DEIG: Detail-Enhanced Instance Generation with Fine-Grained Semantic Control

TL;DR

DEIG is a novel framework for fine-grained, controllable multi-instance image generation that leverages instance-aware representations and attention mechanisms to improve spatial and semantic accuracy.

Contribution

DEIG introduces an instance detail extractor and a detail fusion module for enhanced semantic control and scene coherence in multi-instance generation.

Findings

Outperforms existing methods in spatial and semantic accuracy

Demonstrates strong compositional generalization

Easily integrates into diffusion-based pipelines

Abstract

Multi-Instance Generation has advanced significantly in spatial placement and attribute binding. However, existing approaches still face challenges in fine-grained semantic understanding, particularly when dealing with complex textual descriptions. To overcome these limitations, we propose DEIG, a novel framework for fine-grained and controllable multi-instance generation. DEIG integrates an Instance Detail Extractor (IDE) that transforms text encoder embeddings into compact, instance-aware representations, and a Detail Fusion Module (DFM) that applies instance-based masked attention to prevent attribute leakage across instances. These components enable DEIG to generate visually coherent multi-instance scenes that precisely match rich, localized textual descriptions. To support fine-grained supervision, we construct a high-quality dataset with detailed, compositional instance captions generated by VLMs. We also introduce DEIG-Bench, a new benchmark with region-level annotations and multi-attribute prompts for both humans and objects. Experiments demonstrate that DEIG consistently outperforms existing approaches across multiple benchmarks in spatial consistency, semantic accuracy, and compositional generalization. Moreover, DEIG functions as a plug-and-play module, making it easily integrable into standard diffusion-based pipelines.