Imagen: Text-to-Image Generation Using Diffusion Models - Lecture 9
University of Central Florida via YouTube
Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the innovative Imagen text-to-image diffusion model in this 29-minute lecture from the University of Central Florida. Delve into key components such as the text encoder, efficient unit, and convolution order. Examine the diffusion model's architecture, including static and dynamic thresholding techniques. Analyze qualitative results and thresholding outcomes. Investigate upsampling methods and noise level conditioning. Gain valuable insights into cutting-edge AI-powered image generation techniques and their practical applications.
Syllabus
Introduction
Text Encoder
Efficient Unit
Convolution Order
Efficiency
XR
Diffusion Model
Static Thresholding
Dynamic Thresholding
Qualitative Results
Thresholding Results
Upsampling
Noise Level Conditioning
Conclusion
Taught by
UCF CRCV