# Subject-consistent Text-to-Video Generation on MSRVTT personalization 5

Source: [Subject-consistent Text-to-Video Generation on MSRVTT personalization 5](<https://www.sota2.com/research/sota/subject-consistent-text-to-video-generation-on-msrvtt-personalization-5>)

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

Data updated: 2026-03-23T12:04:50.342Z

Evaluation of subject-consistent text-to-video generation performance using the MSRVTT personalization 5 dataset, measured by Text-S, Vid-S, Subj-S, and Dync-D 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 | Subject-consistent text-to-video generation |
| Dataset (including any stated split) | MSRVTT personalization 5 |
| Metric | Text-S |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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-S](<https://www.sota2.com/research/sota/subject-consistent-text-to-video-generation-on-msrvtt-personalization-5.md?metric=Text-S>): Higher is better; unit: SCALAR.

- [Vid-S](<https://www.sota2.com/research/sota/subject-consistent-text-to-video-generation-on-msrvtt-personalization-5.md?metric=Vid-S>): Higher is better; unit: SCALAR.

- [Subj-S](<https://www.sota2.com/research/sota/subject-consistent-text-to-video-generation-on-msrvtt-personalization-5.md?metric=Subj-S>): Higher is better; unit: SCALAR.

- [Dync-D](<https://www.sota2.com/research/sota/subject-consistent-text-to-video-generation-on-msrvtt-personalization-5.md?metric=Dync-D>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Text-S | Result date | Report paper |
| --- | --- | --- | --- |
| Phantom | 0.27 | Not recorded | 69c0c9150636e5bf4afc3cc2 |
| LumosX | 0.258 | Not recorded | 69c0c9150636e5bf4afc3cc2 |
| SkyReels-A2 | 0.253 | Not recorded | 69c0c9150636e5bf4afc3cc2 |

### Phantom

Text-S: 0.27. Result ID: 69c12c5647f34ce924a9e129.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c9150636e5bf4afc3cc2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77ed1e209131cea7614e.md>)

[Implementation](<https://phantom-video.github.io/Phantom/>)

Recorded evaluation configuration: {"Base Model":"Wan2.1-1.3B-T2V"}. This record does not assert independent reproduction.

### LumosX

Text-S: 0.258. Result ID: 69c12c5647f34ce924a9e12a.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c9150636e5bf4afc3cc2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c0c9150636e5bf4afc3cc2.md>)

Recorded evaluation configuration: {"Base Model":"Wan2.1-1.3B-T2V"}. This record does not assert independent reproduction.

### SkyReels-A2

Text-S: 0.253. Result ID: 69c12c5647f34ce924a9e128.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c9150636e5bf4afc3cc2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77cc1e209131cea7566f.md>)

[Implementation](<https://github.com/SkyworkAI/SkyReels-A2>)

Recorded evaluation configuration: {"Base Model":"Wan2.1-14B-T2V"}. This record does not assert independent reproduction.

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