Copertina

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Lei, Meng, Yuan, Tang, Chen, Ma, Xinzhu, Jiang, Jingyan, Wang, Xin, Wang, Zhi, Zhu, Wenwu
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
di: Sun, Haojun, et al.
Pubblicazione: (2024)

PTQ4DiT: Post-training Quantization for Diffusion Transformers
di: Wu, Junyi, et al.
Pubblicazione: (2024)

LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation
di: Yang, Lianwei, et al.
Pubblicazione: (2025)

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers
di: Deng, Juncan, et al.
Pubblicazione: (2024)

DiT4Edit: Diffusion Transformer for Image Editing
di: Feng, Kunyu, et al.
Pubblicazione: (2024)

Retraining-free Model Quantization via One-Shot Weight-Coupling Learning
di: Tang, Chen, et al.
Pubblicazione: (2024)

FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers
di: Chen, Ruichen, et al.
Pubblicazione: (2025)

Quantization Meets OOD: Generalizable Quantization-aware Training from a Flatness Perspective
di: Jiang, Jiacheng, et al.
Pubblicazione: (2025)

LaVin-DiT: Large Vision Diffusion Transformer
di: Wang, Zhaoqing, et al.
Pubblicazione: (2024)

$Δ$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
di: Chen, Pengtao, et al.
Pubblicazione: (2024)

Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising
di: Fang, Gongfan, et al.
Pubblicazione: (2024)

HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization
di: Liu, Wenxuan, et al.
Pubblicazione: (2024)

U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
di: Tian, Yuchuan, et al.
Pubblicazione: (2024)

Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution
di: Zhang, Xun, et al.
Pubblicazione: (2026)

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
di: Zhao, Tianchen, et al.
Pubblicazione: (2024)

S2DiT: Sandwich Diffusion Transformer for Mobile Streaming Video Generation
di: Zhao, Lin, et al.
Pubblicazione: (2026)

SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer
di: Zhu, Rui, et al.
Pubblicazione: (2024)

RTF-Q: Efficient Unsupervised Domain Adaptation with Retraining-free Quantization
di: Du, Nanyang, et al.
Pubblicazione: (2024)

Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer
di: Yang, Zhuoyi, et al.
Pubblicazione: (2024)

Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing
di: Tang, Siao, et al.
Pubblicazione: (2023)

Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
di: Li, Zhimin, et al.
Pubblicazione: (2024)

UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
di: Wang, Xiang, et al.
Pubblicazione: (2025)

DSV: Exploiting Dynamic Sparsity to Accelerate Large-Scale Video DiT Training
di: Tan, Xin, et al.
Pubblicazione: (2025)

PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference
di: Li, Ye, et al.
Pubblicazione: (2024)

DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression
di: Shi, Junqi, et al.
Pubblicazione: (2026)

DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer
di: Lyu, Hengye, et al.
Pubblicazione: (2026)

MiM-DiT: MoE in MoE with Diffusion Transformers for All-in-One Image Restoration
di: Kong, Lingshun, et al.
Pubblicazione: (2026)

Towards Accurate Post-training Quantization for Diffusion Models
di: Wang, Changyuan, et al.
Pubblicazione: (2023)

AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation
di: Wang, Kai, et al.
Pubblicazione: (2024)

Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration
di: Fang, Haipeng, et al.
Pubblicazione: (2025)

DiT-JSCC: Rethinking Deep JSCC with Diffusion Transformers and Semantic Representations
di: Tan, Kailin, et al.
Pubblicazione: (2026)

DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution
di: Duan, Zheng-Peng, et al.
Pubblicazione: (2025)

RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization
di: Yang, Kaicheng, et al.
Pubblicazione: (2025)

VITON-DiT: Learning In-the-Wild Video Try-On from Human Dance Videos via Diffusion Transformers
di: Zheng, Jun, et al.
Pubblicazione: (2024)

Unveiling Redundancy in Diffusion Transformers (DiTs): A Systematic Study
di: Sun, Xibo, et al.
Pubblicazione: (2024)

FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation
di: Wu, Zhuguanyu, et al.
Pubblicazione: (2025)

Shiva-DiT: Residual-Based Differentiable Top-$k$ Selection for Efficient Diffusion Transformers
di: Zhang, Jiaji, et al.
Pubblicazione: (2026)

DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation
di: Chen, Chen, et al.
Pubblicazione: (2025)

DiVE: DiT-based Video Generation with Enhanced Control
di: Jiang, Junpeng, et al.
Pubblicazione: (2024)

Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers
di: Feng, Weilun, et al.
Pubblicazione: (2025)