TraDiffusion: Trajectory-Based Training-Free Image Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Mingrui, Huang, Oucheng, Ji, Jiayi, Li, Jiale, Cai, Xinyue, Kuang, Huafeng, Liu, Jianzhuang, Sun, Xiaoshuai, Ji, Rongrong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909290589061120
author Wu, Mingrui
Huang, Oucheng
Ji, Jiayi
Li, Jiale
Cai, Xinyue
Kuang, Huafeng
Liu, Jianzhuang
Sun, Xiaoshuai
Ji, Rongrong
author_facet Wu, Mingrui
Huang, Oucheng
Ji, Jiayi
Li, Jiale
Cai, Xinyue
Kuang, Huafeng
Liu, Jianzhuang
Sun, Xiaoshuai
Ji, Rongrong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_09739
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TraDiffusion: Trajectory-Based Training-Free Image Generation
Wu, Mingrui
Huang, Oucheng
Ji, Jiayi
Li, Jiale
Cai, Xinyue
Kuang, Huafeng
Liu, Jianzhuang
Sun, Xiaoshuai
Ji, Rongrong
Computer Vision and Pattern Recognition
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.
title TraDiffusion: Trajectory-Based Training-Free Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.09739