Editing Implicit Assumptions in Text-to-Image Diffusion Models

Understand

Text-to-image diffusion models often make implicit assumptions about the world when generating images.

• While some assumptions are useful (e.g., the sky is blue), they can also be outdated, incorrect, or reflective of social biases present in the training data.
• Thus, there is a need to control these assumptions without requiring explicit user input or costly re-training.
• In this work, we aim to edit a given implicit assumption in a pre-trained diffusion model.