# MoCA-Video: Motion-Aware Concept Alignment for Consistent Video Editing

arXiv: https://arxiv.org/abs/2506.01004 · HTML: https://mlsanity.com/paper/2506.01004/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 31 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## Builds on (most cited first, 28 of 28)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors](https://mlsanity.com/paper/2310.12190/) (2023)
- [TokenFlow: Consistent Diffusion Features for Consistent Video Editing](https://mlsanity.com/paper/2307.10373/) (2023)
- [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://mlsanity.com/paper/2411.17440/) (2024)
- [AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks](https://mlsanity.com/paper/2403.14468/) (2024)
- [FIFO-Diffusion: Generating Infinite Videos from Text without Training](https://mlsanity.com/paper/2405.11473/) (2024)
- [ID-Animator: Zero-Shot Identity-Preserving Human Video Generation](https://mlsanity.com/paper/2404.15275/) (2024)
- [RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models](https://mlsanity.com/paper/2312.04524/) (2023)
- [VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control](https://mlsanity.com/paper/2503.05639/) (2025)
- [MagicEdit: High-Fidelity and Temporally Coherent Video Editing](https://mlsanity.com/paper/2308.14749/) (2023)
- [MagicMix: Semantic Mixing with Diffusion Models](https://mlsanity.com/paper/2210.16056/) (2022)
- [Putting People in Their Place: Affordance-Aware Human Insertion into Scenes](https://mlsanity.com/paper/2304.14406/) (2023)
- [DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control](https://mlsanity.com/paper/2410.13830/) (2024)
- [MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers](https://mlsanity.com/paper/2501.03931/) (2025)
- [DIVE: Taming DINO for Subject-Driven Video Editing](https://mlsanity.com/paper/2412.03347/) (2024)
- [ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generation](https://mlsanity.com/paper/2412.08645/) (2024)
- [EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion](https://mlsanity.com/paper/2501.13452/) (2025)
- [FreeBlend: Advancing Concept Blending with Staged Feedback-Driven Interpolation Diffusion](https://mlsanity.com/paper/2502.05606/) (2025)
- [Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion](https://mlsanity.com/paper/2412.14462/) (2024)

## Built on by (most cited first, 2 of 2)

- [Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations](https://mlsanity.com/paper/2507.04705/) (2025)
- [CAPTAIN: Semantic Feature Injection for Memorization Mitigation in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2512.10655/) (2025)

## Abstract (arXiv)

Unlike traditional video editing or inpainting, video semantic mixing fuses a reference concept with a moving target entity to produce a hybrid while preserving the source video's motion and layout. We propose MoCA-Video, a training-free framework that steers a frozen video-diffusion denoising trajectory through concept-localized reference injection. At selected low-noise steps, MoCA-Video uses concept attention to localize the target object and injects the reference latent into the localized region, where object structure has formed but appearance remains editable. A momentum-based correction carries the injected prediction across frames to encourage coherent concept integration through the sequence. We further introduce CASS, a CLIP-based metric that measures the output's directional alignment shift toward the reference and away from the source prompt. Using the denoiser's internal attention avoids an external localization model; in our A100 FP16 setup, MoCA-Video takes 3.2 seconds per output frame, excluding preprocessing. Across the evaluated baselines, MoCA-Video achieves the highest CASS, rel-CASS, and ImageReward, while LPIPS-T and FVD expose separate temporal-coherence and video-quality trade-offs.