5 papers
PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolution
Wenxue Li, Jingjing Ren, Peng Zhang +4
High-resolution video generation faces a coupled bottleneck of optimization instability and prohibitive computational costs. The massive expansion of the token sequence not only bi…
How Long Can Unified Multimodal Models Generate Images Reliably? Taming Long-Horizon Interleaved Image Generation via Context Curation
Haoyu Chen, Qing Liu, Yuqian Zhou +7
Unified multimodal models hold the promise of generating extensive, interleaved narratives, weaving text and imagery into coherent long-form stories. However, current systems suffe…
Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis
Jingjing Ren, Wenbo Li, Zhongdao Wang +9
Demand for 2K video synthesis is rising with increasing consumer expectations for ultra-clear visuals. While diffusion transformers (DiTs) have demonstrated remarkable capabilities…
POSTA: A Go-to Framework for Customized Artistic Poster Generation
Haoyu Chen, Xiaojie Xu, Wenbo Li +6
Poster design is a critical medium for visual communication. Prior work has explored automatic poster design using deep learning techniques, but these approaches lack text accuracy…
Towards Realistic Data Generation for Real-World Super-Resolution
Long Peng, Wenbo Li, Renjing Pei +5
Existing image super-resolution (SR) techniques often fail to generalize effectively in complex real-world settings due to the significant divergence between training data and prac…