5 papers
InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation
Jinqi Xiao, Qing Yan, Liming Jiang +8
Parameter-Efficient Fine-Tuning of Diffusion Transformers (DiTs) for diverse, multi-conditional tasks often suffers from task interference when using monolithic adapters like LoRA.…
Video-As-Prompt: Unified Semantic Control for Video Generation
Yuxuan Bian, Xin Chen, Zenan Li +4
Unified, generalizable semantic control in video generation remains a critical open challenge. Existing methods either introduce artifacts by enforcing inappropriate pixel-wise pri…
Lynx: Towards High-Fidelity Personalized Video Generation
Shen Sang, Tiancheng Zhi, Tianpei Gu +2
We present Lynx, a high-fidelity model for personalized video synthesis from a single input image. Built on an open-source Diffusion Transformer (DiT) foundation model, Lynx introd…
ID-Patch: Robust ID Association for Group Photo Personalization
Yimeng Zhang, Tiancheng Zhi, Jing Liu +5
The ability to synthesize personalized group photos and specify the positions of each identity offers immense creative potential. While such imagery can be visually appealing, it p…
COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection
Jinqi Xiao, Shen Sang, Tiancheng Zhi +5
Training large-scale neural networks in vision, and multimodal domains demands substantial memory resources, primarily due to the storage of optimizer states. While LoRA, a popular…