
A novel post-training quantization scheme, QNCD, that effectively mitigates both intra and inter quantization noise in diffusion models, enabling efficient low-bit inference while preserving high-quality image synthesis.


coremsg

quantization-noise-correction-scheme-for-efficient-diffusion-model-inference


Quantization Noise Correction Scheme for Efficient Diffusion Model Inference


title_rewrite


An accurate post-training quantization framework for diffusion models that reduces quantization errors across generation timesteps and selects optimal calibration images to enable efficient image generation.


accurate-post-training-quantization-for-efficient-diffusion-model-deployment


Accurate Post-training Quantization for Efficient Diffusion Model Deployment
