LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models.
Yang YangWen WangLiang PengChaotian SongYao ChenHengjia LiXiaolong YangQinglin LuDeng CaiBoxi WuWei LiuPublished in: CoRR (2024)
Keyphrases
- low rank
- diffusion models
- convex optimization
- missing data
- matrix factorization
- linear combination
- low rank matrix
- singular value decomposition
- rank minimization
- agent technology
- matrix completion
- high order
- diffusion model
- information diffusion
- semi supervised
- trace norm
- social networks
- software agents
- high dimensional data
- higher order
- viral marketing
- active learning
- computer vision