FastComposer: Tuning-Free Multi-subject Image Generation with Localized Attention
Guangxuan Xiao, Tianwei Yin, William T. Freeman, Frédo Durand, Song Han
Who it is from
Nvidiaaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- VILA: On Pre-training for Visual Language ModelsNvidia · 1,080 citations
- FoundationPose: Unified 6D Pose Estimation and Tracking of Novel ObjectsNvidia · 925 citations
- CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action ModelsNvidia · 723 citations
- Neural operators for accelerating scientific simulations and designNvidia · 678 citations
- Small Language Models are the Future of Agentic AIGeorgia Institute of Technology · 628 citations
- Foundation models in robotics: Applications, challenges, and the futureNvidia · 583 citations