# CV-VAE: A Compatible Video VAE for Latent Generative Video Models

arXiv: https://arxiv.org/abs/2405.20279 · HTML: https://mlsanity.com/paper/2405.20279/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 30 May 2024.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [VideoCrafter1: Open Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2310.19512/) (2023)
- [VideoPoet: A Large Language Model for Zero-Shot Video Generation](https://mlsanity.com/paper/2312.14125/) (2023)
- [Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://mlsanity.com/paper/2210.02399/) (2022)
- [DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors](https://mlsanity.com/paper/2310.12190/) (2023)
- [MagicVideo: Efficient Video Generation With Latent Diffusion Models](https://mlsanity.com/paper/2211.11018/) (2022)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [MAGVIT: Masked Generative Video Transformer](https://mlsanity.com/paper/2212.05199/) (2022)
- [Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2309.15818/) (2023)

## Built on by (most cited first, 30 of 70)

- [SkyReels-V2: Infinite-length Film Generative Model](https://mlsanity.com/paper/2504.13074/) (2025)
- [Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model](https://mlsanity.com/paper/2504.08685/) (2025)
- [Improving the Diffusability of Autoencoders](https://mlsanity.com/paper/2502.14831/) (2025)
- [SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration](https://mlsanity.com/paper/2501.01320/) (2025)
- [WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model](https://mlsanity.com/paper/2411.17459/) (2024)
- [Improved Video VAE for Latent Video Diffusion Model](https://mlsanity.com/paper/2411.06449/) (2024)
- [Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices](https://mlsanity.com/paper/2410.11795/) (2024)
- [StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videos](https://mlsanity.com/paper/2409.07447/) (2024)
- [VidTok: A Versatile and Open-Source Video Tokenizer](https://mlsanity.com/paper/2412.13061/) (2024)
- [OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model](https://mlsanity.com/paper/2409.01199/) (2024)
- [Geometry-aware 4D Video Generation for Robot Manipulation](https://mlsanity.com/paper/2507.01099/) (2025)
- [OmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding](https://mlsanity.com/paper/2504.10825/) (2025)
- [LaVin-DiT: Large Vision Diffusion Transformer](https://mlsanity.com/paper/2411.11505/) (2024)
- [Large Motion Video Autoencoding with Cross-modal Video VAE](https://mlsanity.com/paper/2412.17805/) (2024)
- [HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation](https://mlsanity.com/paper/2503.24026/) (2025)
- [LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models](https://mlsanity.com/paper/2503.14325/) (2025)
- [Mimir: Improving Video Diffusion Models for Precise Text Understanding](https://mlsanity.com/paper/2412.03085/) (2024)
- [Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices](https://mlsanity.com/paper/2508.09136/) (2025)
- [DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder](https://mlsanity.com/paper/2509.25182/) (2025)
- [VidTwin: Video VAE with Decoupled Structure and Dynamics](https://mlsanity.com/paper/2412.17726/) (2024)
- [Survey of Video Diffusion Models: Foundations, Implementations, and Applications](https://mlsanity.com/paper/2504.16081/) (2025)
- [Demystifying Video Reasoning](https://mlsanity.com/paper/2603.16870/) (2026)
- [Physion-Eval: Evaluating Physical Realism in Generated Video via Human Reasoning](https://mlsanity.com/paper/2603.19607/) (2026)
- [Unified Dense Prediction of Video Diffusion](https://mlsanity.com/paper/2503.09344/) (2025)
- [H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models](https://mlsanity.com/paper/2504.10567/) (2025)
- [Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability](https://mlsanity.com/paper/2512.05394/) (2025)
- [SceneTok: A Compressed, Diffusable Token Space for 3D Scenes](https://mlsanity.com/paper/2602.18882/) (2026)
- [Rethinking Video Tokenization: A Conditioned Diffusion-based Approach](https://mlsanity.com/paper/2503.03708/) (2025)
- [MotionStrata: Hierarchical Motion Latents for Compact Video Autoencoding](https://mlsanity.com/paper/2506.07136/) (2025)
- [MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization](https://mlsanity.com/paper/2507.07997/) (2025)

## Abstract (arXiv)

Spatio-temporal compression of videos, utilizing networks such as Variational Autoencoders (VAE), plays a crucial role in OpenAI's SORA and numerous other video generative models. For instance, many LLM-like video models learn the distribution of discrete tokens derived from 3D VAEs within the VQVAE framework, while most diffusion-based video models capture the distribution of continuous latent extracted by 2D VAEs without quantization. The temporal compression is simply realized by uniform frame sampling which results in unsmooth motion between consecutive frames. Currently, there lacks of a commonly used continuous video (3D) VAE for latent diffusion-based video models in the research community. Moreover, since current diffusion-based approaches are often implemented using pre-trained text-to-image (T2I) models, directly training a video VAE without considering the compatibility with existing T2I models will result in a latent space gap between them, which will take huge computational resources for training to bridge the gap even with the T2I models as initialization. To address this issue, we propose a method for training a video VAE of latent video models, namely CV-VAE, whose latent space is compatible with that of a given image VAE, e.g., image VAE of Stable Diffusion (SD). The compatibility is achieved by the proposed novel latent space regularization, which involves formulating a regularization loss using the image VAE. Benefiting from the latent space compatibility, video models can be trained seamlessly from pre-trained T2I or video models in a truly spatio-temporally compressed latent space, rather than simply sampling video frames at equal intervals. With our CV-VAE, existing video models can generate four times more frames with minimal finetuning. Extensive experiments are conducted to demonstrate the effectiveness of the proposed video VAE.