# EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM

arXiv: https://arxiv.org/abs/2412.09618 · HTML: https://mlsanity.com/paper/2412.09618/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Image editing and quality assessment, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 23 of its 51 references that are in the map.
- First posted on arXiv 12 Dec 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Image editing and quality assessment](https://mlsanity.com/mllm/image-editing-and-quality-assessment/)
- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 23 of 23)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [InstantID: Zero-shot Identity-Preserving Generation in Seconds](https://mlsanity.com/paper/2401.07519/) (2024)
- [SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models](https://mlsanity.com/paper/2311.07575/) (2023)
- [Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2403.16999/) (2024)
- [InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation](https://mlsanity.com/paper/2404.02733/) (2024)
- [Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models](https://mlsanity.com/paper/2409.10695/) (2024)
- [MoVA: Adapting Mixture of Vision Experts to Multimodal Context](https://mlsanity.com/paper/2404.13046/) (2024)
- [CSGO: Content-Style Composition in Text-to-Image Generation](https://mlsanity.com/paper/2408.16766/) (2024)
- [CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching](https://mlsanity.com/paper/2404.03653/) (2024)
- [InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation](https://mlsanity.com/paper/2407.00788/) (2024)
- [Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models](https://mlsanity.com/paper/2406.11831/) (2024)
- [Imagine yourself: Tuning-Free Personalized Image Generation](https://mlsanity.com/paper/2409.13346/) (2024)

## Built on by (most cited first, 25 of 25)

- [T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT](https://mlsanity.com/paper/2505.00703/) (2025)
- [Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation](https://mlsanity.com/paper/2508.09987/) (2025)
- [WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch](https://mlsanity.com/paper/2505.03733/) (2025)
- [Personalize Anything for Free with Diffusion Transformer](https://mlsanity.com/paper/2503.12590/) (2025)
- [DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving](https://mlsanity.com/paper/2601.01528/) (2026)
- [MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models](https://mlsanity.com/paper/2505.19415/) (2025)
- [Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models](https://mlsanity.com/paper/2511.16955/) (2025)
- [X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distillation](https://mlsanity.com/paper/2503.06134/) (2025)
- [UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections](https://mlsanity.com/paper/2509.24817/) (2025)
- [PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Models](https://mlsanity.com/paper/2503.10529/) (2025)
- [High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning](https://mlsanity.com/paper/2503.22179/) (2025)
- [HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion](https://mlsanity.com/paper/2512.14542/) (2025)
- [Alignment with Fill-In-the-Middle for Enhancing Code Generation](https://mlsanity.com/paper/2508.19532/) (2025)
- [AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization](https://mlsanity.com/paper/2603.17461/) (2026)
- [Improving Joint Audio-Video Generation with Cross-Modal Context Learning](https://mlsanity.com/paper/2603.18600/) (2026)
- [IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting](https://mlsanity.com/paper/2501.15641/) (2025)
- [IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance](https://mlsanity.com/paper/2509.26231/) (2025)
- [PrefGen: Multimodal Preference Learning for Preference-Conditioned Image Generation](https://mlsanity.com/paper/2512.06020/) (2025)
- [Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation](https://mlsanity.com/paper/2603.20725/) (2026)
- [Say Cheese! Detail-Preserving Portrait Collection Generation via Natural Language Edits](https://mlsanity.com/paper/2601.20511/) (2026)
- [FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining](https://mlsanity.com/paper/2606.20506/) (2026)
- [Image Generation Based on Image Style Extraction](https://mlsanity.com/paper/2510.01347/) (2025)
- [Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification](https://mlsanity.com/paper/2510.24078/) (2025)
- [Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation](https://mlsanity.com/paper/2605.26111/) (2026)
- [VIF-Bench: Evaluating Visual Instruction Following in Multi-Reference Image Generation](https://mlsanity.com/paper/2609.37709/) (2026)

## Abstract (arXiv)

Significant achievements in personalization of diffusion models have been witnessed. Conventional tuning-free methods mostly encode multiple reference images by averaging their image embeddings as the injection condition, but such an image-independent operation cannot perform interaction among images to capture consistent visual elements within multiple references. Although the tuning-based Low-Rank Adaptation (LoRA) can effectively extract consistent elements within multiple images through the training process, it necessitates specific finetuning for each distinct image group. This paper introduces EasyRef, a novel plug-and-play adaptation method that enables diffusion models to be conditioned on multiple reference images and the text prompt. To effectively exploit consistent visual elements within multiple images, we leverage the multi-image comprehension and instruction-following capabilities of the multimodal large language model (MLLM), prompting it to capture consistent visual elements based on the instruction. Besides, injecting the MLLM's representations into the diffusion process through adapters can easily generalize to unseen domains, mining the consistent visual elements within unseen data. To mitigate computational costs and enhance fine-grained detail preservation, we introduce an efficient reference aggregation strategy and a progressive training scheme. Finally, we introduce MRBench, a new multi-reference image generation benchmark. Experimental results demonstrate EasyRef surpasses both tuning-free methods like IP-Adapter and tuning-based methods like LoRA, achieving superior aesthetic quality and robust zero-shot generalization across diverse domains.