# QVGen: Pushing the Limit of Quantized Video Generative Models

arXiv: https://arxiv.org/abs/2505.11497 · HTML: https://mlsanity.com/paper/2505.11497/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 82 of its 102 references that are in the map.
- First posted on arXiv 16 May 2025.

## Placed in

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

## Builds on (most cited first, 30 of 82)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming](https://mlsanity.com/paper/1309.5549/) (2013)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)

## Built on by (most cited first, 22 of 22)

- [PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models](https://mlsanity.com/paper/2506.16054/) (2025)
- [DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder](https://mlsanity.com/paper/2509.25182/) (2025)
- [SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning](https://mlsanity.com/paper/2508.06447/) (2025)
- [Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation](https://mlsanity.com/paper/2604.03118/) (2026)
- [LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generation](https://mlsanity.com/paper/2510.08318/) (2025)
- [SalQ-VLM: Fine-Grained Saliency-Guided Quantization for Vision-Language Models](https://mlsanity.com/paper/2508.03351/) (2025)
- [DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space](https://mlsanity.com/paper/2509.25180/) (2025)
- [LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit](https://mlsanity.com/paper/2508.09981/) (2025)
- [Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing](https://mlsanity.com/paper/2602.02159/) (2026)
- [Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video Generation](https://mlsanity.com/paper/2602.19161/) (2026)
- [Efficient Video Diffusion Models: Advancements and Challenges](https://mlsanity.com/paper/2604.15911/) (2026)
- [Feed-Forward 3D Gaussian Splatting Compression with Long-Context Modeling](https://mlsanity.com/paper/2512.00877/) (2025)
- [OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers](https://mlsanity.com/paper/2607.02461/) (2026)
- [Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms](https://mlsanity.com/paper/2603.28489/) (2026)
- [Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers](https://mlsanity.com/paper/2603.10744/) (2026)
- [Omni-LiveAvatar: Minute-Level Real-Time Streaming Joint Audio-Video Avatar Generation](https://mlsanity.com/paper/2608.13602/) (2026)
- [PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers](https://mlsanity.com/paper/2609.33384/) (2026)
- [Q-ARVD: Quantizing Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2605.21072/) (2026)
- [RotateAttention: RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation](https://mlsanity.com/paper/2607.02584/) (2026)
- [Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation](https://mlsanity.com/paper/2607.06631/) (2026)
- [DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video Generation](https://mlsanity.com/paper/2609.04031/) (2026)
- [LatentQuant: Preserving the Policy-Facing Latent Contract under NVFP4 VAE Quantization](https://mlsanity.com/paper/2610.03959/) (2026)

## Abstract (arXiv)

Video diffusion models (DMs) have enabled high-quality video synthesis. Yet, their substantial computational and memory demands pose serious challenges to real-world deployment, even on high-end GPUs. As a commonly adopted solution, quantization has proven notable success in reducing cost for image DMs, while its direct application to video DMs remains ineffective. In this paper, we present QVGen, a novel quantization-aware training (QAT) framework tailored for high-performance and inference-efficient video DMs under extremely low-bit quantization (e.g., 4-bit or below). We begin with a theoretical analysis demonstrating that reducing the gradient norm is essential to facilitate convergence for QAT. To this end, we introduce auxiliary modules (Phi) to mitigate large quantization errors, leading to significantly enhanced convergence. To eliminate the inference overhead of Phi, we propose a rank-decay strategy that progressively eliminates Phi. Specifically, we repeatedly employ singular value decomposition (SVD) and a proposed rank-based regularization γ to identify and decay low-contributing components. This strategy retains performance while zeroing out additional inference overhead. Extensive experiments across 4 state-of-the-art (SOTA) video DMs, with parameter sizes ranging from 1.3B~14B, show that QVGen is the first to reach full-precision comparable quality under 4-bit settings. Moreover, it significantly outperforms existing methods. For instance, our 3-bit CogVideoX-2B achieves improvements of +25.28 in Dynamic Degree and +8.43 in Scene Consistency on VBench. Code and models are available at https://github.com/ModelTC/QVGen.