Papers

• 2024

  • [ICLR - Aware Fine-Tuning of Low-Bit Diffusion Models [[code]](https://github.com/ThisisBillhe/EfficientDM)
  • [CVPR - training Quantization for Diffusion Models [[code]](https://github.com/ChangyuanWang17/APQ-DM)
  • [ECCV - Efficient Fine-Tuning for Quantized Diffusion Model [[code]](https://github.com/ugonfor/TuneQDM)
  • [NeurIPS - Resolution [[code]](https://github.com/zhengchen1999/BI-DiffSR)
  • [Arxiv - Training Vector Quantization for Diffusion Transformers
  • [CVPR - DM: Temporal Feature Maintenance Quantization for Diffusion Models [[code]](https://github.com/ModelTC/TFMQ-DM)
  • [ECCV - Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization [[code]](https://github.com/thu-nics/MixDQ)
  • [ECCV - Aware Correction for Quantized Diffusion Models
  • [ECCV - training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing [[code]](https://github.com/tsa18/PCR)
  • [NeurIPS - training Quantization for Diffusion Transformers [[code]](https://github.com/adreamwu/PTQ4DiT)
  • [NeurIPS - research/BitsFusion)
  • [NeurIPS - Lance/TerDiT)
  • [NeurIPS - Zheng/BiDM)
  • [NeurIPS
  • [AAAI - DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models [[code]](https://github.com/cantbebetter2/MPQ-DM)
  • [AAAI - Research/Qua2SeDiMo)
  • [AAAI - DM: Timestep-Channel Adaptive Quantization for Diffusion Models
  • [AAAI - Timestep Error Correction
  • [Arxiv - DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization
  • [Arxiv - DiT: Time-aware Quantization for Diffusion Transformers [[code]](https://github.com/yhwangs/TQ-DiT)

• 2023

  • [NeurIPS
  • [ICCV - Diffusion: Quantizing Diffusion Models [[code]](https://github.com/Xiuyu-Li/q-diffusion)
  • [CVPR - training Quantization on Diffusion Models [[code]](https://github.com/42Shawn/PTQ4DM)
  • [NeurIPS - Training Quantization for Diffusion Models [[code]](https://github.com/ziplab/PTQD)
  • [NeurIPS - DM: An Efficient Low-bit Quantized Diffusion Model

• 2025

  • [ICLR - Zheng/BinaryDM)
  • [ICLR - Bit Attention for Plug-and-play Inference Acceleration [[code]](https://github.com/thu-ml/SageAttention)
  • [ICML - thread INT4 Quantization [[code]](https://github.com/thu-ml/SageAttention)
  • [CVPR - Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution [[code]](https://github.com/libozhu03/PassionSR)
  • [Arxiv - Module and Timestep-Retraining in One-Step Diffusion based Image Super-Resolution [[code]](https://github.com/libozhu03/QArtSR) 
  • [ICLR - Rank Components for 4-Bit Diffusion Models [[code]](https://github.com/mit-han-lab/nunchaku)
  • [ICLR - Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation [[code]](https://github.com/thu-nics/ViDiT-Q)
  • [WACV
  • [CVPR - DiT: Accurate Post-Training Quantization for Diffusion Transformers [[code]](https://github.com/Juanerx/Q-DiT)
  • [ICCV - Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation [[code]](https://github.com/JunyiWuCode/QuantCache) 
  • [Arxiv - Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models
  • [ICCV - Guided Diffusion Models
  • [CVPR
  • [ICML - VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers [[code]](https://github.com/cantbebetter2/Q-VDiT)
  • [ICCV - bit Diffusion Model Quantization via Efficient Selective Finetuning [[code]](https://github.com/hatchetProject/QuEST)
  • [ICCV - Training Quantization[[code]](https://github.com/LeeDongYeun/dmq)
  • [ISCAS - QTA: Quantized Training Acceleration for Efficient LoRA Fine-Tuning of Diffusion Model
  • [Arxiv
  • [Arxiv - DQ: Time-Rotation Diffusion Quantization
  • [Arxiv - Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping
  • [Arxiv - DiT: Efficient Time-Aware Quantization for Diffusion Transformers
  • [Arxiv
  • [Arxiv - Aware Perspective
  • [Arxiv
  • [Arxiv - Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning
  • [Arxiv - Quant: Data-free Video Diffusion Transformers Quantization [[code]](https://github.com/lhxcs/DVD-Quant) 
  • [Arxiv - DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation