AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

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

Yuta Oshima, Daiki Miyake, Kohsei Matsutani, Yusuke Iwasawa, Masahiro Suzuki, Yutaka Matsuo, Hiroki Furuta

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Increase number of references from 3 to 8 (ablation)all evaluated models · MultiBanana total scoretotal scoreHurt
Add iterative prompt refinement agent (IPR) (ablation)GPT-Image-1 · MultiBanana Two referencesavg score: 6.585 -> 6.808Improved
Add iterative prompt refinement agent (IPR) (ablation)GPT-Image-1 · MultiBanana X-1 + Localavg score: 5.147 -> 5.419Improved
Add iterative prompt refinement agent (IPR) (ablation)Nano Banana · MultiBanana Two referencesavg score: 4.891 -> 5.030 (Two); 4.118 -> 4.030 (X-1 + Local)Mixed
Add iterative prompt refinement agent (IPR) (ablation)Nano Banana · MultiBanana Singleavg score: 7.817 -> 7.606Hurt
Background replacement vs other task types (X-1 + Background)closed and open models · MultiBananaavg score: Nano Banana 3.575 vs 4.453 (X Objects)Hurt
Cross-domain, scale/view, rare concept, multilingual referencesmost models · MultiBananascoreHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy