FRDiff : Feature Reuse for Universal Training-Free Acceleration of Diffusion Models

Junhyuk So, Jungwon Lee, Eunhyeok Park. FRDiff : Feature Reuse for Universal Training-Free Acceleration of Diffusion Models. In Ales Leonardis, Elisa Ricci 0001, Stefan Roth 0001, Olga Russakovsky, Torsten Sattler, Gül Varol, editors, Computer Vision - ECCV 2024 - 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part LXXIII. Volume 15131 of Lecture Notes in Computer Science, pages 328-344, Springer, 2024. [doi]

@inproceedings{SoLP24,
  title = {FRDiff : Feature Reuse for Universal Training-Free Acceleration of Diffusion Models},
  author = {Junhyuk So and Jungwon Lee and Eunhyeok Park},
  year = {2024},
  doi = {10.1007/978-3-031-73464-9_20},
  url = {https://doi.org/10.1007/978-3-031-73464-9_20},
  researchr = {https://researchr.org/publication/SoLP24},
  cites = {0},
  citedby = {0},
  pages = {328-344},
  booktitle = {Computer Vision - ECCV 2024 - 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part LXXIII},
  editor = {Ales Leonardis and Elisa Ricci 0001 and Stefan Roth 0001 and Olga Russakovsky and Torsten Sattler and Gül Varol},
  volume = {15131},
  series = {Lecture Notes in Computer Science},
  publisher = {Springer},
  isbn = {978-3-031-73464-9},
}