DisenDreamer: Subject-Driven Text-to-Image Generation With Sample-Aware Disentangled Tuning

• Published in: IEEE transactions on circuits and systems for video technology Vol. 34; no. 8; pp. 6860 - 6873
• Main Authors: Chen, Hong, Zhang, Yipeng, Wang, Xin, Duan, Xuguang, Zhou, Yuwei, Zhu, Wenwu
• Format: Journal Article
• Language: English
• Published: IEEE 01.08.2024
• Subjects: Circuits and systems; Controllability; Diffusion model; disentangled finetuning; Image synthesis; Noise reduction; subject-driven text-to-image generation; Training; Tuning; Visualization

Subject-driven text-to-image generation aims to generate customized images of the given subject based on the text descriptions, which has drawn increasing attention recently. Existing methods mainly resort to finetuning a pretrained generative model, where the identity-relevant information (e.g., th...