# Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations

arXiv: https://arxiv.org/abs/2507.04705 · HTML: https://mlsanity.com/paper/2507.04705/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 51 references that are in the map.
- First posted on arXiv 7 Jul 2025.

## Builds on (most cited first, 30 of 33)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [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)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors](https://mlsanity.com/paper/2310.12190/) (2023)
- [InstantID: Zero-shot Identity-Preserving Generation in Seconds](https://mlsanity.com/paper/2401.07519/) (2024)
- [PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding](https://mlsanity.com/paper/2312.04461/) (2023)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation](https://mlsanity.com/paper/2304.09790/) (2023)
- [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://mlsanity.com/paper/2411.17440/) (2024)
- [ID-Animator: Zero-Shot Identity-Preserving Human Video Generation](https://mlsanity.com/paper/2404.15275/) (2024)
- [MotionBooth: Motion-Aware Customized Text-to-Video Generation](https://mlsanity.com/paper/2406.17758/) (2024)
- [HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation](https://mlsanity.com/paper/2505.04512/) (2025)
- [High-resolution Iterative Feedback Network for Camouflaged Object Detection](https://mlsanity.com/paper/2203.11624/) (2022)
- [SkyReels-A2: Compose Anything in Video Diffusion Transformers](https://mlsanity.com/paper/2504.02436/) (2025)
- [AnimateAnything: Fine-Grained Open Domain Image Animation with Motion Guidance](https://mlsanity.com/paper/2311.12886/) (2023)
- [MotionMaster: Training-free Camera Motion Transfer For Video Generation](https://mlsanity.com/paper/2404.15789/) (2024)
- [Still-Moving: Customized Video Generation without Customized Video Data](https://mlsanity.com/paper/2407.08674/) (2024)
- [Moonshot: Towards Controllable Video Generation and Editing with Multimodal Conditions](https://mlsanity.com/paper/2401.01827/) (2024)
- [Face Super-Resolution Guided by 3D Facial Priors](https://mlsanity.com/paper/2007.09454/) (2020)
- [Concat-ID: Towards Universal Identity-Preserving Video Synthesis](https://mlsanity.com/paper/2503.14151/) (2025)
- [EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion](https://mlsanity.com/paper/2501.13452/) (2025)
- [HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis](https://mlsanity.com/paper/2503.16944/) (2025)
- [Non-Imaging Medical Data Synthesis for Trustworthy AI: A Comprehensive Survey](https://mlsanity.com/paper/2209.09239/) (2022)

## Built on by (most cited first, 4 of 4)

- [Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization](https://mlsanity.com/paper/2510.14255/) (2025)
- [EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation](https://mlsanity.com/paper/2605.15199/) (2026)
- [Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation](https://mlsanity.com/paper/2606.02441/) (2026)
- [Keyframe-Anchored Identity Preservation for Sequential-Action Video Generation](https://mlsanity.com/paper/2607.17985/) (2026)

## Abstract (arXiv)

Identity-preserving text-to-video (IPT2V) generation, which aims to create high-fidelity videos with consistent human identity, has become crucial for downstream applications. However, current end-to-end frameworks suffer a critical spatial-temporal trade-off: optimizing for spatially coherent layouts of key elements (e.g., character identity preservation) often compromises instruction-compliant temporal smoothness, while prioritizing dynamic realism risks disrupting the spatial coherence of visual structures. To tackle this issue, we propose a simple yet effective spatial-temporal decoupled framework that decomposes representations into spatial features for layouts and temporal features for motion dynamics. Specifically, our paper proposes a semantic prompt optimization mechanism and stage-wise decoupled generation paradigm. The former module decouples the prompt into spatial and temporal components. Aligned with the subsequent stage-wise decoupled approach, the spatial prompts guide the text-to-image (T2I) stage to generate coherent spatial features, while the temporal prompts direct the sequential image-to-video (I2V) stage to ensure motion consistency. Experimental results validate that our approach achieves excellent spatiotemporal consistency, demonstrating outstanding performance in identity preservation, text relevance, and video quality. By leveraging this simple yet robust mechanism, our algorithm secures the runner-up position in 2025 ACM MultiMedia Challenge. Our code is available at https://github.com/rain152/IPVG.