2026
Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual Generation
ICML 2026poster
We present Causal-Adapter, a modular framework that adapts frozen text-to-image diffusion backbones for counterfactual image generation. Our method enables causal interventions on target attributes while preserving all other aspects of the image, including the core identity. In contrast to prior app…