Diffusion models achieve high-quality image generation but are limited by slow iterative sampling. Distillation methods alleviate this by enabling one- or few-step generation. Flow matching, originally introduced as a distinct framework, has since been shown to be theoretically equivalent to diffusion under Gaussian assumptions, raising the question of whether distillation techniques such as score distillation transfer directly. We provide a simple derivation — based on Bayes’ rule and conditional expectations — that unifies Gaussian diffusion and flow matching without relying on ODE/SDE… Read More
Score Distillation of Flow Matching Models
Diffusion models achieve high-quality image generation but are limited by slow iterative sampling. Distillation methods alleviate this by enabling one- or few-step generation. Flow matching, originally introduced as a distinct framework, has since been shown to be theoretically equivalent to diffusion under Gaussian assumptions, raising the question of whether distillation techniques such as score distillation transfer directly. We provide a simple derivation — based on Bayes’ rule and conditional expectations — that unifies Gaussian diffusion and flow matching without relying on ODE/SDE…
Related Posts
Here are 5 ways to feast, celebrate and explore with Google Arts & Culture.
This holiday season, transform screen-time into a festive cultural journey with Google Arts & Culture's…
The Machine Learning Practitioner’s Guide to Model Deployment with FastAPI
If you’ve trained a machine learning model, a common question comes up: “How do…
The CMA’s designation of Google’s mobile ecosystem
We are disappointed by the CMA’s designation of an open mobile ecosystem with strategic market…