# ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment

arXiv: https://arxiv.org/abs/2509.17818 · HTML: https://mlsanity.com/paper/2509.17818/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 85 of its 104 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Placed in

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

## Builds on (most cited first, 30 of 85)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [MotionCtrl: A Unified and Flexible Motion Controller for Video Generation](https://mlsanity.com/paper/2312.03641/) (2023)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [FateZero: Fusing Attentions for Zero-shot Text-based Video Editing](https://mlsanity.com/paper/2303.09535/) (2023)
- [TokenFlow: Consistent Diffusion Features for Consistent Video Editing](https://mlsanity.com/paper/2307.10373/) (2023)
- [AnyDoor: Zero-shot Object-level Image Customization](https://mlsanity.com/paper/2307.09481/) (2023)
- [Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos](https://mlsanity.com/paper/2304.01186/) (2023)
- [Diffusion models as plug-and-play priors](https://mlsanity.com/paper/2206.09012/) (2022)
- [CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion](https://mlsanity.com/paper/2211.14461/) (2022)
- [Taming Rectified Flow for Inversion and Editing](https://mlsanity.com/paper/2411.04746/) (2024)
- [AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation](https://mlsanity.com/paper/2304.09790/) (2023)
- [Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation](https://mlsanity.com/paper/2406.01900/) (2024)
- [AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks](https://mlsanity.com/paper/2403.14468/) (2024)
- [DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion](https://mlsanity.com/paper/2303.06840/) (2023)
- [GameGen-X: Interactive Open-world Game Video Generation](https://mlsanity.com/paper/2411.00769/) (2024)
- [ID-Animator: Zero-Shot Identity-Preserving Human Video Generation](https://mlsanity.com/paper/2404.15275/) (2024)
- [Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise](https://mlsanity.com/paper/2501.08331/) (2025)
- [RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models](https://mlsanity.com/paper/2312.04524/) (2023)
- [ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples](https://mlsanity.com/paper/1811.12673/) (2018)
- [DiT4Edit: Diffusion Transformer for Image Editing](https://mlsanity.com/paper/2411.03286/) (2024)
- [Controllable Video Generation: A Survey](https://mlsanity.com/paper/2507.16869/) (2025)
- [LAS-AT: Adversarial Training with Learnable Attack Strategy](https://mlsanity.com/paper/2203.06616/) (2022)

## Built on by (most cited first, 27 of 27)

- [FastVMT: Eliminating Redundancy in Video Motion Transfer](https://mlsanity.com/paper/2602.05551/) (2026)
- [Top-Down Semantic Refinement for Image Captioning](https://mlsanity.com/paper/2510.22391/) (2025)
- [LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing](https://mlsanity.com/paper/2606.26740/) (2026)
- [Group Editing: Edit Multiple Images in One Go](https://mlsanity.com/paper/2603.22883/) (2026)
- [PISCO: Precise Video Instance Insertion with Sparse Control](https://mlsanity.com/paper/2602.08277/) (2026)
- [AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner](https://mlsanity.com/paper/2512.10571/) (2025)
- [VideoCoF: Unified Video Editing with Temporal Reasoner](https://mlsanity.com/paper/2512.07469/) (2025)
- [LiveLight: Real-time Streaming Video Relighting with Interactive Control](https://mlsanity.com/paper/2608.01771/) (2026)
- [LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation](https://mlsanity.com/paper/2604.11789/) (2026)
- [Embedding-perturbed Exploration Preference Optimization for Flow Models](https://mlsanity.com/paper/2605.15803/) (2026)
- [GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflows](https://mlsanity.com/paper/2603.12155/) (2026)
- [MultiMotion: Multi Subject Video Motion Transfer via Video Diffusion Transformer](https://mlsanity.com/paper/2512.07500/) (2025)
- [Over++: Generative Video Compositing for Layer Interaction Effects](https://mlsanity.com/paper/2512.19661/) (2025)
- [AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents](https://mlsanity.com/paper/2602.15325/) (2026)
- [ResWM: Residual-Action World Model for Visual RL](https://mlsanity.com/paper/2603.11110/) (2026)
- [Unified Long Video Inpainting and Outpainting via Overlapping High-Order Co-Denoising](https://mlsanity.com/paper/2511.03272/) (2025)
- [Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis](https://mlsanity.com/paper/2606.29020/) (2026)
- [GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising](https://mlsanity.com/paper/2606.30003/) (2026)
- [MSEditor: Toward Consistent Multi-Shot Video Editing](https://mlsanity.com/paper/2608.17559/) (2026)
- [SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling](https://mlsanity.com/paper/2609.34502/) (2026)
- [A Scalable Curiosity-Driven Game-Theoretic Framework for Long-Tail Multi-Label Learning in Data Mining](https://mlsanity.com/paper/2602.15330/) (2026)
- [Video2LoRA: Unified Semantic-Controlled Video Generation via Per-Reference-Video LoRA](https://mlsanity.com/paper/2603.08210/) (2026)
- [ProxyUp: Training-Free Proxy-Conditioned Video Generation for Controllable Dynamics](https://mlsanity.com/paper/2607.03732/) (2026)
- [MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation](https://mlsanity.com/paper/2607.14595/) (2026)
- [One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing](https://mlsanity.com/paper/2609.04190/) (2026)
- [Edit-VAR: Taming Visual Autoregressive Model for Precise Video Editing](https://mlsanity.com/paper/2609.21268/) (2026)
- [TripleFlow: Training-Free Video Object Removal by Bridging Residual Editing and Native Generation](https://mlsanity.com/paper/2609.39157/) (2026)

## Abstract (arXiv)

Training-free video object editing aims to achieve precise object-level manipulation, including object insertion, swapping, and deletion. However, it faces significant challenges in maintaining fidelity and temporal consistency. Existing methods, often designed for U-Net architectures, suffer from two primary limitations: inaccurate inversion due to first-order solvers, and contextual conflicts caused by crude "hard" feature replacement. These issues are more challenging in Diffusion Transformers (DiTs), where the unsuitability of prior layer-selection heuristics makes effective guidance challenging. To address these limitations, we introduce ContextFlow, a novel training-free framework for DiT-based video object editing. In detail, we first employ a high-order Rectified Flow solver to establish a robust editing foundation. The core of our framework is Adaptive Context Enrichment (for specifying what to edit), a mechanism that addresses contextual conflicts. Instead of replacing features, it enriches the self-attention context by concatenating Key-Value pairs from parallel reconstruction and editing paths, empowering the model to dynamically fuse information. Additionally, to determine where to apply this enrichment (for specifying where to edit), we propose a systematic, data-driven analysis to identify task-specific vital layers. Based on a novel Guidance Responsiveness Metric, our method pinpoints the most influential DiT blocks for different tasks (e.g., insertion, swapping), enabling targeted and highly effective guidance. Extensive experiments show that ContextFlow significantly outperforms existing training-free methods and even surpasses several state-of-the-art training-based approaches, delivering temporally coherent, high-fidelity results.