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

Zhuofan Zong, Dongzhi Jiang, Bingqi Ma, Guanglu Song, Hao Shao +3 more
2/14/2026

No official code found. Best implementation: TempleX98/EasyRef (72 stars, Apache-2.0, last commit 2025-07-16).

Semantic Scholar

Code Implementations(1)

TempleX98/EasyRefCommunity58%
Apache-2.0

[ICML 2025] EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM

720Shell, PythonDec 12, 20241 years agoApache-2.0

Similar Papers

POTEC: Off-Policy Contextual Bandits for Large Action Spaces via Policy Decomposition

100% match2026

Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning

99% match2026

In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment

99% match1 repo22026

Robust Function-Calling for On-Device Language Model via Function Masking

99% match1 repo1152026

RetroInText: A Multimodal Large Language Model Enhanced Framework for Retrosynthetic Planning via In-Context Representation Learning

98% match2026

VP-SAM: Taming Segment Anything Model for Video Polyp Segmentation via Disentanglement and Spatio-Temporal Side Network

98% match2026

Cite this paper

@article{zong2026easyref,
  title  = {EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM},
  author = {Zhuofan Zong and Dongzhi Jiang and Bingqi Ma and Guanglu Song and Hao Shao and Dazhong Shen and Yu Liu and Hongsheng Li},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:0c5c7ccb283ca0c6424b25e439babfb59975c36b},
  journal = {ICML 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/0c5c7ccb283ca0c6424b25e439babfb59975c36b.svg)](https://codeofpaper.com/paper/0c5c7ccb283ca0c6424b25e439babfb59975c36b)

Discussion