This training explores the principles behind multimodal generative AI, focusing on text-to-video diffusion models and their practical applications.

We will begin by defining multimodal generative AI and examining the core mechanisms of text-to-video synthesis.Participants will gain insights into building an interactive text-to-video generation pipeline using Gradio, leveraging multi-GPU processing, and optimizing performance with NVIDIA NeMo Framework for faster video generation.

Who Should Attend?

• Developers
• AI/ML Engineers
• Solution Architects
• Data Scientist

Prerequisite: Bring your laptop to participate fully in this hands-on workshop.

Additionally to this workshop, NVIDIA is hosting the session "Unlocking a New Era of Startup Opportunities with Generative AI" on April 8 - for more information and registration details, please click here.