# Video Editing on Custom facial video editing dataset

Source: [Video Editing on Custom facial video editing dataset](<https://www.sota2.com/research/sota/video-editing-on-custom-facial-video-editing-dataset>)

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

Data updated: 2026-04-16T08:13:26.591Z

Evaluation of general Video Editing performance on the Custom facial video editing dataset, measured by time cost per frame.

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 | Video Editing |
| Dataset (including any stated split) | Custom facial video editing dataset |
| Metric | Time Cost (s/frame) |
| Unit | TIME |
| Direction | Lower is better |
| Results loaded | 5 of 5 |
| 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

- [Time Cost (s/frame)](<https://www.sota2.com/research/sota/video-editing-on-custom-facial-video-editing-dataset.md?metric=Time%20Cost%20(s%2Fframe)>): Lower is better; unit: TIME.

## Recorded results

| Method | Time Cost (s/frame) | Result date | Report paper |
| --- | --- | --- | --- |
| InstructPix2Pix | 0.9357 | Not recorded | 69e06d037d0172140ec7ca0e |
| DiffMagicFace | 2.3572 | Not recorded | 69e06d037d0172140ec7ca0e |
| Rendering Software | 4.6326 | Not recorded | 69e06d037d0172140ec7ca0e |
| DiffEdit | 15.9757 | Not recorded | 69e06d037d0172140ec7ca0e |
| Diffusion Video Autoencoder | 103.6842 | Not recorded | 69e06d037d0172140ec7ca0e |

### InstructPix2Pix

Time Cost (s/frame): 0.9357. Result ID: 69e099da47f34ce924c9bd90.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d037d0172140ec7ca0e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e641e209131cea3fa43.md>)

[Implementation](<https://www.sota2.com/timothybrooks.com/instruct-pix2pix>)

Recorded evaluation configuration: {"GPU":"1 RTX 3090 GPU","Diffusion inference steps":"30"}. This record does not assert independent reproduction.

### DiffMagicFace

Time Cost (s/frame): 2.3572. Result ID: 69e099da47f34ce924c9bd93.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d037d0172140ec7ca0e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e06d037d0172140ec7ca0e.md>)

Recorded evaluation configuration: {"GPU":"1 RTX 3090 GPU","Diffusion inference steps":"30"}. This record does not assert independent reproduction.

### Rendering Software

Time Cost (s/frame): 4.6326. Result ID: 69e099da47f34ce924c9bd8f.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d037d0172140ec7ca0e.md>)

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

### DiffEdit

Time Cost (s/frame): 15.9757. Result ID: 69e099da47f34ce924c9bd91.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d037d0172140ec7ca0e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bc66.md>)

Recorded evaluation configuration: {"GPU":"1 RTX 3090 GPU","Diffusion inference steps":"30"}. This record does not assert independent reproduction.

### Diffusion Video Autoencoder

Time Cost (s/frame): 103.6842. Result ID: 69e099da47f34ce924c9bd92.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d037d0172140ec7ca0e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42ced.md>)

Recorded evaluation configuration: {"GPU":"1 RTX 3090 GPU","Diffusion inference steps":"30"}. This record does not assert independent reproduction.

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