DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generation

TL;DR

DiffGraph is an innovative framework that automatically merges online expert diffusion models for diverse text-to-image generation needs by dynamically activating relevant subgraphs.

Contribution

It introduces a scalable, agent-driven graph-based merging approach that leverages online experts for flexible, user-specific image generation.

Findings

Effective merging of online experts demonstrated

Flexible, user-driven model activation achieved

Outperforms existing model merging methods

Abstract

The rapid growth of the text-to-image (T2I) community has fostered a thriving online ecosystem of expert models, which are variants of pretrained diffusion models specialized for diverse generative abilities. Yet, existing model merging methods remain limited in fully leveraging abundant online expert resources and still struggle to meet diverse in-the-wild user needs. We present DiffGraph, a novel agent-driven graph-based model merging framework, which automatically harnesses online experts and flexibly merges them for diverse user needs. Our DiffGraph constructs a scalable graph and organizes ever-expanding online experts within it through node registration and calibration. Then, DiffGraph dynamically activates specific subgraphs based on user needs, enabling flexible combinations of different experts to achieve user-desired generation. Extensive experiments show the efficacy of our method.