Classifier-Free Guidance
Concept
A technique for guided generation that defines an implicit classifier based on conditioned and unconditioned generation networks, removing the need for a separate classifier.
Mentioned in 2 videos
Save the 2 videos on Classifier-Free Guidance to your own pod.
Sign up free to keep building your knowledge base on Classifier-Free Guidance as more episodes are added.
Videos Mentioning Classifier-Free Guidance
Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 4 - Latent Space & Guidance
Stanford Online
A technique for guided generation that defines an implicit classifier based on conditioned and unconditioned generation networks, removing the need for a separate classifier.
Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 5 - Architectures
Stanford Online
A method to condition the generation process, allowing models to emphasize more on the input prompt by predicting noise or velocity twice with a guidance factor.