# GenCompositor: Generative Video Compositing with Diffusion Transformer

arXiv: https://arxiv.org/abs/2509.02460 · HTML: https://mlsanity.com/paper/2509.02460/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 16 of its 68 references that are in the map.
- First posted on arXiv 2 Sep 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 16 of 16)

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models](https://mlsanity.com/paper/2303.17599/) (2023)
- [HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation](https://mlsanity.com/paper/2505.04512/) (2025)
- [FullDiT: Multi-Task Video Generative Foundation Model with Full Attention](https://mlsanity.com/paper/2503.19907/) (2025)
- [VFX Creator: Animated Visual Effect Generation with Controllable Diffusion Transformer](https://mlsanity.com/paper/2502.05979/) (2025)
- [Deep Video Harmonization with Color Mapping Consistency](https://mlsanity.com/paper/2205.00687/) (2022)
- [ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing](https://mlsanity.com/paper/2508.10881/) (2025)
- [Neural Video Fields Editing](https://mlsanity.com/paper/2312.08882/) (2023)
- [4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation](https://mlsanity.com/paper/2508.04467/) (2025)
- [Tiger200K: Manually Curated High Visual Quality Video Dataset from UGC Platform](https://mlsanity.com/paper/2504.15182/) (2025)

## Built on by (most cited first, 9 of 9)

- [DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancer](https://mlsanity.com/paper/2602.24096/) (2026)
- [VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning](https://mlsanity.com/paper/2510.08555/) (2025)
- [OctoT2I: A Self-Evolving Agentic Text-to-Image Router](https://mlsanity.com/paper/2606.01803/) (2026)
- [Over++: Generative Video Compositing for Layer Interaction Effects](https://mlsanity.com/paper/2512.19661/) (2025)
- [TRACE: Object Motion Editing in Videos with First-Frame Trajectory Guidance](https://mlsanity.com/paper/2603.25707/) (2026)
- [Controllable Video Object Insertion via Multi-View Priors](https://mlsanity.com/paper/2604.14556/) (2026)
- [FlexComposer: Unified Video Compositing from Images to Dynamic Footage with Flexible Trajectory Control](https://mlsanity.com/paper/2607.29627/) (2026)
- [DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting](https://mlsanity.com/paper/2609.01516/) (2026)
- [OREO: Fidelity Alignment in 3D Generation via On-the-fly Rendering-Editing Optimization](https://mlsanity.com/paper/2609.29788/) (2026)

## Abstract (arXiv)

Video compositing combines live-action footage to create video production, serving as a crucial technique in video creation and film production. Traditional pipelines require intensive labor efforts and expert collaboration, resulting in lengthy production cycles and high manpower costs. To address this issue, we automate this process with generative models, called generative video compositing. This new task strives to adaptively inject identity and motion information of foreground video to the target video in an interactive manner, allowing users to customize the size, motion trajectory, and other attributes of the dynamic elements added in final video. Specifically, we designed a novel Diffusion Transformer (DiT) pipeline based on its intrinsic properties. To maintain consistency of the target video before and after editing, we revised a light-weight DiT-based background preservation branch with masked token injection. As to inherit dynamic elements from other sources, a DiT fusion block is proposed using full self-attention, along with a simple yet effective foreground augmentation for training. Besides, for fusing background and foreground videos with different layouts based on user control, we developed a novel position embedding, named Extended Rotary Position Embedding (ERoPE). Finally, we curated a dataset comprising 61K sets of videos for our new task, called VideoComp. This data includes complete dynamic elements and high-quality target videos. Experiments demonstrate that our method effectively realizes generative video compositing, outperforming existing possible solutions in fidelity and consistency. Project is available at https://gencompositor.github.io/