# Text-to-Video Generation on 65 dynamic scene prompts

Source: [Text-to-Video Generation on 65 dynamic scene prompts](<https://www.sota2.com/research/sota/text-to-video-generation-on-65-dynamic-scene-prompts>)

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

Data updated: 2026-02-26T05:57:59.921Z

Evaluation of Text-to-Video Generation models using the '65 dynamic scene prompts' dataset, assessed using metrics including Photorealism, Video-Text Alignment, Motion Quantity, and Motion 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 | Text-to-Video Generation |
| Dataset (including any stated split) | 65 dynamic scene prompts |
| Metric | Photorealism Score |
| Unit | PERCENT |
| 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

- [Photorealism Score](<https://www.sota2.com/research/sota/text-to-video-generation-on-65-dynamic-scene-prompts.md?metric=Photorealism%20Score>): Higher is better; unit: PERCENT.

- [Video-Text Alignment](<https://www.sota2.com/research/sota/text-to-video-generation-on-65-dynamic-scene-prompts.md?metric=Video-Text%20Alignment>): Higher is better; unit: PERCENT.

- [Motion Quantity](<https://www.sota2.com/research/sota/text-to-video-generation-on-65-dynamic-scene-prompts.md?metric=Motion%20Quantity>): Higher is better; unit: PERCENT.

- [Motion Quality](<https://www.sota2.com/research/sota/text-to-video-generation-on-65-dynamic-scene-prompts.md?metric=Motion%20Quality>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Photorealism Score | Result date | Report paper |
| --- | --- | --- | --- |
| Snap Video | 76.3 | Not recorded | 68fa72431e209131cea555c7 |
| Snap Video | 61.5 | Not recorded | 68fa72431e209131cea555c7 |
| Snap Video | 44.3 | Not recorded | 68fa72431e209131cea555c7 |

### Snap Video

Photorealism Score: 76.3. Result ID: 699226a03a6c3148490cf46f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72431e209131cea555c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72431e209131cea555c7.md>)

[Implementation](<https://www.sota2.com/snap-research.github.io/snapvideo>)

Recorded evaluation configuration: {"baseline\_comparison":"Floor33 \[17\]"}. This record does not assert independent reproduction.

### Snap Video

Photorealism Score: 61.5. Result ID: 699226a03a6c3148490cf46e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72431e209131cea555c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72431e209131cea555c7.md>)

[Implementation](<https://www.sota2.com/snap-research.github.io/snapvideo>)

Recorded evaluation configuration: {"baseline\_comparison":"PikaLab \[1\]"}. This record does not assert independent reproduction.

### Snap Video

Photorealism Score: 44.3. Result ID: 699226a03a6c3148490cf46d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72431e209131cea555c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72431e209131cea555c7.md>)

[Implementation](<https://www.sota2.com/snap-research.github.io/snapvideo>)

Recorded evaluation configuration: {"baseline\_comparison":"Gen-2 \[11\]"}. This record does not assert independent reproduction.

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