Classifier-Free Diffusion Guidance

By Jonathan Ho. 2022

6,753 citations recorded by the source corpus.

Classifier guidance is a recently introduced method to trade off mode coverage and sample fidelity in conditional diffusion models post training, in the same spirit as low temperature sampling or truncation in other types of generative models. Classifier guidance combines the score estimate of a diffusion model with the gradient of an image classifier and thereby requires training an image classifier separate from the diffusion model. It also raises the question of whether guidance can be performed without a classifier. We show that guidance can be indeed performed by a pure generative model without such a classifier: in what we call classifier-free guidance, we jointly train a conditional and an unconditional diffusion model, and we combine the resulting conditional and unconditional score estimates to attain a trade-off between sample quality and diversity similar to that obtained using classifier guidance.

Subfields: Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Ming-Hsuan Yang
  3. Dacheng Tao
  4. Xiaogang Wang
  5. Trevor Darrell
  6. Jitendra Malik
  7. Andrea Vedaldi
  8. Andrew Zisserman

In Statistical and Nonlinear Physics

  1. Arash Vahdat
  2. Karsten Kreis
  3. Stefano Ermon
  4. Jonathan Ho
  5. Yang Song
  6. Sergey Levine
  7. David J. Fleet
  8. Prafulla Dhariwal

In Generative Models

  1. Arash Vahdat
  2. Jun-Yan Zhu
  3. Richard Zhang
  4. Eli Shechtman
  5. Stefano Ermon
  6. Karsten Kreis
  7. Alexei A. Efros
  8. Daniel Cohen-Or

Citations in the corpus