FastComposer: Tuning-Free Multi-subject Image Generation with Localized Attention

• Published in: International journal of computer vision Vol. 133; no. 3; pp. 1175 - 1194
• Main Authors: Xiao, Guangxuan, Yin, Tianwei, Freeman, William T., Durand, Frédo, Han, Song
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.03.2025; Springer Nature B.V
• Subjects: Artificial Intelligence; Computer Imaging; Computer Science; Conditioning; Customization; Diffusion models; Diffusion rate; Efficiency; Image processing; Image Processing and Computer Vision; Image quality; Pattern Recognition; Pattern Recognition and Graphics; Special Issue on Large-Scale Generative Models for Content Creation and Manipulation; Vision; Model acceleration; Diffusion-based models; Efficiency; Image generation

Diffusion models excel at text-to-image generation, especially in subject-driven generation for personalized images. However, existing methods are inefficient due to the subject-specific fine-tuning, which is computationally intensive and hampers efficient deployment. Moreover, existing methods stru...