eval-unlearn: Benchmarking unlearning in Text-to-Image Diffusion Models
Eval-unlearn is an open-source Python library providing a unified, reproducible benchmarking framework for concept unlearning in T2I Diffusion models, integrating twelve published unlearning techniques spanning fine-tuning, closed-form model editing, and inference-time intervention.
Mansi, Nikhil Raghavan, Zi-Xia Huang et al.
· 0 citations