做图像生成的开发者终于有了理论扎实的引导方法——AdaMaG解决了CFG强引导下样本失真和幻觉问题，直接提升生成质量，建议做扩散模型的团队试试。
扩散和流生成模型依赖引导机制对齐样本与用户输入，但现有方法如无分类器引导（CFG）是启发式的速度/分数线性组合，忽略生成流形几何，导致概率不守恒，强引导下样本偏离流形。研究者通过连续性方程分析引导，将其分解为散度项和分数平行项，并证明散度项在接近数据流形时结构性地发散。基于此提出自适应流形引导（AdaMaG），通过时间依赖调度和分数平行衰减同时约束两项，无需额外推理成本。实验表明，AdaMaG在图像生成基准上提升真实感、减少幻觉，并在高引导强度下实现受控去饱和。
Probability-Conserving Flow Guidance
Diffusion and flow-based generative models dominate visual synthesis, with guidance aligning samples to user input and improving perceptual quality. However, Classifier-Free Guidance (CFG) and extrapolation-based methods are heuristic linear combinations of velocities/scores that ignore the generative manifold geometry, breaking probability conservation and driving samples off the learned manifold under strong guidance. We analyse guidance through the continuity equation and show its effect decomposes into a divergence term and a score-parallel term defined invariantly across parameterisations. We prove the divergence term blows up structurally as sampling approaches the data manifold, motivating a time-dependent schedule alongside score-parallel attenuation. The resulting plug-and-play rule, Adaptive Manifold Guidance (AdaMaG), bounds both terms at no additional inference cost. Finally, we show that most empirical heuristics for reducing saturation or improving generation quality correspond directly to the two terms in our decomposition. Across image generation benchmarks, AdaMaG improves realism, reduces hallucinations, and induces controlled desaturation in high-guidance regimes.