Unified Editing of Panorama, 3D Scenes, and Videos Through Disentangled Self-Attention Injection

While text-to-image models have achieved impressive capabilities in image generation and editing, their application across various modalities often necessitates training separate models. We propose a novel editing method enabling unified editing across modalities utilizing only a basic 2D image text-to-image (T2I) diffusion model. We design a sampling method that facilitates editing consecutive images while maintaining semantic consistency utilizing shared self-attention features during both reference and consecutive image sampling processes. Inspired by existing method of single image editing with self attention injection and video editing with shared attention, we propose a novel unified editing framework that combines the strengths of both approaches. Different from previous work, our method enables editing across diverse modalities including 3D scenes, videos, and panorama images.