# Portrait Video Editing Empowered by Multimodal Generative Priors

arXiv: https://arxiv.org/abs/2409.13591 · HTML: https://mlsanity.com/paper/2409.13591/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 85 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Builds on (most cited first, 30 of 52)

- [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)
- [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)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions](https://mlsanity.com/paper/2303.12789/) (2023)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis](https://mlsanity.com/paper/2110.08985/) (2021)
- [FateZero: Fusing Attentions for Zero-shot Text-based Video Editing](https://mlsanity.com/paper/2303.09535/) (2023)
- [TokenFlow: Consistent Diffusion Features for Consistent Video Editing](https://mlsanity.com/paper/2307.10373/) (2023)
- [AnyDoor: Zero-shot Object-level Image Customization](https://mlsanity.com/paper/2307.09481/) (2023)
- [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020)
- [GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting](https://mlsanity.com/paper/2311.14521/) (2023)
- [StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation](https://mlsanity.com/paper/2112.11427/) (2021)
- [GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians](https://mlsanity.com/paper/2312.02069/) (2023)
- [Deferred Neural Rendering: Image Synthesis using Neural Textures](https://mlsanity.com/paper/1904.12356/) (2019)
- [Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation](https://mlsanity.com/paper/2306.07954/) (2023)
- [GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation](https://mlsanity.com/paper/2112.08867/) (2021)
- [CLIPstyler: Image Style Transfer with a Single Text Condition](https://mlsanity.com/paper/2112.00374/) (2021)
- [Dreamix: Video Diffusion Models are General Video Editors](https://mlsanity.com/paper/2302.01329/) (2023)
- [Generating Holistic 3D Human Motion from Speech](https://mlsanity.com/paper/2212.04420/) (2022)

## Built on by (most cited first, 12 of 12)

- [FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video](https://mlsanity.com/paper/2411.15604/) (2024)
- [A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation](https://mlsanity.com/paper/2508.09977/) (2025)
- [SparseLGS: Sparse View Language Embedded Gaussian Splatting](https://mlsanity.com/paper/2412.02245/) (2024)
- [Bringing Your Portrait to 3D Presence](https://mlsanity.com/paper/2511.22553/) (2025)
- [In-Context Sync-LoRA for Portrait Video Editing](https://mlsanity.com/paper/2512.03013/) (2025)
- [Text-based Animatable 3D Avatars with Morphable Model Alignment](https://mlsanity.com/paper/2504.15835/) (2025)
- [Follow Your Motion: A Generic Temporal Consistency Portrait Editing Framework with Trajectory Guidance](https://mlsanity.com/paper/2503.22225/) (2025)
- [EmoDiffTalk:Emotion-aware Diffusion for Editable 3D Gaussian Talking Head](https://mlsanity.com/paper/2512.05991/) (2025)
- [GTAvatar: Bridging Gaussian Splatting and Texture Mapping for Relightable and Editable Gaussian Avatars](https://mlsanity.com/paper/2512.09162/) (2025)
- [GSwap: Realistic Head Swapping with Dynamic Neural Gaussian Field](https://mlsanity.com/paper/2603.23168/) (2026)
- [Giving Faces Their Feelings Back: Explicit Emotion Control for Feedforward Single-Image 3D Head Avatars](https://mlsanity.com/paper/2604.14541/) (2026)
- [HarmoVid: Relightful Video Portrait Harmonization](https://mlsanity.com/paper/2605.28811/) (2026)

## Abstract (arXiv)

We introduce PortraitGen, a powerful portrait video editing method that achieves consistent and expressive stylization with multimodal prompts. Traditional portrait video editing methods often struggle with 3D and temporal consistency, and typically lack in rendering quality and efficiency. To address these issues, we lift the portrait video frames to a unified dynamic 3D Gaussian field, which ensures structural and temporal coherence across frames. Furthermore, we design a novel Neural Gaussian Texture mechanism that not only enables sophisticated style editing but also achieves rendering speed over 100FPS. Our approach incorporates multimodal inputs through knowledge distilled from large-scale 2D generative models. Our system also incorporates expression similarity guidance and a face-aware portrait editing module, effectively mitigating degradation issues associated with iterative dataset updates. Extensive experiments demonstrate the temporal consistency, editing efficiency, and superior rendering quality of our method. The broad applicability of the proposed approach is demonstrated through various applications, including text-driven editing, image-driven editing, and relighting, highlighting its great potential to advance the field of video editing. Demo videos and released code are provided in our project page: https://ustc3dv.github.io/PortraitGen/