8 papers
The World is Your Canvas: Painting Promptable Events with Reference Images, Trajectories, and Text
Hanlin Wang, Hao Ouyang, Qiuyu Wang +12
We present WorldCanvas, a framework for promptable world events that enables rich, user-directed simulation by combining text, trajectories, and reference images. Unlike text-only…
MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues
Zichen Liu, Yue Yu, Hao Ouyang +11
We propose MagicQuill V2, a novel system that introduces a \textbf{layered composition} paradigm to generative image editing, bridging the gap between the semantic power of diffusi…
HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives
Yihao Meng, Hao Ouyang, Yue Yu +9
State-of-the-art text-to-video models excel at generating isolated clips but fall short of creating the coherent, multi-shot narratives, which are the essence of storytelling. We b…
Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
Qingyan Bai, Qiuyu Wang, Hao Ouyang +10
Instruction-based video editing promises to democratize content creation, yet its progress is severely hampered by the scarcity of large-scale, high-quality training data. We intro…
Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models
Wen Wang, Bozhen Fang, Chenchen Jing +6
Diffusion large language models (dLLMs) generate text through iterative denoising, yet current decoding strategies discard rich intermediate predictions in favor of the final outpu…
AniDoc: Animation Creation Made Easier
Yihao Meng, Hao Ouyang, Hanlin Wang +6
The production of 2D animation follows an industry-standard workflow, encompassing four essential stages: character design, keyframe animation, in-betweening, and coloring. Our res…