较新（24.3）加速Diffusion模型推理的方法，附带参考文献

众人（某音、某书同名）

于 2024-10-18 20:02:05 发布

阅读量716

点赞数 8

CC 4.0 BY-SA版权

分类专栏：跟无神学AI 跟无神读视觉论文文章标签：人工智能算法生成对抗网络

本文链接：https://blog.youkuaiyun.com/m0_72806612/article/details/143061273

1.采用fast ODE solvers：

Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusionbased generative models. In: Conference on Neural Information Processing Systems (NeurIPS) (2022)

Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps. Conference on Neural Information Processing Systems (NeurIPS) 35, 5775–5787 (2022)

2.将原来的扩散模型作为教师，蒸馏到更快的少步学生网络

Meng, C., Rombach, R., Gao, R., Kingma, D., Ermon, S., Ho, J., Salimans, T.: On distillation of guided diffusion models. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)

Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. In: International Conference on Learning Representations (ICLR) (2022)

3.一些采用一致性模型训练

Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models. In: International Conference on