Training Data Attribution for Diffusion Models

Diffusion models have become increasingly popular for synthesizing high-quality samples based on training datasets. However, given the oftentimes enormous sizes of the training datasets, it is difficult to assess how training data impact the samples produced by a trained diffusion model.

Data and Resources

Cite this as

Zheng Dai, David K Gifford (2024). Dataset: Training Data Attribution for Diffusion Models. https://doi.org/10.57702/h7kn4dyo

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2306.02174
Author Zheng Dai
More Authors
David K Gifford
Homepage https://github.com/zheng-dai/GenEns