TFG: Unified Training-Free Guidance for Diffusion Models
This work addresses the challenge of training-free guidance for conditional generation in diffusion models, providing a solid foundation for researchers and practitioners, though it is incremental as it builds upon existing methods.
The paper tackles the problem of generating samples with desired properties using unconditional diffusion models without additional training, by introducing a unified algorithmic framework that improves performance by 8.5% on average across extensive benchmarks.
Given an unconditional diffusion model and a predictor for a target property of interest (e.g., a classifier), the goal of training-free guidance is to generate samples with desirable target properties without additional training. Existing methods, though effective in various individual applications, often lack theoretical grounding and rigorous testing on extensive benchmarks. As a result, they could even fail on simple tasks, and applying them to a new problem becomes unavoidably difficult. This paper introduces a novel algorithmic framework encompassing existing methods as special cases, unifying the study of training-free guidance into the analysis of an algorithm-agnostic design space. Via theoretical and empirical investigation, we propose an efficient and effective hyper-parameter searching strategy that can be readily applied to any downstream task. We systematically benchmark across 7 diffusion models on 16 tasks with 40 targets, and improve performance by 8.5% on average. Our framework and benchmark offer a solid foundation for conditional generation in a training-free manner.