# Text-to-Video Generation on Text-to-Video Generation prompts (test)

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

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

Data updated: 2026-02-26T05:59:06.367Z

Evaluation of Text-to-Video Generation models using the 'Text-to-Video Generation prompts (test)' dataset, assessed using QAlign and CLIP Score 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 | Text-to-Video Generation |
| Dataset (including any stated split) | Text-to-Video Generation prompts (test) |
| Metric | QAlign Image Quality |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [QAlign Image Quality](<https://www.sota2.com/research/sota/text-to-video-generation-on-text-to-video-generation-prompts-test.md?metric=QAlign%20Image%20Quality>): Higher is better; unit: SCALAR.

- [QAlign Image Aesthetic](<https://www.sota2.com/research/sota/text-to-video-generation-on-text-to-video-generation-prompts-test.md?metric=QAlign%20Image%20Aesthetic>): Higher is better; unit: SCALAR.

- [QAlign Video Quality](<https://www.sota2.com/research/sota/text-to-video-generation-on-text-to-video-generation-prompts-test.md?metric=QAlign%20Video%20Quality>): Higher is better; unit: SCALAR.

- [QAlign Video Aesthetic](<https://www.sota2.com/research/sota/text-to-video-generation-on-text-to-video-generation-prompts-test.md?metric=QAlign%20Video%20Aesthetic>): Higher is better; unit: SCALAR.

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

## Recorded results

| Method | QAlign Image Quality | Result date | Report paper |
| --- | --- | --- | --- |
| C3V | 4.03 | Not recorded | 68fa74f31e209131cea64cc0 |
| VideoCrafter2 | 3.839 | Not recorded | 68fa74f31e209131cea64cc0 |
| Comp4D | 1.687 | Not recorded | 68fa74f31e209131cea64cc0 |
| 4D-FY | 1.681 | Not recorded | 68fa74f31e209131cea64cc0 |

### C3V

QAlign Image Quality: 4.03. Result ID: 6993801d3a6c31484916660e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64cc0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64cc0.md>)

[Implementation](<https://aka.ms/c3v>)

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

### VideoCrafter2

QAlign Image Quality: 3.839. Result ID: 6993801d3a6c31484916660d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64cc0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71df1e209131cea537b0.md>)

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

### Comp4D

QAlign Image Quality: 1.687. Result ID: 6993801d3a6c31484916660c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64cc0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b51e209131cea580f5.md>)

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

### 4D-FY

QAlign Image Quality: 1.681. Result ID: 6993801d3a6c31484916660b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64cc0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73541e209131cea5bdbf.md>)

[Implementation](<https://github.com/sherwinbahmani/4dfy>)

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.
