# Customizing Video Portraits via Identity-ActionDecoupling

arXiv: https://arxiv.org/abs/2606.22347 · HTML: https://mlsanity.com/paper/2606.22347/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 21 Jun 2026.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [InstantID: Zero-shot Identity-Preserving Generation in Seconds](https://mlsanity.com/paper/2401.07519/) (2024)
- [DreamVideo: Composing Your Dream Videos with Customized Subject and Motion](https://mlsanity.com/paper/2312.04433/) (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)
- [PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization](https://mlsanity.com/paper/2312.06354/) (2023)
- [Still-Moving: Customized Video Generation without Customized Video Data](https://mlsanity.com/paper/2407.08674/) (2024)
- [InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation](https://mlsanity.com/paper/2404.19427/) (2024)
- [PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation](https://mlsanity.com/paper/2411.17048/) (2024)
- [IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation](https://mlsanity.com/paper/2412.11638/) (2024)
- [CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance](https://mlsanity.com/paper/2503.10391/) (2025)
- [Ingredients: Blending Custom Photos with Video Diffusion Transformers](https://mlsanity.com/paper/2501.01790/) (2025)
- [MovieCharacter: A Tuning-Free Framework for Controllable Character Video Synthesis](https://mlsanity.com/paper/2410.20974/) (2024)
- [CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RL](https://mlsanity.com/paper/2512.01311/) (2025)
- [Real-time Identity Defenses against Malicious Personalization of Diffusion Models](https://mlsanity.com/paper/2412.09844/) (2024)
- [Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms](https://mlsanity.com/paper/2603.28489/) (2026)
- [Hi-EF: Benchmarking Emotion Forecasting in Human-interaction](https://mlsanity.com/paper/2407.16406/) (2024)

## Abstract (arXiv)

Identity-Preserving Text-to-Video Generation (IPT2V) seeks to synthesize a temporally coherent video from a reference image and a textual description, while simultaneously preserving the subject's identity and allowing fine-grained control over facial dynamics. Although recent methods such as ID-Animator and ConsisID inject identity features only at inference time, they ignored the ID-irrelevant information contained in Facial embedding, leading to monotonous or inaccurate facial movements that poorly follow the prompt. We introduce Identity-Action Decoupling (IaD) framework as well as two loss function Identity Decoupling Loss and Text Alignment Loss to solve this problem. Without any subject-specific fine-tuning, IaD yields videos that (1) maintain cross-temporal identity consistency and (2) exhibit rich, controllable expressions and scene variations that closely match the input text.