TWIML AI Podcast
TWIML AI Podcast

High-Efficiency Diffusion Models for On-Device Image Generation and Editing with Hung Bui - #753

Oct 28, 2025 · 52m

In this episode, Hung Bui, Technology Vice President at Qualcomm, joins us to explore the latest high-efficiency techniques for running generative AI, particularly diffusion models, on-device. We dive deep into the technical challenges of deploying these models, which are powerful but computationally expensive due to their iterative sampling process. Hung details his team's work on SwiftBrush and SwiftEdit, which enable high-quality text-to-image generation and editing in a single inference step. He explains their novel distillation framework, where a multi-step teacher …

Qeybtan weli lama soo gudbin

isticmaal STT.ai in ay ku qoran qaybtan la AI. hel qoraalka saxda ah la hadalka ogaadaan, timestamps, iyo dhoofinta qaabab badan.

Ogaanshaha hadalka Waqtiga erey-ka-dhexdhexaadka ah Soo bixi sida SRT, TXT, JSON

Faallo dheeraad ah