# Identity-Preserving Text-to-Video Generation via Training-Free Prompt, Image, and Guidance Enhancement

arXiv: https://arxiv.org/abs/2509.01362 · HTML: https://mlsanity.com/paper/2509.01362/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 26 of 26)

- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [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)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [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)
- [DreamVideo: Composing Your Dream Videos with Customized Subject and Motion](https://mlsanity.com/paper/2312.04433/) (2023)
- [AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation](https://mlsanity.com/paper/2304.09790/) (2023)
- [GME: Improving Universal Multimodal Retrieval by Multimodal LLMs](https://mlsanity.com/paper/2412.16855/) (2024)
- [Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models](https://mlsanity.com/paper/2405.04233/) (2024)
- [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)
- [ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling](https://mlsanity.com/paper/2501.02487/) (2025)
- [MotionBooth: Motion-Aware Customized Text-to-Video Generation](https://mlsanity.com/paper/2406.17758/) (2024)
- [CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects](https://mlsanity.com/paper/2401.09962/) (2024)
- [Magic-Me: Identity-Specific Video Customized Diffusion](https://mlsanity.com/paper/2402.09368/) (2024)
- [EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images](https://mlsanity.com/paper/2405.20224/) (2024)
- [MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators](https://mlsanity.com/paper/2404.05014/) (2024)
- [Still-Moving: Customized Video Generation without Customized Video Data](https://mlsanity.com/paper/2407.08674/) (2024)
- [Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle](https://mlsanity.com/paper/2407.19548/) (2024)
- [Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts](https://mlsanity.com/paper/2502.07802/) (2025)
- [Diff-BGM: A Diffusion Model for Video Background Music Generation](https://mlsanity.com/paper/2405.11913/) (2024)
- [ConMo: Controllable Motion Disentanglement and Recomposition for Zero-Shot Motion Transfer](https://mlsanity.com/paper/2504.02451/) (2025)
- [Balancing Preservation and Modification: A Region and Semantic Aware Metric for Instruction-Based Image Editing](https://mlsanity.com/paper/2506.13827/) (2025)

## Built on by (most cited first, 8 of 8)

- [Scaling Zero-Shot Reference-to-Video Generation](https://mlsanity.com/paper/2512.06905/) (2025)
- [ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation](https://mlsanity.com/paper/2606.11670/) (2026)
- [BachVid: Training-Free Video Generation with Consistent Background and Character](https://mlsanity.com/paper/2510.21696/) (2025)
- [Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild](https://mlsanity.com/paper/2607.13881/) (2026)
- [HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement](https://mlsanity.com/paper/2607.18217/) (2026)
- [Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation](https://mlsanity.com/paper/2606.02441/) (2026)
- [KeyID: Decoupled Drafting and Keyframe Editing for Identity-Preserving Video Generation](https://mlsanity.com/paper/2608.16154/) (2026)
- [Identity-Preserving Text-to-Video Generation via Agentic Enhancement and Semantic Repair](https://mlsanity.com/paper/2608.20749/) (2026)

## Abstract (arXiv)

Identity-preserving text-to-video (IPT2V) generation creates videos faithful to both a reference subject image and a text prompt. While fine-tuning large pretrained video diffusion models on ID-matched data achieves state-of-the-art results on IPT2V, data scarcity and high tuning costs hinder broader improvement. We thus introduce a Training-Free Prompt, Image, and Guidance Enhancement (TPIGE) framework that bridges the semantic gap between the video description and the reference image and design sampling guidance that enhances identity preservation and video quality, achieving performance gains at minimal cost.Specifically, we first propose Face Aware Prompt Enhancement, using GPT-4o to enhance the text prompt with facial details derived from the reference image. We then propose Prompt Aware Reference Image Enhancement, leveraging an identity-preserving image generator to refine the reference image, rectifying conflicts with the text prompt. The above mutual refinement significantly improves input quality before video generation. Finally, we propose ID-Aware Spatiotemporal Guidance Enhancement, utilizing unified gradients to optimize identity preservation and video quality jointly during generation.Our method outperforms prior work and is validated by automatic and human evaluations on a 1000 video test set, winning first place in the ACM Multimedia 2025 Identity-Preserving Video Generation Challenge, demonstrating state-of-the-art performance and strong generality. The code is available at https://github.com/Andyplus1/IPT2V.git.