The paradox of diffusion distillation (2024)
Thoughts on the tension between iterative refinement as the thing that makes diffusion models work, and our continual attempts to make it _less_ iterative.
Summary
The article discusses the conflicting nature of diffusion models, highlighting how their success relies on iterative refinement while efforts are being made to streamline the process. It raises important questions about the balance between efficiency and effectiveness in model development.
Comments (1 of ) ⌛