# Text-to-Video Generation on VBench Wan 2.2 14B 720P T2V (50 samples)

Source: [Text-to-Video Generation on VBench Wan 2.2 14B 720P T2V (50 samples)](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-wan-2-2-14b-720p-t2v-50-samples>)

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

Data updated: 2026-03-11T07:02:33.225Z

Evaluation of Text-to-Video Generation models using the specific VBench Wan 2.2 14B 720P T2V subset consisting of 50 samples, assessed using metrics like PSNR, SSIM, LPIPS, Image Quality, and Subject Consistency.

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) | VBench Wan 2.2 14B 720P T2V 50 samples |
| Metric | Image Quality |
| Unit | PERCENT |
| 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

- [Image Quality](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-wan-2-2-14b-720p-t2v-50-samples.md?metric=Image%20Quality>): Higher is better; unit: PERCENT.

- [PSNR](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-wan-2-2-14b-720p-t2v-50-samples.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-wan-2-2-14b-720p-t2v-50-samples.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [LPIPS](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-wan-2-2-14b-720p-t2v-50-samples.md?metric=LPIPS>): Lower is better; unit: SCALAR.

- [Subject Consistency](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-wan-2-2-14b-720p-t2v-50-samples.md?metric=Subject%20Consistency>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Image Quality | Result date | Report paper |
| --- | --- | --- | --- |
| SVG | 71.2 | Not recorded | 69b0f6f22d603e6de3e45c32 |
| SpargeAttn | 70.8 | Not recorded | 69b0f6f22d603e6de3e45c32 |
| Wan 2.2 14B | 70.6 | Not recorded | 69b0f6f22d603e6de3e45c32 |
| SVG-EAR | 70.6 | Not recorded | 69b0f6f22d603e6de3e45c32 |
| SVG2 | 70.5 | Not recorded | 69b0f6f22d603e6de3e45c32 |
| SVG-EAR-Turbo | 70.5 | Not recorded | 69b0f6f22d603e6de3e45c32 |

### SVG

Image Quality: 71.2. Result ID: 69b113076dbb7075b95aeb45.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f22d603e6de3e45c32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78471e209131cea7791d.md>)

Recorded evaluation configuration: {"Density":"30.25%","FLOP":"397.20 PFLOPS","Speedup":"1.59×"}. This record does not assert independent reproduction.

### SpargeAttn

Image Quality: 70.8. Result ID: 69b113076dbb7075b95aeb44.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f22d603e6de3e45c32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bbe1e209131cea8a28a.md>)

Recorded evaluation configuration: {"Density":"30.15%","FLOP":"396.83 PFLOPS","Speedup":"1.58×"}. This record does not assert independent reproduction.

### Wan 2.2 14B

Image Quality: 70.6. Result ID: 69b113076dbb7075b95aeb43.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f22d603e6de3e45c32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76f7d.md>)

Recorded evaluation configuration: {"Density":"100%","FLOP":"658.46 PFLOPS","Speedup":"1×"}. This record does not assert independent reproduction.

### SVG-EAR

Image Quality: 70.6. Result ID: 69b113076dbb7075b95aeb47.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f22d603e6de3e45c32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6f22d603e6de3e45c32.md>)

Recorded evaluation configuration: {"Density":"25.95%","FLOP":"387.53 PFLOPS","Speedup":"1.59×"}. This record does not assert independent reproduction.

### SVG2

Image Quality: 70.5. Result ID: 69b113076dbb7075b95aeb46.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f22d603e6de3e45c32.md>)

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

Recorded evaluation configuration: {"Density":"32.30%","FLOP":"404.88 PFLOPS","Speedup":"1.57×"}. This record does not assert independent reproduction.

### SVG-EAR-Turbo

Image Quality: 70.5. Result ID: 69b113076dbb7075b95aeb48.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f22d603e6de3e45c32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6f22d603e6de3e45c32.md>)

Recorded evaluation configuration: {"Density":"22.25%","FLOP":"370.71 PFLOPS","Speedup":"1.75×"}. This record does not assert independent reproduction.

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