# MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation

arXiv: https://arxiv.org/abs/2511.22989 · HTML: https://mlsanity.com/paper/2511.22989/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 74 of its 87 references that are in the map.
- First posted on arXiv 28 Nov 2025.

## Builds on (most cited first, 30 of 74)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing](https://mlsanity.com/paper/2304.08465/) (2023)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [Zero-shot Image-to-Image Translation](https://mlsanity.com/paper/2302.03027/) (2023)
- [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://mlsanity.com/paper/2305.14720/) (2023)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [OmniGen: Unified Image Generation](https://mlsanity.com/paper/2409.11340/) (2024)

## Built on by (most cited first, 9 of 9)

- [GenArena: How Can We Achieve Human-Aligned Evaluation for Visual Generation Tasks?](https://mlsanity.com/paper/2602.06013/) (2026)
- [Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories](https://mlsanity.com/paper/2603.14153/) (2026)
- [MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generation](https://mlsanity.com/paper/2603.21937/) (2026)
- [Scaling Multi-Reference Image Generation with Dynamic Reward Optimization](https://mlsanity.com/paper/2606.26947/) (2026)
- [MIBE: Multi-subject Interaction Benchmark and Evaluator for Personalized Image Generation](https://mlsanity.com/paper/2607.01383/) (2026)
- [Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation](https://mlsanity.com/paper/2607.14962/) (2026)
- [RefAdapt-DiT: Adaptive Joint Attention for Reference-Conditioned Diffusion Transformers](https://mlsanity.com/paper/2609.32415/) (2026)
- [AutoRef: Harness Optimization for Agentic Multi-Reference Image Generation](https://mlsanity.com/paper/2609.35530/) (2026)
- [VIF-Bench: Evaluating Visual Instruction Following in Multi-Reference Image Generation](https://mlsanity.com/paper/2609.37709/) (2026)

## Abstract (arXiv)

Recent text-to-image generation models have acquired the ability of multi-reference generation and editing; that is, to inherit the appearance of subjects from multiple reference images and re-render them in new contexts. However, existing benchmark datasets often focus on generation using a single or a few reference images, which prevents us from measuring progress in model performance or identifying weaknesses when following instructions with a larger number of references. In addition, their task definitions are still vague, limited to axes such as ``what to edit'' or ``how many references are given'', and therefore fail to capture the challenges inherent in combining heterogeneous references. To address this gap, we introduce MultiBanana, which is designed to assess the edge of model capabilities by widely covering problems specific to multi-reference settings: (1) varying the number of references (up to 8), (2) domain mismatch among references (e.g., photo vs. anime), (3) scale mismatch between reference and target scenes, (4) references containing rare concepts (e.g., a red banana), and (5) multilingual textual references for rendering. Our analysis among a variety of text-to-image models reveals their respective performances, typical failure modes, and areas for improvement. MultiBanana is released as an open benchmark to push the boundaries and establish a standardized basis for fair comparison in multi-reference image generation. Our data and code are available at https://github.com/matsuolab/multibanana .