# Image-to-Video on image-prompt pairs 220

Source: [Image-to-Video on image-prompt pairs 220](<https://www.sota2.com/research/sota/image-to-video-on-image-prompt-pairs-220>)

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

Data updated: 2026-03-25T13:36:33.414Z

Evaluation of Image-to-Video generation models using the 'image-prompt pairs 220' dataset, assessed using metrics such as OF, DD, FID, and FVD.

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 |
| Dataset (including any stated split) | image-prompt pairs 220 |
| Metric | OF |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [OF](<https://www.sota2.com/research/sota/image-to-video-on-image-prompt-pairs-220.md?metric=OF>): Higher is better; unit: SCALAR.

- [DD](<https://www.sota2.com/research/sota/image-to-video-on-image-prompt-pairs-220.md?metric=DD>): Higher is better; unit: PERCENT.

- [FID](<https://www.sota2.com/research/sota/image-to-video-on-image-prompt-pairs-220.md?metric=FID>): Lower is better; unit: SCALAR.

- [FVD](<https://www.sota2.com/research/sota/image-to-video-on-image-prompt-pairs-220.md?metric=FVD>): Lower is better; unit: SCALAR.

## Recorded results

| Method | OF | Result date | Report paper |
| --- | --- | --- | --- |
| Phased DMD | 9.84 | Not recorded | 690836e73ef7ccd74e5e532c |
| Base model | 9.32 | Not recorded | 690836e73ef7ccd74e5e532c |
| DMD2 | 7.87 | Not recorded | 690836e73ef7ccd74e5e532c |

### Phased DMD

OF: 9.84. Result ID: 69c3e3e547f34ce924ad6c71.

[Reporting paper](<https://www.sota2.com/research/paper/690836e73ef7ccd74e5e532c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690836e73ef7ccd74e5e532c.md>)

Recorded evaluation configuration: {"Sampling Steps":"4","Guidance Scale":"1"}. This record does not assert independent reproduction.

### Base model

OF: 9.32. Result ID: 69c3e3e547f34ce924ad6c6f.

[Reporting paper](<https://www.sota2.com/research/paper/690836e73ef7ccd74e5e532c.md>)

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

Recorded evaluation configuration: {"Sampling Steps":"40","Guidance Scale":"4"}. This record does not assert independent reproduction.

### DMD2

OF: 7.87. Result ID: 69c3e3e547f34ce924ad6c70.

[Reporting paper](<https://www.sota2.com/research/paper/690836e73ef7ccd74e5e532c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73501e209131cea5bc47.md>)

[Implementation](<https://tianweiy.github.io/dmd2/>)

Recorded evaluation configuration: {"Sampling Steps":"4","Guidance Scale":"1"}. This record does not assert independent reproduction.

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