Year: 2025
Type: conference-paper
Abstract: The use of denoising diffusion models is becoming increasingly popular in the field of image editing. However, current approaches often rely on either image-guided methods, which provide a visual reference but lack control over semantic consistency, or text-guided methods, which ensure alignment with the text guidance but compromise visual quality. To resolve this issue, we propose a framework that integrates a fusion of generated visual references and text guidance into the semantic latent space of a frozen pre-trained diffusion model. Using only a tiny neural network, our framework provides control over diverse content and attributes, driven intuitively by the simple prompt. Compared to state-of-the-art methods, the framework generates images of higher quality while providing realistic editing effects across various benchmark datasets. The code is available at https://github.com/SadAngelF/Editing-via-Step-Wise-Alignment.
Authors: Zhanbo Feng, Zenan Ling, Xinyu Lu, Ci Gong, Feng Zhou, Wugedele Bao, Jie Li, Fan Yang, Robert C. Qiu
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4408352618