# Story-to-image generation on Shakoo Maku (human evaluation)

Source: [Story-to-image generation on Shakoo Maku (human evaluation)](<https://www.sota2.com/research/sota/story-to-image-generation-on-shakoo-maku-human-evaluation>)

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

Data updated: 2026-05-22T08:57:52.605Z

Human evaluation of Story-to-Image generation models, assessing output fidelity based on character consistency, story relevance, and overall visual quality.

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 | Story-to-image generation |
| Dataset (including any stated split) | Shakoo Maku (human evaluation) |
| Metric | Character Consistency |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Character Consistency](<https://www.sota2.com/research/sota/story-to-image-generation-on-shakoo-maku-human-evaluation.md?metric=Character%20Consistency>): Higher is better; unit: SCALAR.

- [Story Relevance](<https://www.sota2.com/research/sota/story-to-image-generation-on-shakoo-maku-human-evaluation.md?metric=Story%20Relevance>): Higher is better; unit: SCALAR.

- [Visual Quality](<https://www.sota2.com/research/sota/story-to-image-generation-on-shakoo-maku-human-evaluation.md?metric=Visual%20Quality>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Character Consistency | Result date | Report paper |
| --- | --- | --- | --- |
| S2ED | 4.4 | Not recorded | 6a0fe30bf984739ed6739d7f |
| Gemini-2.5 Pro | 3.3 | Not recorded | 6a0fe30bf984739ed6739d7f |
| GPT5 | 3.2 | Not recorded | 6a0fe30bf984739ed6739d7f |
| LayoutPrompt | 3.1 | Not recorded | 6a0fe30bf984739ed6739d7f |
| TokenInject | 2.8 | Not recorded | 6a0fe30bf984739ed6739d7f |
| PlainPrompt | 2.3 | Not recorded | 6a0fe30bf984739ed6739d7f |

### S2ED

Character Consistency: 4.4. Result ID: 6a101a86fbc373592c0943e4.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30bf984739ed6739d7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe30bf984739ed6739d7f.md>)

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

### Gemini-2.5 Pro

Character Consistency: 3.3. Result ID: 6a101a86fbc373592c0943e3.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30bf984739ed6739d7f.md>)

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

### GPT5

Character Consistency: 3.2. Result ID: 6a101a86fbc373592c0943e2.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30bf984739ed6739d7f.md>)

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

### LayoutPrompt

Character Consistency: 3.1. Result ID: 6a101a86fbc373592c0943e1.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30bf984739ed6739d7f.md>)

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

### TokenInject

Character Consistency: 2.8. Result ID: 6a101a86fbc373592c0943e0.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30bf984739ed6739d7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d2d1e209131cea38190.md>)

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

### PlainPrompt

Character Consistency: 2.3. Result ID: 6a101a86fbc373592c0943df.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30bf984739ed6739d7f.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.