Paper
Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion
Authors
Zhenghong Zhou, Xiaohang Zhan, Zhiqin Chen, Soo Ye Kim, Nanxuan Zhao, Haitian Zheng, Qing Liu, He Zhang, Zhe Lin, Yuqian Zhou, Jiebo Luo
Abstract
Recent video diffusion models have made remarkable strides in visual quality, yet precise, fine-grained control remains a key bottleneck that limits practical customizability for content creation. For AI video creators, three forms of control are crucial: (i) scene composition, (ii) multi-view consistent subject customization, and (iii) camera-pose or object-motion adjustment. Existing methods typically handle these dimensions in isolation, with limited support for multi-view subject synthesis and identity preservation under arbitrary pose changes. This lack of a unified architecture makes it difficult to support versatile, jointly controllable video. We introduce Tri-Prompting, a unified framework and two-stage training paradigm that integrates scene composition, multi-view subject consistency, and motion control. Our approach leverages a dual-condition motion module driven by 3D tracking points for background scenes and downsampled RGB cues for foreground subjects. To ensure a balance between controllability and visual realism, we further propose an inference ControlNet scale schedule. Tri-Prompting supports novel workflows, including 3D-aware subject insertion into any scenes and manipulation of existing subjects in an image. Experimental results demonstrate that Tri-Prompting significantly outperforms specialized baselines such as Phantom and DaS in multi-view subject identity, 3D consistency, and motion accuracy.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.15614v1</id>\n <title>Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion</title>\n <updated>2026-03-16T17:59:05Z</updated>\n <link href='https://arxiv.org/abs/2603.15614v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.15614v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Recent video diffusion models have made remarkable strides in visual quality, yet precise, fine-grained control remains a key bottleneck that limits practical customizability for content creation. For AI video creators, three forms of control are crucial: (i) scene composition, (ii) multi-view consistent subject customization, and (iii) camera-pose or object-motion adjustment. Existing methods typically handle these dimensions in isolation, with limited support for multi-view subject synthesis and identity preservation under arbitrary pose changes. This lack of a unified architecture makes it difficult to support versatile, jointly controllable video. We introduce Tri-Prompting, a unified framework and two-stage training paradigm that integrates scene composition, multi-view subject consistency, and motion control. Our approach leverages a dual-condition motion module driven by 3D tracking points for background scenes and downsampled RGB cues for foreground subjects. To ensure a balance between controllability and visual realism, we further propose an inference ControlNet scale schedule. Tri-Prompting supports novel workflows, including 3D-aware subject insertion into any scenes and manipulation of existing subjects in an image. Experimental results demonstrate that Tri-Prompting significantly outperforms specialized baselines such as Phantom and DaS in multi-view subject identity, 3D consistency, and motion accuracy.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <published>2026-03-16T17:59:05Z</published>\n <arxiv:comment>Project page: https://zhouzhenghong-gt.github.io/Tri-Prompting-Page/</arxiv:comment>\n <arxiv:primary_category term='cs.CV'/>\n <author>\n <name>Zhenghong Zhou</name>\n </author>\n <author>\n <name>Xiaohang Zhan</name>\n </author>\n <author>\n <name>Zhiqin Chen</name>\n </author>\n <author>\n <name>Soo Ye Kim</name>\n </author>\n <author>\n <name>Nanxuan Zhao</name>\n </author>\n <author>\n <name>Haitian Zheng</name>\n </author>\n <author>\n <name>Qing Liu</name>\n </author>\n <author>\n <name>He Zhang</name>\n </author>\n <author>\n <name>Zhe Lin</name>\n </author>\n <author>\n <name>Yuqian Zhou</name>\n </author>\n <author>\n <name>Jiebo Luo</name>\n </author>\n </entry>"
}