# Text-to-Video Generation on Wan 720P 2.1-14B

Source: [Text-to-Video Generation on Wan 720P 2.1-14B](<https://www.sota2.com/research/sota/text-to-video-generation-on-wan-720p-2-1-14b>)

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

Data updated: 2026-04-15T08:04:39.428Z

Evaluation of Text-to-Video generation models on the Wan 720P 2.1-14B dataset, assessed using quality metrics (T.F., M.S., A.Q., SSIM, PSNR, LPIPS) and performance metrics (Latency, Speedup).

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) | Wan Text-to-Video 720P 2.1-14B |
| Metric | T.F. |
| Unit | PERCENT |
| 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

- [T.F.](<https://www.sota2.com/research/sota/text-to-video-generation-on-wan-720p-2-1-14b.md?metric=T.F.>): Higher is better; unit: PERCENT.

- [M.S.](<https://www.sota2.com/research/sota/text-to-video-generation-on-wan-720p-2-1-14b.md?metric=M.S.>): Higher is better; unit: PERCENT.

- [A.Q.](<https://www.sota2.com/research/sota/text-to-video-generation-on-wan-720p-2-1-14b.md?metric=A.Q.>): Higher is better; unit: PERCENT.

- [SSIM](<https://www.sota2.com/research/sota/text-to-video-generation-on-wan-720p-2-1-14b.md?metric=SSIM>): Higher is better; unit: SCALAR.

- [PSNR](<https://www.sota2.com/research/sota/text-to-video-generation-on-wan-720p-2-1-14b.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [LPIPS](<https://www.sota2.com/research/sota/text-to-video-generation-on-wan-720p-2-1-14b.md?metric=LPIPS>): Lower is better; unit: SCALAR.

- [Latency (s)](<https://www.sota2.com/research/sota/text-to-video-generation-on-wan-720p-2-1-14b.md?metric=Latency%20(s)>): Lower is better; unit: TIME.

- [Speedup](<https://www.sota2.com/research/sota/text-to-video-generation-on-wan-720p-2-1-14b.md?metric=Speedup>): Higher is better; unit: SCALAR.

## Recorded results

| Method | T.F. | Result date | Report paper |
| --- | --- | --- | --- |
| PASA | 98.48 | Not recorded | 69df1ba67d0172140ec7ba27 |
| Dense | 98.47 | Not recorded | 69df1ba67d0172140ec7ba27 |
| SVG2 | 98.46 | Not recorded | 69df1ba67d0172140ec7ba27 |
| PISA | 98.45 | Not recorded | 69df1ba67d0172140ec7ba27 |

### PASA

T.F.: 98.48. Result ID: 69df468847f34ce924c7e010.

[Reporting paper](<https://www.sota2.com/research/paper/69df1ba67d0172140ec7ba27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1ba67d0172140ec7ba27.md>)

Recorded evaluation configuration: {"Sparsity":"85%"}. This record does not assert independent reproduction.

### Dense

T.F.: 98.47. Result ID: 69df468847f34ce924c7e00d.

[Reporting paper](<https://www.sota2.com/research/paper/69df1ba67d0172140ec7ba27.md>)

Recorded evaluation configuration: {"Sparsity":"0.00%"}. This record does not assert independent reproduction.

### SVG2

T.F.: 98.46. Result ID: 69df468847f34ce924c7e00e.

[Reporting paper](<https://www.sota2.com/research/paper/69df1ba67d0172140ec7ba27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be31e209131cea8b13e.md>)

Recorded evaluation configuration: {"Sparsity":"79.5%"}. This record does not assert independent reproduction.

### PISA

T.F.: 98.45. Result ID: 69df468847f34ce924c7e00f.

[Reporting paper](<https://www.sota2.com/research/paper/69df1ba67d0172140ec7ba27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69818134a8b01e76cc8e2365.md>)

[Implementation](<https://github.com/xie-lab-ml/piecewise-sparse-attention>)

Recorded evaluation configuration: {"Sparsity":"85%"}. This record does not assert independent reproduction.

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