mlsanityData to 14 Oct 2026

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

arXiv 2603.20470 ↗First posted 20 Mar 2026cs.AIcited by 4

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 48 of its 56 references that are in the map. First posted on arXiv 20 Mar 2026.

Builds on

48 of 56 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025AutoLoRA: Automatic LoRA Retrieval and Fine-Grained Gated Fusion for Text-to-Image Generation4 Aug
  2. 2024Diffusion Soup: Model Merging for Text-to-Image Diffusion Models12 Jun
  3. 2024LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models18 Mar
  4. 2023Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models29 May
  5. 2022Inversion-Based Style Transfer with Diffusion Models23 Nov
  6. 2022DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models26 Oct
  7. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation25 Aug

Other references · 41

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  7. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  8. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  9. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  10. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,396
  11. 2016Variational Graph Auto-Encoderscited by 1,382
  12. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 977
29 more
  1. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 890
  2. 2024DoRA: Weight-Decomposed Low-Rank Adaptationcited by 758
  3. 2023Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunchcited by 694
  4. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 494
  5. 2023Directly Fine-Tuning Diffusion Models on Differentiable Rewardscited by 448
  6. 2023ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAscited by 194
  7. 2024Mixture of LoRA Expertscited by 181
  8. 2024GraphRouter: A Graph-based Router for LLM Selectionscited by 165
  9. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 119
  10. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 100
  11. 2024Multi-LoRA Composition for Image Generationcited by 80
  12. 2023LLaFS: When Large Language Models Meet Few-Shot Segmentationcited by 48
  13. 2025K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAscited by 48
  14. 2021ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregationcited by 39
  15. 2024LLMs are Good Action Recognizerscited by 37
  16. 2024Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generationcited by 30
  17. 2024Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligencecited by 27
  18. 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
  19. 2024Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackerscited by 24
  20. 2024LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generationcited by 19
  21. 2024SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Datacited by 14
  22. 2025LongDiff: Training-Free Long Video Generation in One Gocited by 13
  23. 2024DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Modelcited by 12
  24. 2024UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkerscited by 12
  25. 2024IterIS: Iterative Inference-Solving Alignment for LoRA Mergingcited by 11
  26. 2023LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognitioncited by 10
  27. 2024SceneLLM: Implicit Language Reasoning in LLM for Dynamic Scene Graph Generationcited by 5
  28. 2025An Image-like Diffusion Method for Human-Object Interaction Detectioncited by 5
  29. 2024Floating Anchor Diffusion Model for Multi-motif Scaffoldingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussionscited by 0
  2. 2026New Wide-Net-Casting Jailbreak Attacks Risk Large Modelscited by 0
  3. 2026Training-free Controllable Human Motion Generation under Heterogeneous Constraintscited by 0
  4. 2026Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024DiffusionAgent: Navigating Expert Models for Agentic Image Generation
  2. 2024ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models and Large Language Models
  3. 2025Learning Graph Representation of Agent Diffusers
  4. 2026Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation
  5. 2024ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers
  6. 2023TextDiffuser: Diffusion Models as Text Painters
  7. 2025DiffBrush:Just Painting the Art by Your Hands
  8. 2026OctoT2I: A Self-Evolving Agentic Text-to-Image Router