Flow MatchingFlow Matching
Flow Matching
学一个从噪声到数据的连续速度场,用常微分方程把噪声推成样本。Learn a continuous velocity field from noise to data and push noise into samples with an ODE.
训练时让模型回归「从噪声点指向数据点」的速度,而不是直接预测噪声或像素。
推理时从噪声出发,沿速度场积分若干步,得到样本。
它是扩散模型之外的连续生成框架;Stable Diffusion 3、Flux 等图像模型采用了 rectified flow 变体。
Training regresses the velocity from a noise point toward a data point, rather than predicting noise or pixels directly.
Inference starts from noise and integrates the velocity field for a number of steps.
A continuous generative framework beside diffusion; Stable Diffusion 3 and Flux use rectified-flow variants.
扩散模型要很多步采样,Flow Matching 把「走哪条路」学得更直,步数可以更少;理解它,才能看懂 2025–2026 图像 / 视频生成模型为什么普遍从「扩散」转向「流」。Diffusion needs many sampling steps; Flow Matching learns a straighter path, so fewer steps can suffice. It explains why image and video generators moved from “diffusion” to “flow” in 2025–2026.
回到名词地图看第6站的其他 36 个词 →Back to the map: the other 36 terms in station 6 →