Lakonik / GMFlow

What it does

• Gaussian Mixture Output. GMFlow expands the network's output layer to predict a Gaussian mixture (GM) distribution of flow velocity. Standard diffusion/flow matching models are special cases of GMFlow with a single Gaussian component.
• Precise Few-Step Sampling. GMFlow introduces novel GM-SDE and GM-ODE solvers that leverage analytic denoising distributions and velocity fields for precise few-step sampling.
• Improved Classifier-Free Guidance (CFG). GMFlow introduces a probabilistic guidance scheme that mitigates the over-saturation issues of CFG and improves image generation quality.
• Efficiency. GMFlow maintains similar training and inference costs to standard diffusion/flow matching models.