Dual-Seed Evolutionary Algorithm for Noise Optimization in Diffusion Models

Diffusion models have emerged as state-of-the-art generative methods, particularly excelling in conditional tasks such as prompt-driven image synthesis. While recent research emphasizes the pivotal role of noise seeds in enhancing text-image alignment and generating human-preferred outputs,these works predominantly rely on random Gaussian noise or heuristic local adjustments,, overlooking the potential of global optimization trategies to systematically improve generation quality. To bridge this gap, we propose Seed Optimization based on Evolution (SOE), a hybrid framework that integrates global evolutionary search with local semantic refinement. The global evolutionary stage conducts seed selection by jointly optimizing text-image alignment (via CLIP-Score) and human preference estimation (via ImageReward), while the local stage employs diffusion inversion to inject conditional semantics into the noise seed. Together, these components constitute a model-agnostic, training-free optimization framework for conditional diffusion models. Extensive experiments across various diffusion models demonstrate that SOE consistently improves semantic fidelity and visual quality, highlighting its generalizability and potential as a plug-and-play enhancement for generative diffusion pipelines.

Authors

• Yuzheng Tan State Key Laboratory of Integrated Electromechanical Manufacturing of High-performance Electronic Equipments, Xidian University
• Yuan He
• Yao Zhu Tsinghua University
• Tianlin Huo Tsinghua University
• Huanqian Yan Beihang University
• Hang Su Dept. of CST, BNRist Center, Inst. for AI, Tsinghua-Bosch Joint Center for ML, Tsinghua University
• Shuxin Zhang State Key Laboratory of Integrated Electromechanical Manufacturing of High-performance Electronic Equipments, Xidian University
• Guangneng Hu School of Computer Science and Technology, Xidian University

Keywords

No keywords are indexed for this paper.