# Image-to-Video Generation with Fine-Grained Motion Control on WebVid-10M 1k (val)

Source: [Image-to-Video Generation with Fine-Grained Motion Control on WebVid-10M 1k (val)](<https://www.sota2.com/research/sota/image-to-video-generation-with-fine-grained-motion-control-on-webvid-10m-1k-val>)

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

Data updated: 2026-02-26T05:45:04.543Z

Evaluation of Image-to-Video generation models focusing on fine-grained motion control, tested on the 1k subset of the WebVid-10M validation set, using FVD, FID, and Frame Consistency metrics.

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 with fine-grained motion control |
| Dataset (including any stated split) | WebVid-10M 1k (val) |
| Metric | FVD |
| Unit | SCALAR |
| Direction | Lower 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

- [FVD](<https://www.sota2.com/research/sota/image-to-video-generation-with-fine-grained-motion-control-on-webvid-10m-1k-val.md?metric=FVD>): Lower is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/image-to-video-generation-with-fine-grained-motion-control-on-webvid-10m-1k-val.md?metric=FID>): Lower is better; unit: SCALAR.

- [Frame Consistency](<https://www.sota2.com/research/sota/image-to-video-generation-with-fine-grained-motion-control-on-webvid-10m-1k-val.md?metric=Frame%20Consistency>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FVD | Result date | Report paper |
| --- | --- | --- | --- |
| MotionPro | 59.88 | Not recorded | 68fa78da1e209131cea7aced |
| MOFA-Video | 87.7 | Not recorded | 68fa78da1e209131cea7aced |
| DragNUWA | 96.65 | Not recorded | 68fa78da1e209131cea7aced |

### MotionPro

FVD: 59.88. Result ID: 6995a7073badfaffe6a4ce9b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78da1e209131cea7aced.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78da1e209131cea7aced.md>)

[Implementation](<https://zhw-zhang.github.io/MotionPro-page/>)

Recorded evaluation configuration: {"base\_architecture":"SVD"}. This record does not assert independent reproduction.

### MOFA-Video

FVD: 87.7. Result ID: 6995a7073badfaffe6a4ce9a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78da1e209131cea7aced.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74131e209131cea5fab4.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DragNUWA

FVD: 96.65. Result ID: 6995a7073badfaffe6a4ce99.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78da1e209131cea7aced.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa705d1e209131cea4a9ee.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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