Simplify model architecture: [3]
Reduce sampling times: DDIM [1], PLMS [2]
Step distillation: [3] [4] [5] [6]
Adversarial distillation: [7]
References
[1] Song, Jiaming, Chenlin Meng, and Stefano Ermon. “Denoising diffusion implicit models.” arXiv preprint arXiv:2010.02502 (2020).
[2] Liu, Luping, et al. “Pseudo numerical methods for diffusion models on manifolds.” ICLR, (2022).
[3] Li, Yanyu, et al. “SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds.” NeurIPS(2023).
[4] Salimans, Tim, and Jonathan Ho. “Progressive distillation for fast sampling of diffusion models.” ICLR, 2022.
[5] Luhman, Eric, and Troy Luhman. “Knowledge distillation in iterative generative models for improved sampling speed.” arXiv preprint arXiv:2101.02388 (2021).
[6] Meng, Chenlin, et al. “On distillation of guided diffusion models.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023.
[7] https://stability.ai/research/adversarial-diffusion-distillation