Skip to content
Global sound
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

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

· 52 min · Episode 753

Show notes

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 model guides the training of an efficient, single-step student model. We explore the architecture and training, including the use of a secondary 'coach' network that aligns the student's denoising function with the teacher's, allowing the model to bypass the iterative process entirely. Finally, we discuss how these efficiency breakthroughs pave the way for personalized on-device agents and the challenges of running reasoning models with techniques like inference-time scaling under a fixed compute budget.

The complete show notes for this episode can be found at https://twimlai.com/go/753.

Website: twimlai.com

Live, last hour: 10,992 songs on 5,729 stations in 143 countries

Discover the world through radio

More ways to discover (9)

Heard something good? Save it, or open it straight away in Spotify.

★ Artist of the week The fastest riser on the radio this week
Your song here? From € 9 per week →
D99 98.9 FM MonterreyContinue listening