Login / Signup

MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization.

Tianchen ZhaoXuefei NingTongcheng FangEnshu LiuGuyue HuangZinan LinShengen YanGuohao DaiYu Wang
Published in: CoRR (2024)
Keyphrases
  • memory efficient
  • multiscale
  • input image
  • image data
  • image analysis
  • uniform quantization
  • integral image
  • diffusion models
  • image segmentation
  • high resolution
  • edge detection
  • quantization error
  • search engine