TraDiffusion: Trajectory-Based Training-Free Image Generation

Mingrui Wu, Oucheng Huang, Jiayi Ji, Jiale Li, Xinyue Cai, huafeng, Jianzhuang Liu, Xiaoshuai Sun, Rongrong Ji

TraDiffusion: Trajectory-Based Training-Free Image Generation: 9 upvotes on Hugging Face Daily Papers, #10 of 11 papers on 2024-08-20. Day-by-day upvote history.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.