# Multi-reference Image Generation on MultiBanana (Text and Tone Metrics)

Source: [Multi-reference Image Generation on MultiBanana (Text and Tone Metrics)](<https://www.sota2.com/research/sota/multi-reference-image-generation-on-multibanana-text-and-tone-metrics>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-26T08:47:57.218Z

Evaluation of Multi-reference Image Generation models on the MultiBanana dataset, specifically assessing Textual Quality and Tone fidelity using corresponding metrics.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Multi-reference Image Generation |
| Dataset (including any stated split) | MultiBanana |
| Metric | Text Quality Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Text Quality Score](<https://www.sota2.com/research/sota/multi-reference-image-generation-on-multibanana-text-and-tone-metrics.md?metric=Text%20Quality%20Score>): Higher is better; unit: SCALAR.

- [Tone Fidelity Score](<https://www.sota2.com/research/sota/multi-reference-image-generation-on-multibanana-text-and-tone-metrics.md?metric=Tone%20Fidelity%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Text Quality Score | Result date | Report paper |
| --- | --- | --- | --- |
| DyRef | 3.82 | Not recorded | 6a3e0791206542251d7cb496 |
| Qwen-2511 | 3.52 | Not recorded | 6a3e0791206542251d7cb496 |

### DyRef

Text Quality Score: 3.82. Result ID: 6a3e3cbafbc373592c607bf2.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e0791206542251d7cb496.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3e0791206542251d7cb496.md>)

Recorded evaluation configuration: {"Base Model":"Qwen-2511"}. This record does not assert independent reproduction.

### Qwen-2511

Text Quality Score: 3.52. Result ID: 6a3e3cbafbc373592c607bf1.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e0791206542251d7cb496.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a6a1e209131cea83137.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
