Achin Jain

Aug 16, 2024 | amazon.science | Ben Biggs |Arjun Seshadri |Yang Zou |Achin Jain

We present Diffusion Soup, a compartmentalization method for Text-to-Image Generation that averages the weights of diffusion models trained on sharded data. By construction, our approach enables training-free continual learning and unlearning with no additional memory or inference costs, since models corresponding to data shards can be added or removed by re-averaging.