5 papers
OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model
Maomao Li, Zhen Li, Kaipeng Zhang +3
Existing mainstream video customization methods focus on generating identity-consistent videos based on given reference images and textual prompts. Benefiting from the rapid advanc…
Dehallu3D: Hallucination-Mitigated 3D Generation from Single Image via Cyclic View Consistency Refinement
Xiwen Wang, Shichao Zhang, Hailun Zhang +5
Large 3D reconstruction models have revolutionized the 3D content generation field, enabling broad applications in virtual reality and gaming. Just like other large models, large 3…
FREE-Edit: Using Editing-aware Injection in Rectified Flow Models for Zero-shot Image-Driven Video Editing
Maomao Li, Yunfei Liu, Yu Li
Image-driven video editing aims to propagate edit contents from the modified first frame to the remaining frames. Existing methods usually invert the source video to noise using a…
Qffusion: Controllable Portrait Video Editing via Quadrant-Grid Attention Learning
Maomao Li, Lijian Lin, Yunfei Liu +2
This paper presents Qffusion, a dual-frame-guided framework for portrait video editing. Specifically, we consider a design principle of ``animation for editing'', and train Qffusio…
Exploring Iterative Manifold Constraint for Zero-shot Image Editing
Maomao Li, Yu Li, Yunfei Liu +1
Editability and fidelity are two essential demands for text-driven image editing, which expects that the editing area should align with the target prompt and the rest remain unchan…