# Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video Generation

arXiv: https://arxiv.org/abs/2602.19161 · HTML: https://mlsanity.com/paper/2602.19161/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 38 of its 44 references that are in the map.
- First posted on arXiv 22 Feb 2026.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 38)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://mlsanity.com/paper/2410.10629/) (2024)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [Post-training Quantization on Diffusion Models](https://mlsanity.com/paper/2211.15736/) (2022)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations](https://mlsanity.com/paper/2308.06767/) (2023)
- [Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation](https://mlsanity.com/paper/2602.02214/) (2026)
- [VSA: Faster Video Diffusion with Trainable Sparse Attention](https://mlsanity.com/paper/2505.13389/) (2025)
- [The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation](https://mlsanity.com/paper/1905.00737/) (2019)
- [TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models](https://mlsanity.com/paper/2311.16503/) (2023)
- [VidGen-1M: A Large-Scale Dataset for Text-to-video Generation](https://mlsanity.com/paper/2408.02629/) (2024)
- [WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model](https://mlsanity.com/paper/2411.17459/) (2024)
- [Masked Autoencoders Enable Efficient Knowledge Distillers](https://mlsanity.com/paper/2208.12256/) (2022)
- [SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation](https://mlsanity.com/paper/2506.00523/) (2025)
- [SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device](https://mlsanity.com/paper/2412.10494/) (2024)
- [QVGen: Pushing the Limit of Quantized Video Generative Models](https://mlsanity.com/paper/2505.11497/) (2025)
- [SparseDM: Toward Sparse Efficient Diffusion Models](https://mlsanity.com/paper/2404.10445/) (2024)
- [LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models](https://mlsanity.com/paper/2503.14325/) (2025)

## Built on by (most cited first, 7 of 7)

- [Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation](https://mlsanity.com/paper/2607.26694/) (2026)
- [Omni-LiveAvatar: Minute-Level Real-Time Streaming Joint Audio-Video Avatar Generation](https://mlsanity.com/paper/2608.13602/) (2026)
- [PACE: Progressive Angular-to-Norm Contrastive Embedding](https://mlsanity.com/paper/2609.15152/) (2026)
- [EditaLive! Unified Character Video Editing for Live Streaming](https://mlsanity.com/paper/2608.27123/) (2026)
- [UnStep: Training-Free Acceleration of Causal Video Diffusion with Fewer Steps Than Distillation](https://mlsanity.com/paper/2609.32518/) (2026)
- [LatentQuant: Preserving the Policy-Facing Latent Contract under NVFP4 VAE Quantization](https://mlsanity.com/paper/2610.03959/) (2026)
- [LightVAE: Towards Compact and Efficient Video Autoencoders](https://mlsanity.com/paper/2610.14726/) (2026)

## Abstract (arXiv)

Latent diffusion models have enabled high-quality video synthesis, yet their inference remains costly and time-consuming. As diffusion transformers become increasingly efficient, the latency bottleneck inevitably shifts to VAE decoders. To reduce their latency while maintaining quality, we propose a universal acceleration framework for VAE decoders that preserves full alignment with the original latent distribution. Specifically, we propose (1) an independence-aware channel pruning method to effectively mitigate severe channel redundancy, and (2) a stage-wise dominant operator optimization strategy to address the high inference cost of the widely used causal 3D convolutions in VAE decoders. Based on these innovations, we construct a Flash-VAED family. Moreover, we design a three-phase dynamic distillation framework that efficiently transfers the capabilities of the original VAE decoder to Flash-VAED. Extensive experiments on Wan and LTX-Video VAE decoders demonstrate that our method outperforms baselines in both quality and speed, achieving approximately a 6× speedup while maintaining the reconstruction performance up to 96.9%. Notably, Flash-VAED accelerates the end-to-end generation pipeline by up to 36% with negligible quality drops on VBench-2.0. Our code is available at https://github.com/Aoko955/Flash-VAED.