# Dynamic Frequency Modulation for Controllable Text-driven Image Generation Source: [Dynamic Frequency Modulation for Controllable Text-driven Image Generation]() Collection index: [llms.txt]() Data updated: 2026-02-13T05:00:04.184Z Authors: Tiandong Shi, Ling Zhao, Ji Qi, Jiayi Ma, Chengli Peng Published: 2026-02-11T09:06:44.000Z ## Abstract The success of text-guided diffusion models has established a new image generation paradigm driven by the iterative refinement of text prompts. However, modifying the original text prompt to achieve the expected semantic adjustments often results in unintended global structure changes that disrupt user intent. Existing methods rely on empirical feature map selection for intervention, whose performance heavily depends on appropriate selection, leading to suboptimal stability. This paper tries to solve the aforementioned problem from a frequency perspective and analyzes the impact of the frequency spectrum of noisy latent variables on the hierarchical emergence of the structure framework and fine-grained textures during the generation process. We find that lower-frequency components are primarily responsible for establishing the structure framework in the early generation stage. Their influence diminishes over time, giving way to higher-frequency components that synthesize fine-grained textures. In light of this, we propose a training-free frequency modulation method utilizing a frequency-dependent weighting function with dynamic decay. This method maintains the structure framework consistency while permitting targeted semantic modifications. By directly manipulating the noisy latent variable, the proposed method avoids the empirical selection of internal feature maps. Extensive experiments demonstrate that the proposed method significantly outperforms current state-of-the-art methods, achieving an effective balance between preserving structure and enabling semantic updates. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Editing on ImageNetR-Fake (test)](): Image Editing; ImageNetR-Fake (test); Structural Distance: 44.3462. - [Image Editing on PIE-Bench (test)](): Image Editing; PIE-Bench (test); PSNR: 20.8003. ## Original sources and implementation [Original paper]() [PDF]()