How Diffusion Models Generate Images

Table of Links

Abstract and 1 Introduction

2 Improving Stable Diffusion

2.1 Architecture & Scale

2.2 Micro-Conditioning

2.3 Multi-Aspect Training

2.4 Improved Autoencoder and 2.5 Putting Everything Together

3 Future Work

Appendix

A Acknowledgements

B Limitations

C Diffusion Models

D Comparison to the State of the Art

E Comparison to Midjourney v5.1

F On FID Assessment of Generative Text-Image Foundation Models

G Additional Comparison between Single- and Two-Stage SDXL pipeline

References

C Diffusion Models

Sampling. In practice, this iterative denoising process explained above can be implemented through the numerical simulation of the Probability Flow ordinary differential equation (ODE) [47]

Classifier-free guidance. Classifier-free guidance [13] is a technique to guide the iterative sampling process of a DM towards a conditioning signal c by mixing the predictions of a conditional and an unconditional model

where w ≥ 0 is the guidance strength. In practice, the unconditional model can be trained jointly alongside the conditional model in a single network by randomly replacing the conditional signal c with a null embedding in Eq. (3), e.g., 10% of the time [13]. Classifier-free guidance is widely used to improve the sampling quality, trading for diversity, of text-to-image DMs [30, 38]