# Concat-ID: Towards Universal Identity-Preserving Video Synthesis

arXiv: https://arxiv.org/abs/2503.14151 · HTML: https://mlsanity.com/paper/2503.14151/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 34 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (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)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://mlsanity.com/paper/2410.05954/) (2024)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://mlsanity.com/paper/2411.17440/) (2024)
- [PuLID: Pure and Lightning ID Customization via Contrastive Alignment](https://mlsanity.com/paper/2404.16022/) (2024)
- [ID-Animator: Zero-Shot Identity-Preserving Human Video Generation](https://mlsanity.com/paper/2404.15275/) (2024)
- [Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection](https://mlsanity.com/paper/2405.10300/) (2024)
- [Sample and Computation Redistribution for Efficient Face Detection](https://mlsanity.com/paper/2105.04714/) (2021)
- [ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning](https://mlsanity.com/paper/2501.04698/) (2025)
- [RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers](https://mlsanity.com/paper/2502.15894/) (2025)
- [Magic-Me: Identity-Specific Video Customized Diffusion](https://mlsanity.com/paper/2402.09368/) (2024)
- [MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers](https://mlsanity.com/paper/2501.03931/) (2025)
- [Imagine yourself: Tuning-Free Personalized Image Generation](https://mlsanity.com/paper/2409.13346/) (2024)
- [VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models](https://mlsanity.com/paper/2412.19645/) (2024)
- [Ingredients: Blending Custom Photos with Video Diffusion Transformers](https://mlsanity.com/paper/2501.01790/) (2025)
- [PoseCrafter: One-Shot Personalized Video Synthesis Following Flexible Pose Control](https://mlsanity.com/paper/2405.14582/) (2024)
- [Toffee: Efficient Million-Scale Dataset Construction for Subject-Driven Text-to-Image Generation](https://mlsanity.com/paper/2406.09305/) (2024)

## Built on by (most cited first, 28 of 28)

- [OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation](https://mlsanity.com/paper/2505.20292/) (2025)
- [Helios: Real Real-Time Long Video Generation Model](https://mlsanity.com/paper/2603.04379/) (2026)
- [Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation](https://mlsanity.com/paper/2508.07901/) (2025)
- [MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement](https://mlsanity.com/paper/2505.23742/) (2025)
- [DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers](https://mlsanity.com/paper/2506.10568/) (2025)
- [DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation](https://mlsanity.com/paper/2602.12160/) (2026)
- [Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset](https://mlsanity.com/paper/2506.18851/) (2025)
- [Frame In-N-Out: Unbounded Controllable Image-to-Video Generation](https://mlsanity.com/paper/2505.21491/) (2025)
- [RefAlign: Representation Alignment for Reference-to-Video Generation](https://mlsanity.com/paper/2603.25743/) (2026)
- [RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation](https://mlsanity.com/paper/2601.05241/) (2026)
- [ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation](https://mlsanity.com/paper/2606.11670/) (2026)
- [Bind-Your-Avatar: Multi-Talking-Character Video Generation with Dynamic 3D-mask-based Embedding Router](https://mlsanity.com/paper/2506.19833/) (2025)
- [Proteus-ID: ID-Consistent and Motion-Coherent Video Customization](https://mlsanity.com/paper/2506.23729/) (2025)
- [ID-Crafter: VLM-Grounded Online RL for Compositional Multi-Subject Video Generation](https://mlsanity.com/paper/2511.00511/) (2025)
- [LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation](https://mlsanity.com/paper/2603.20192/) (2026)
- [Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation](https://mlsanity.com/paper/2604.10030/) (2026)
- [EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation](https://mlsanity.com/paper/2605.15199/) (2026)
- [ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generation](https://mlsanity.com/paper/2512.07328/) (2025)
- [Temporal In-Context Fine-Tuning with Temporal Reasoning for Versatile Control of Video Diffusion Models](https://mlsanity.com/paper/2506.00996/) (2025)
- [Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations](https://mlsanity.com/paper/2507.04705/) (2025)
- [LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation](https://mlsanity.com/paper/2508.07603/) (2025)
- [Active Intelligence in Video Avatars via Closed-loop World Modeling](https://mlsanity.com/paper/2512.20615/) (2025)
- [TIDE: Task-Isolated Diffusion for Unified Video Editing and Generation](https://mlsanity.com/paper/2606.08260/) (2026)
- [Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment](https://mlsanity.com/paper/2607.04311/) (2026)
- [Collaborative Face Experts Fusion in Video Generation: Boosting Identity Consistency Across Large Face Poses](https://mlsanity.com/paper/2508.09476/) (2025)
- [Keyframe-Anchored Identity Preservation for Sequential-Action Video Generation](https://mlsanity.com/paper/2607.17985/) (2026)
- [GroupVideo: Multi-Identity Customized Text-to-Video Generation](https://mlsanity.com/paper/2607.21027/) (2026)
- [KeyID: Decoupled Drafting and Keyframe Editing for Identity-Preserving Video Generation](https://mlsanity.com/paper/2608.16154/) (2026)

## Abstract (arXiv)

We present Concat-ID, a unified framework for identity-preserving video generation. Concat-ID employs variational autoencoders to extract image features, which are then concatenated with video latents along the sequence dimension. It relies exclusively on inherent 3D self-attention mechanisms to incorporate them, eliminating the need for additional parameters or modules. A novel cross-video pairing strategy and a multi-stage training regimen are introduced to balance identity consistency and facial editability while enhancing video naturalness. Extensive experiments demonstrate Concat-ID's superiority over existing methods in both single and multi-identity generation, as well as its seamless scalability to multi-subject scenarios, including virtual try-on and background-controllable generation. Concat-ID establishes a new benchmark for identity-preserving video synthesis, providing a versatile and scalable solution for a wide range of applications.