DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generation
This addresses the challenge for users and developers in the text-to-image community to efficiently utilize specialized models for in-the-wild applications, though it appears incremental in improving model merging techniques.
The paper tackles the problem of leveraging diverse online expert text-to-image models to meet varied user needs by introducing DiffGraph, an automated agent-driven graph-based merging framework that dynamically combines experts for flexible generation.
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.