4 papers
OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models
Jinshu Chen, Xinghui Li, Xu Bai +8
Recent advances in video insertion based on diffusion models are impressive. However, existing methods rely on complex control signals but struggle with subject consistency, limiti…
HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning
Liyang Chen, Tianxiang Ma, Jiawei Liu +7
Human-Centric Video Generation (HCVG) methods seek to synthesize human videos from multimodal inputs, including text, image, and audio. Existing methods struggle to effectively coo…
Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset
Zhuowei Chen, Bingchuan Li, Tianxiang Ma +8
Subject-to-video generation has witnessed substantial progress in recent years. However, existing models still face significant challenges in faithfully following textual instructi…
Phantom: Subject-consistent video generation via cross-modal alignment
Lijie Liu, Tianxiang Ma, Bingchuan Li +6
The continuous development of foundational models for video generation is evolving into various applications, with subject-consistent video generation still in the exploratory stag…