mlsanityData to 14 Oct 2026

DVD-Quant: Data-free Video Diffusion Transformers Quantization

arXiv 2505.18663 ↗First posted 24 May 2025cs.CVcited by 15

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion Transformers (DiTs) have emerged as the state-of-the-art architecture for video generation, yet their computational and memory demands hinder practical deployment. While post-training quantization (PTQ) presents a promising approach to accelerate Video DiT models, existing methods suffer from two critical limitations: (1) dependence on computation-heavy and inflexible calibration procedures, and (2) considerable performance deterioration after quantization. To address these challenges, we propose DVD-Quant, a novel Data-free quantization framework for Video DiTs. Our approach integrates three key innovations: (1) Bounded-init Grid Refinement (BGR) and (2) Auto-scaling Rotated Quantization (ARQ) for calibration data-free quantization error reduction, as well as (3) δ-Guided Bit Switching (δ-GBS) for adaptive bit-width allocation. Extensive experiments across multiple video generation benchmarks demonstrate that DVD-Quant achieves an approximately 2× speedup over full-precision baselines on advanced DiT models while maintaining visual fidelity. Notably, DVD-Quant is the first to enable W4A4 PTQ for Video DiTs without compromising video quality. Code and models will be available at https://github.com/lhxcs/DVD-Quant.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 41 of its 51 references that are in the map. First posted on arXiv 24 May 2025.

Builds on

41 of 51 references.

Closest ancestors · 13

Same direction, newest first

  1. 2025QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation9 Mar
  2. 2024SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models7 Nov
  3. 2024Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers25 Jun
  4. 2024ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation4 Jun
  5. 2024PTQ4DiT: Post-training Quantization for Diffusion Transformers25 May
  6. 2024TerDiT: Ternary Diffusion Models with Transformers23 May
  7. 2023FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models6 Dec
  8. 2023DeepCache: Accelerating Diffusion Models for Free1 Dec
  9. 2023Q-Diffusion: Quantizing Diffusion Models8 Feb
  10. 2022Scalable Diffusion Models with Transformers19 Dec
  11. 2022Post-training Quantization on Diffusion Models28 Nov
  12. 2022All are Worth Words: A ViT Backbone for Diffusion Models25 Sep
1 more
  1. 2022Classifier-Free Diffusion Guidance26 Jul

Other references · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  4. 2022Flow Matching for Generative Modelingcited by 5,702
  5. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
  6. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  7. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  8. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  9. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  10. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  11. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  12. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
16 more
  1. 2024Open-Sora: Democratizing Efficient Video Production for Allcited by 652
  2. 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMscited by 634
  3. 2024Latte: Latent Diffusion Transformer for Video Generationcited by 546
  4. 2024SpinQuant: LLM quantization with learned rotationscited by 471
  5. 2023OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Modelscited by 424
  6. 2024QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebookscited by 378
  7. 2024Timestep Embedding Tells: It's Time to Cache for Video Diffusion Modelcited by 269
  8. 2025SkyReels-V2: Infinite-length Film Generative Modelcited by 229
  9. 2025Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsitycited by 217
  10. 2025Open-Sora 2.0: Training a Commercial-Level Video Generation Model in 200kcited by 163
  11. 2024SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Accelerationcited by 160
  12. 2024ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generationcited by 132
  13. 2024Adaptive Caching for Faster Video Generation with Diffusion Transformerscited by 108
  14. 2024ARB-LLM: Alternating Refined Binarizations for Large Language Modelscited by 31
  15. 20242DQuant: Low-bit Post-Training Quantization for Image Super-Resolutioncited by 14
  16. 2025Progressive Binarization with Semi-Structured Pruning for LLMscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 10.

15 papers.

Sort:

By area:

  1. 2025LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generationcited by 12
  2. 2026SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routingcited by 10
  3. 2025DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Spacecited by 8
  4. 2025InfVSR: Toward Consistency-Driven Streaming Generative Video Super-Resolutioncited by 8
  5. 2026Efficient Video Diffusion Models: Advancements and Challengescited by 7
  6. 2026OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformerscited by 6
  7. 2026AdaTSQ: Pushing the Pareto Frontier of Diffusion Transformers via Temporal-Sensitivity Quantizationcited by 5
  8. 2026Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithmscited by 5
  9. 2025FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editingcited by 4
  10. 2025Plug-and-Play Fidelity Optimization for Diffusion Transformer Acceleration via Cumulative Error Minimizationcited by 2
  11. 2026PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformerscited by 1
  12. 2026Q-ARVD: Quantizing Autoregressive Video Diffusion Modelscited by 0
3 more
  1. 2026CAST: Reconstruction-Coupled Acceleration of Interactive World Modelscited by 0
  2. 2026VDOT++: Unified Few-Step Video Generation via Unbalanced Optimal Transport Distillationcited by 0
  3. 2026HGA-Quant: Heterogeneity-Aware Quantization for AutoRegressive Visual Generation Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers
  2. 20266Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models
  3. 2025Hardware-Friendly Static Quantization Method for Video Diffusion Transformers
  4. 2025S2Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
  5. 2025TR-DQ: Time-Rotation Diffusion Quantization
  6. 2024VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers
  7. 2024TaQ-DiT: Time-aware Quantization for Diffusion Transformers
  8. 2025QVGen: Pushing the Limit of Quantized Video Generative Models