| ### Model zoo of Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models | |
| ECCV 2024 | [Paper](https://arxiv.org/abs/2407.12383) | [Code](https://github.com/CharlesGong12/RECE) | |
| #### Overview | |
| This repository hosts the checkpoints for the RECE in the diffusers' format. | |
| These checkpoints can be directly loaded into your UNet if you are using diffusers. | |
| #### Checkpoints | |
| The checkpoints are named with the suffix "_ep*" indicating the epoch selected based on validation performance. | |
| #### Erasure Details | |
| For all concepts, the UCE parameters used are: $\lambda_1=0.1$ and $\lambda_2=0.1$. | |
| The regularization coefficients $\lambda$ are: | |
| * Nudity and unsafe concepts(I2P concepts), $\lambda=1e-1$. | |
| * Artistic styles, $\lambda=1e-3$. | |
| * Difficult objects (e.g., church and garbage truck), $\lambda=1e-3$. | |
| * Easy objects (e.g., English Springer, golf ball and parachute), $\lambda=1e-1$. | |
| * For other objects where erasing accuracies reach 0 using UCE, RECE's further erasure is not applied. | |
| --- | |
| license: apache-2.0 | |
| --- | |