# Image-to-Video Generation on VBench Wan 2.2 14B 720P I2V (subset of 50 samples)

Source: [Image-to-Video Generation on VBench Wan 2.2 14B 720P I2V (subset of 50 samples)](<https://www.sota2.com/research/sota/image-to-video-generation-on-vbench-wan-2-2-14b-720p-i2v-subset-of-50-samples>)

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

Data updated: 2026-03-11T07:02:33.182Z

Evaluation of Image-to-Video generation models using a specific 50-sample subset of the VBench Wan 2.2 14B 720P configuration. Metrics include objective measures (PSNR, SSIM, LPIPS) and VBench quality scores (ImgQual, SubCons).

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 | Image-to-Video Generation |
| Dataset (including any stated split) | VBench Wan 2.2 14B 720P I2V (subset of 50 samples) |
| Metric | ImgQual |
| 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

- [ImgQual](<https://www.sota2.com/research/sota/image-to-video-generation-on-vbench-wan-2-2-14b-720p-i2v-subset-of-50-samples.md?metric=ImgQual>): Higher is better; unit: PERCENT.

- [PSNR](<https://www.sota2.com/research/sota/image-to-video-generation-on-vbench-wan-2-2-14b-720p-i2v-subset-of-50-samples.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/image-to-video-generation-on-vbench-wan-2-2-14b-720p-i2v-subset-of-50-samples.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [LPIPS](<https://www.sota2.com/research/sota/image-to-video-generation-on-vbench-wan-2-2-14b-720p-i2v-subset-of-50-samples.md?metric=LPIPS>): Lower is better; unit: PERCENT.

- [SubCons](<https://www.sota2.com/research/sota/image-to-video-generation-on-vbench-wan-2-2-14b-720p-i2v-subset-of-50-samples.md?metric=SubCons>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ImgQual | Result date | Report paper |
| --- | --- | --- | --- |
| Wan 2.2 14B | 0.704 | Not recorded | 69b0f6f22d603e6de3e45c32 |
| SVG-EAR | 0.704 | Not recorded | 69b0f6f22d603e6de3e45c32 |
| SpargeAttn | 0.703 | Not recorded | 69b0f6f22d603e6de3e45c32 |
| SVG | 0.703 | Not recorded | 69b0f6f22d603e6de3e45c32 |
| SVG-EAR-Turbo | 0.702 | Not recorded | 69b0f6f22d603e6de3e45c32 |
| SVG2 | 0.701 | Not recorded | 69b0f6f22d603e6de3e45c32 |

### Wan 2.2 14B

ImgQual: 0.704. Result ID: 69b113076dbb7075b95aeb3d.

[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

ImgQual: 0.704. Result ID: 69b113076dbb7075b95aeb41.

[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":"23.64%","FLOP":"378.88 PFLOPS","Speedup":"1.61×"}. This record does not assert independent reproduction.

### SpargeAttn

ImgQual: 0.703. Result ID: 69b113076dbb7075b95aeb3e.

[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.

### SVG

ImgQual: 0.703. Result ID: 69b113076dbb7075b95aeb3f.

[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":"1.58×"}. This record does not assert independent reproduction.

### SVG-EAR-Turbo

ImgQual: 0.702. Result ID: 69b113076dbb7075b95aeb42.

[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":"20.42%","FLOP":"363.85 PFLOPS","Speedup":"1.77×"}. This record does not assert independent reproduction.

### SVG2

ImgQual: 0.701. Result ID: 69b113076dbb7075b95aeb40.

[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":"29.38%","FLOP":"393.95 PFLOPS","Speedup":"1.61×"}. This record does not assert independent reproduction.

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