OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models

TL;DR

OMG introduces an occlusion-friendly framework for multi-concept personalization in diffusion models, effectively handling occlusions and preserving identities through a novel two-stage sampling process that integrates multiple concepts seamlessly.

Contribution

The paper proposes a novel two-stage sampling method for multi-concept personalization that improves occlusion handling and identity preservation without additional tuning.

Findings

Outperforms existing methods in multi-concept personalization tasks.

Effectively preserves identities during occlusion scenarios.

Compatible with various single-concept models like LoRA and InstantID.

Abstract

Personalization is an important topic in text-to-image generation, especially the challenging multi-concept personalization. Current multi-concept methods are struggling with identity preservation, occlusion, and the harmony between foreground and background. In this work, we propose OMG, an occlusion-friendly personalized generation framework designed to seamlessly integrate multiple concepts within a single image. We propose a novel two-stage sampling solution. The first stage takes charge of layout generation and visual comprehension information collection for handling occlusions. The second one utilizes the acquired visual comprehension information and the designed noise blending to integrate multiple concepts while considering occlusions. We also observe that the initiation denoising timestep for noise blending is the key to identity preservation and layout. Moreover, our method can be combined with various single-concept models, such as LoRA and InstantID without additional tuning. Especially, LoRA models on civitai.com can be exploited directly. Extensive experiments demonstrate that OMG exhibits superior performance in multi-concept personalization.