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 …

Þessi þáttur hefur ekki verið afritaður ennþá

Notaðu STT.ai til að afrita þennan þátt með AI.Fáðu nákvæman texta með hátalaragreiningu, tímastimpil og flytja út í mörgum sniðum.

Hátalaragreining Tímastimpill á orðastigi Flytja út sem SRT, TXT, JSON

Fleiri þættir