# Transition Video Generation on Webvid10M (test)

Source: [Transition Video Generation on Webvid10M (test)](<https://www.sota2.com/research/sota/transition-video-generation-on-webvid10m-test>)

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

Data updated: 2026-02-26T05:48:19.217Z

Evaluation of models generating smooth temporal transitions within video sequences using the test split of the Webvid10M dataset, assessed via LPIPS and CLIPSIM metrics focusing on first frame and frame-to-frame 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 | Transition Video Generation |
| Dataset (including any stated split) | Webvid10M (test) |
| Metric | LPIPS (First Frame) |
| 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

- [LPIPS (First Frame)](<https://www.sota2.com/research/sota/transition-video-generation-on-webvid10m-test.md?metric=LPIPS%20(First%20Frame)>): Lower is better; unit: SCALAR.

- [LPIPS (Frame-to-Frame)](<https://www.sota2.com/research/sota/transition-video-generation-on-webvid10m-test.md?metric=LPIPS%20(Frame-to-Frame)>): Lower is better; unit: SCALAR.

- [CLIPSIM (First Frame)](<https://www.sota2.com/research/sota/transition-video-generation-on-webvid10m-test.md?metric=CLIPSIM%20(First%20Frame)>): Higher is better; unit: SCALAR.

- [CLIPSIM (Frame-to-Frame)](<https://www.sota2.com/research/sota/transition-video-generation-on-webvid10m-test.md?metric=CLIPSIM%20(Frame-to-Frame)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | LPIPS (First Frame) | Result date | Report paper |
| --- | --- | --- | --- |
| StoryDiffusion | 0.3794 | Not recorded | 68fa73161e209131cea5a71f |
| SEINE | 0.4332 | Not recorded | 68fa73161e209131cea5a71f |
| SparseCtrl | 0.4913 | Not recorded | 68fa73161e209131cea5a71f |

### StoryDiffusion

LPIPS (First Frame): 0.3794. Result ID: 6992beb93a6c3148491130f9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73161e209131cea5a71f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73161e209131cea5a71f.md>)

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

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

### SEINE

LPIPS (First Frame): 0.4332. Result ID: 6992beb93a6c3148491130f7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73161e209131cea5a71f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71221e209131cea4f65c.md>)

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

### SparseCtrl

LPIPS (First Frame): 0.4913. Result ID: 6992beb93a6c3148491130f8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73161e209131cea5a71f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea5053f.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.
