Concept均值流 / pixel MeanFlow / pMF
MeanFlow
A generative modeling paradigm based on flow matching that parameterizes the average velocity along an entire trajectory as a single network output, enabling one-step forward inference for high-quality image synthesis. Compared to diffusion models, it substantially reduces the number of inference steps required.
Timeline (last 90 days)
Oct 9
MeanFlow is a generative modeling paradigm based on flow matching that parameterizes the average velocity of an entire trajectory as a single network output, theoretically enabling high-quality image synthesis in a single forward inference step.
Unverified50%