Generative AI has taken the world by storm, but the need for finetuned and customized models on edge devices is growing. In this MWC 2024 technology demo, Qualcomm AI Research is showcasing its first demonstration of Low Rank Adaptation (LoRA) on an Android smartphone. Running Stable Diffusion with LoRA, users can create high-quality custom images based on personal or artistic preferences. LoRA reduces the number of trainable parameters of AI models, enabling greater efficiency, scalability, and customization of on-device generative AI use cases. Our full-stack AI optimization helps to achieve high performance at low power and fast switching between adapters. Beyond enabling fine-tuned language vision models (LVMs) for different artistic styles, LoRA is broadly applicable for customized AI models, such as large language models (LLMs), to create tailored personal assistants, improved language translation, and more.
Visit the Qualcomm AI Research website https://www.qualcomm.com/research/art...
Develop with the Qualcomm AI Stack
https://www.qualcomm.com/products/tec...
Sign up for our newsletter
https://assets.qualcomm.com/mobile-co...