Ablating Concepts in Text-to-Image Diffusion Models
Abstract: Large-scale text-to-image diffusion models can generate high-fidelity images with powerful compositional ability. However, these models are typically trained on an enormous amount of Internet data, often containing copyrighted material, licensed images, and personal photos. Furthermore, they have been found to replicate the style of various living artists or memorize exact training samples. How can we remove such copyrighted concepts or images without retraining the model from scratch? To achieve this goal, we propose an efficient method of ablating concepts in the pretrained model, i.e., preventing the generation of a target concept. Our algorithm learns to match the image distribution for a target style, instance, or text prompt we wish to ablate to the distribution corresponding to an anchor concept. This prevents the model from generating target concepts given its text condition. Extensive experiments show that our method can successfully prevent the generation of the ablated concept while preserving closely related concepts in the model.
Keywords: model from generating / Ablating Concepts / copyrighted / diffusion / style / concepts given its text
Scifeed alert for new publicationsNever miss any articles matching your research from any publisher
- Get alerts for new papers matching your research
- Find out the new papers from selected authors
- Updated daily for 49'000+ journals and 6000+ publishers
- Define your Scifeed now
Click here to see the statistics on "ArXiv" .