is often used to generate detailed pictures primarily based on textual content descriptions inside tens of seconds, as seen on ‘DALL-E’ and different comparable on-line platforms.

For the primary time, Qualcomm’s AI Research group carried out full-stack AI optimisations utilizing the corporate’s AI Stack to deploy Stable Diffusion on an Android smartphone powered by its Snapdragon 8 Gen 2 platform.

“For Stable Diffusion, we started with the FP32 version 1-5 open-source model from Hugging Face and made optimisations through quantisation, compilation, and hardware acceleration to run it on a phone powered by Snapdragon 8 Gen 2 Mobile Platform,” the corporate mentioned in a blogpost.

Qualcomm’s AI stack software program employs synthetic intelligence with assist for a various vary of clever devices, together with cellular, automotive, IoT, cloud platforms, and others.

This demonstration primarily allowed a smartphone to generate a picture render primarily based on textual content descriptions in lower than 15 seconds.

“Our one technology roadmap allows us to scale and utilise a single AI stack that works across not only different end devices but also different models,” Qualcomm mentioned.

“This means that the optimisations for Stable Diffusion to run efficiently on phones can also be used for other platforms like laptops, XR headsets, and virtually any other device powered by Qualcomm Technologies,” it added.