BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing
Abstract
Element-level visual manipulation is essential in digital content creation, but current diffusion-based methods lack the precision and flexibility of traditional tools. In this work, we introduce BlobCtrl, a framework that unifies element-level generation and editing using a probabilistic blob-based representation. By employing blobs as visual primitives, our approach effectively decouples and represents spatial location, semantic content, and identity information, enabling precise element-level manipulation. Our key contributions include: 1) a dual-branch diffusion architecture with hierarchical feature fusion for seamless foreground-background integration; 2) a self-supervised training paradigm with tailored data augmentation and score functions; and 3) controllable dropout strategies to balance fidelity and diversity. To support further research, we introduce BlobData for large-scale training and BlobBench for systematic evaluation. Experiments show that BlobCtrl excels in various element-level manipulation tasks while maintaining computational efficiency, offering a practical solution for precise and flexible visual content creation. Project page: https://liyaowei-stu.github.io/project/BlobCtrl/
Community
BlobCtrl enables precise, user-friendly element-level visual manipulation.
Main Features: 🦉Element-level Add/Remove/Move/Replace/Enlarge/Shrink.
Arxiv: http://arxiv.org/abs/2503.13434
Github Code: https://github.com/TencentARC/BlobCtrl
Project Webpage: https://liyaowei-stu.github.io/project/BlobCtrl/
Huggingface Demo: https://huggingface.co/spaces/Yw22/BlobCtrl
Huggingface Models: https://huggingface.co/Yw22/BlobCtrl
Youtube: https://youtu.be/rdR4QRR-mbE
Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper