Compositional Image Generation

The field aims to make image generators reliably follow instructions about what belongs in a scene, where it goes, how objects relate, and which details come from reference images. Approaches include layout- and graph-conditioned diffusion, spatial and occlusion controls, modular adapters and layered synthesis, and agentic planning with iterative generation and editing. Evaluation spans layout-to-image, multi-subject and multi-reference tasks, with benchmarks such as CogCanvas and TRACE-Bench probing identity, attribute binding, relations, and spatial accuracy. A central challenge is generalizing to unfamiliar combinations and crowded scenes: binding and identity errors grow with complexity, while stronger control must preserve image quality and remain efficient.