Diverse Sampling in Diffusion Models with Marginal Preserving Particle Guidance
For practitioners of generative modeling, this method addresses the diversity-quality trade-off in diffusion models without requiring additional training or fine-tuning.
EDDY introduces a training-free guidance mechanism for diffusion models that improves sample diversity by using divergence-free dynamics to perturb particle trajectories while preserving marginal distributions, achieving better diversity-fidelity trade-offs in text-to-image generation.
We present EDDY (Exact-marginal Diversification via Divergence-free dYnamics), a guidance mechanism for diffusion and flow matching models that promotes diversity among samples generated while maintaining quality. EDDY exploits symmetries of the Fokker-Planck equation, using drift perturbations that change particle trajectories while preserving the evolving marginal distribution. We instantiate this principle through kernel-based anti-symmetric pairwise matrix fields, constructed from the repulsive directions. The resulting divergence-free dynamics promote diversity at the joint particle level while preserving each particle's marginal distribution without any additional training. As computing the guidance can be computationally expensive in cases such as text-to-image generation with perceptual embeddings, we propose practical approximations as an effective and efficient solution. Experiments on synthetic distributions and text-to-image generation show that EDDY improves diversity while maintaining strong distributional fidelity compared to common baselines.