A Survey on Video Diffusion Models 
Zhen Xing, Qijun Feng, Haoran Chen, Qi Dai, Han Hu, Hang Xu, Zuxuan Wu, Yu-Gang Jiang
(Source: Make-A-Video, SimDA, PYoCo, SVD , Video LDM and Tune-A-Video)
- [News] We are planning to update the survey soon to encompass the latest work. If you have any suggestions, please feel free to contact us.
- [News] The Chinese translation is available on Zhihu. Special thanks to Dai-Wenxun for this.
Open-source Toolboxes and Foundation Models
| Methods | Task | Github |
|---|---|---|
| Sora | T2V Generation & Editing | - |
| VideoPoet | T2V Generation & Editing | - |
| Stable Video Diffusion | T2V Generation |  |
| NeverEnds | T2V Generation | - |
| Pika | T2V Generation | - |
| EMU-Video | T2V Generation | - |
| GEN-2 | T2V Generation & Editing | - |
| ModelScope | T2V Generation |  |
| ZeroScope | T2V Generation | - |
| T2V Synthesis Colab | T2V Genetation |  |
| VideoCraft | T2V Genetation & Editing |  |
| Diffusers (T2V synthesis) | T2V Genetation | - |
| AnimateDiff | Personalized T2V Genetation |  |
| Text2Video-Zero | T2V Genetation |  |
| HotShot-XL | T2V Genetation |  |
| Genmo | T2V Genetation | - |
| Fliki | T2V Generation | - |
Table of Contents
Video Generation
Data
Caption-level
| Title | arXiv | Github | WebSite | Pub. & Date |
|---|---|---|---|---|
| CelebV-Text: A Large-Scale Facial Text-Video Dataset |  |
 |
- | CVPR, 2023 |
| InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation | |
 |
- | May, 2023 |
| VideoFactory: Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation | |
- | - | May, 2023 |
| Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions | |
- | - | Nov, 2021 |
| Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval | |
- | - | ICCV, 2021 |
| MSR-VTT: A Large Video Description Dataset for Bridging Video and Language | |
- | - | CVPR, 2016 |
Category-level
| Title | arXiv | Github | WebSite | Pub. & Date |
|---|---|---|---|---|
| UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild | |
- | - | Dec., 2012 |
| First Order Motion Model for Image Animation | |
- | - | May, 2023 |
| Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks | |
- | - | CVPR,2018 |
Metric and BenchMark
| Title | arXiv | Github | WebSite | Pub. & Date |
|---|---|---|---|---|
| Towards A Better Metric for Text-to-Video Generation | |
- |  |
Jan, 2024 |
| AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI | |
- | - | Jan, 2024 |
| VBench: Comprehensive Benchmark Suite for Video Generative Models | |
 |
|
Nov, 2023 |
| FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation | |
- | - | NeurIPS, 2023 |
| CVPR 2023 Text Guided Video Editing Competition | |
- | - | Oct., 2023 |
| EvalCrafter: Benchmarking and Evaluating Large Video Generation Models | |
 |
|
Oct., 2023 |
| Measuring the Quality of Text-to-Video Model Outputs: Metrics and Dataset | |
- | - | Sep., 2023 |
Text-to-Video Generation
Training-based
Training-free
Video Generation with other conditions
Pose-guided Video Generation
Motion-guided Video Generation
| Title | arXiv | Github | WebSite | Pub. & Date |
|---|---|---|---|---|
| Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling | |
- | - | Jan., 2024 |
| Motion-Zero: Zero-Shot Moving Object Control Framework for Diffusion-Based Video Generation | |
- | - | Jan., 2024 |
| Customizing Motion in Text-to-Video Diffusion Models | |
- | |
Dec., 2023 |
| VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models | |
 |
|
Nov., 2023 |
| Motion-Conditioned Diffusion Model for Controllable Video Synthesis | |
- | |
Apr., 2023 |
| DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory | |
- | - | Aug., 2023 |
Sound-guided Video Generation
| Title | arXiv | Github | WebSite | Pub. & Date |
|---|---|---|---|---|
| The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion | |
- | - | ICCV, 2023 |
| Generative Disco: Text-to-Video Generation for Music Visualization | |
- | - | Apr., 2023 |
| AADiff: Audio-Aligned Video Synthesis with Text-to-Image Diffusion | |
- | - | CVPRW, 2023 |
Image-guided Video Generation
Brain-guided Video Generation
| Title | arXiv | Github | WebSite | Pub. & Date |
|---|---|---|---|---|
| NeuroCine: Decoding Vivid Video Sequences from Human Brain Activties | |
- | - | Feb., 2024 |
| Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity | |
 |
|
NeurIPS, 2023 |
Depth-guided Video Generation
| Title | arXiv | Github | WebSite | Pub. & Date |
|---|---|---|---|---|
| Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation | |
 |
|
Jul., 2023 |
| Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance | |
 |
|
Jun., 2023 |
Multi-modal guided Video Generation
Unconditional Video Generation
U-Net based
| Title | arXiv | Github | WebSite | Pub. & Date |
|---|---|---|---|---|
| Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation | |
- | - | Feb. 2024 |
| Video Probabilistic Diffusion Models in Projected Latent Space | |
 |
|
CVPR 2023 |
| VIDM: Video Implicit Diffusion Models | |
 |
|
AAAI 2023 |
| GD-VDM: Generated Depth for better Diffusion-based Video Generation | |
 |
- | Jun., 2023 |
| LEO: Generative Latent Image Animator for Human Video Synthesis | |
 |
|
May., 2023 |
Transformer based
| Title | arXiv | Github | WebSite | Pub. & Date |
|---|---|---|---|---|
| Latte: Latent Diffusion Transformer for Video Generation | |
 |
|
Jan., 2024 |
| VDT: An Empirical Study on Video Diffusion with Transformers | |
 |
- | May, 2023 |
Video Completion
Video Enhancement and Restoration
| Title | arXiv | Github | WebSite | Pub. & Date |
|---|---|---|---|---|
| Towards Language-Driven Video Inpainting via Multimodal Large Language Models | |
 |
|
Jan., 2024 |
| Inflation with Diffusion: Efficient Temporal Adaptation for Text-to-Video Super-Resolution | - | - | - | WACW, 2023 |
| Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution | |
 |
|
Dec., 2023 |
| AVID: Any-Length Video Inpainting with Diffusion Model | |
 |
|
Dec., 2023 |
| Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution | |
 |
- | CVPR 2023 |
| LDMVFI: Video Frame Interpolation with Latent Diffusion Models | |
- | - | Mar., 2023 |
| CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streaming | |
- | - | Nov., 2022 |
| Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videos | |
- | - | May., 2023 |
Video Prediction
| Title | arXiv | Github | Website | Pub. & Date |
|---|---|---|---|---|
| STDiff: Spatio-temporal Diffusion for Continuous Stochastic Video Prediction | |
 |
- | Dec, 2023 |
| Video Diffusion Models with Local-Global Context Guidance | |
 |
- | IJCAI, 2023 |
| Seer: Language Instructed Video Prediction with Latent Diffusion Models | |
- | |
Mar., 2023 |
| Diffusion Models for Video Prediction and Infilling | |
 |
|
TMLR 2022 |
| McVd: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation | |
|
|
NeurIPS 2022 |
| Diffusion Probabilistic Modeling for Video Generation | |
 |
- | Mar., 2022 |
| Flexible Diffusion Modeling of Long Videos | |
 |
|
May, 2022 |
| Control-A-Video: Controllable Text-to-Video Generation with Diffusion Models | |
 |
|
May, 2023 |
Video Editing
General Editing Model
Training-free Editing Model
One-shot Editing Model
Instruct-guided Video Editing
| Title | arXiv | Github | Website | Pub. Date |
|---|---|---|---|---|
| Fairy: Fast Parallellized Instruction-Guided Video-to-Video Synthesis | |
- | |
Dec, 2023 |
| Neural Video Fields Editing | |
 |
|
Dec, 2023 |
| VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Models | |
 |
|
Nov, 2023 |
| Consistent Video-to-Video Transfer Using Synthetic Dataset | |
- | - | Nov., 2023 |
| InstructVid2Vid: Controllable Video Editing with Natural Language Instructions | |
- | - | May, 2023 |
| Collaborative Score Distillation for Consistent Visual Synthesis | |
- | - | July, 2023 |
Motion-guided Video Editing
| Title | arXiv | Github | Website | Pub. Date |
|---|---|---|---|---|
| MotionCtrl: A Unified and Flexible Motion Controller for Video Generation | |
 |
|
Nov, 2023 |
| Drag-A-Video: Non-rigid Video Editing with Point-based Interaction | |
- | |
Nov, 2023 |
| DragVideo: Interactive Drag-style Video Editing | |
 |
- | Nov, 2023 |
| VideoControlNet: A Motion-Guided Video-to-Video Translation Framework by Using Diffusion Model with ControlNet | |
- | |
July, 2023 |
Sound-guided Video Editing
| Title | arXiv | Github | Website | Pub. Date |
|---|---|---|---|---|
| Speech Driven Video Editing via an Audio-Conditioned Diffusion Model | |
- | - | May., 2023 |
| Soundini: Sound-Guided Diffusion for Natural Video Editing | |
 |
|
Apr., 2023 |
Multi-modal Control Editing Model
| Title | arXiv | Github | Website | Pub. Date |
|---|---|---|---|---|
| DreamVideo: Composing Your Dream Videos with Customized Subject and Motion | |
 |
|
Dec, 2023 |
| MagicStick: Controllable Video Editing via Control Handle Transformations | |
 |
|
Nov, 2023 |
| SAVE: Protagonist Diversification with Structure Agnostic Video Editing | |
- | |
Nov, 2023 |
| MotionZero:Exploiting Motion Priors for Zero-shot Text-to-Video Generation | |
- | - | May, 2023 |
| CCEdit: Creative and Controllable Video Editing via Diffusion Models | |
- | - | Sep, 2023 |
| Make-A-Protagonist: Generic Video Editing with An Ensemble of Experts | |
 |
|
May, 2023 |
Domain-specific Editing Model
Non-diffusion Editing model
| Title | arXiv | Github | Website | Pub. Date |
|---|---|---|---|---|
| DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing | |
- | |
Oct., 2023 |
| INVE: Interactive Neural Video Editing | |
- | |
Jul., 2023 |
| Shape-Aware Text-Driven Layered Video Editing | |
- | |
Jan., 2023 |
Video Understanding
Contact
If you have any suggestions or find our work helpful, feel free to contact us
Homepage: Zhen Xing
Email: [email protected]
If you find our survey is useful in your research or applications, please consider giving us a star ๐ and citing it by the following BibTeX entry.
@article{vdmsurvey,
title={A Survey on Video Diffusion Models},
author={Zhen Xing and Qijun Feng and Haoran Chen and Qi Dai and Han Hu and Hang Xu and Zuxuan Wu and Yu-Gang Jiang},
journal={arXiv preprint arXiv:2310.10647},
year={2023}
}