# Image-to-Video Generation on VBench-I2V 63-sample (test)

Source: [Image-to-Video Generation on VBench-I2V 63-sample (test)](<https://www.sota2.com/research/sota/image-to-video-generation-on-vbench-i2v-63-sample-test>)

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

Data updated: 2026-05-08T11:04:59.451Z

Evaluation of Image-to-Video generation models using the specific 63-sample test split of the VBench I2V dataset, reporting scores for Total Score, Subject consistency, Background fidelity, and Dynamic Degree.

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-I2V 63-sample (test) |
| Metric | Total Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Total Score](<https://www.sota2.com/research/sota/image-to-video-generation-on-vbench-i2v-63-sample-test.md?metric=Total%20Score>): Higher is better; unit: SCALAR.

- [Subject Consistency](<https://www.sota2.com/research/sota/image-to-video-generation-on-vbench-i2v-63-sample-test.md?metric=Subject%20Consistency>): Higher is better; unit: PERCENT.

- [Background Fidelity](<https://www.sota2.com/research/sota/image-to-video-generation-on-vbench-i2v-63-sample-test.md?metric=Background%20Fidelity>): Higher is better; unit: PERCENT.

- [Dynamic Degree](<https://www.sota2.com/research/sota/image-to-video-generation-on-vbench-i2v-63-sample-test.md?metric=Dynamic%20Degree>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Total Score | Result date | Report paper |
| --- | --- | --- | --- |
| SwiftI2V | 6.4284 | Not recorded | 69fd6e565497b3b670c896b2 |
| CineScale | 6.3638 | Not recorded | 69fd6e565497b3b670c896b2 |

### SwiftI2V

Total Score: 6.4284. Result ID: 69fdc34f47f34ce924e191f4.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e565497b3b670c896b2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e565497b3b670c896b2.md>)

[Implementation](<https://github.com/HKUST-LongGroup/SwiftI2V>)

Recorded evaluation configuration: {"Resolution":"2K","Frames":"81-frame"}. This record does not assert independent reproduction.

### CineScale

Total Score: 6.3638. Result ID: 69fdc34f47f34ce924e191f3.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e565497b3b670c896b2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ad51e209131cea8569b.md>)

Recorded evaluation configuration: {"Resolution":"2K","Frames":"81-frame"}. This record does not assert independent reproduction.

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