In this work, we propose a training-free, trajectory-based controllable T2I approach, termed TraDiffusion. This novel method allows users to effortlessly guide image generation via mouse trajectories. To achieve precise control, we design a distance awareness energy function to effectively guide latent variables, ensuring that the focus of generation is within the areas defined by the trajectory. The energy function encompasses a control function to draw the generation closer to the specified trajectory and a movement function to diminish activity in areas distant from the trajectory. Through extensive experiments and qualitative assessments on the COCO dataset, the results reveal that TraDiffusion facilitates simpler, more natural image control. Moreover, it showcases the ability to manipulate salient regions, attributes, and relationships within the generated images, alongside visual input based on arbitrary or enhanced trajectories.
@article{arxiv.2408.09739,
title = {TraDiffusion: Trajectory-Based Training-Free Image Generation},
author = {Mingrui Wu and Oucheng Huang and Jiayi Ji and Jiale Li and Xinyue Cai and Huafeng Kuang and Jianzhuang Liu and Xiaoshuai Sun and Rongrong Ji},
journal= {arXiv preprint arXiv:2408.09739},
year = {2024}
}