# Video Motion Transfer on Video Motion Transfer Dataset 50 videos 1.0 (test)

Source: [Video Motion Transfer on Video Motion Transfer Dataset 50 videos 1.0 (test)](<https://www.sota2.com/research/sota/video-motion-transfer-on-video-motion-transfer-dataset-50-videos-1-0-test>)

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

Data updated: 2026-03-09T08:43:25.087Z

Evaluation of models performing Video Motion Transfer on the test split of the Video Motion Transfer Dataset (v1.0, 50 videos), assessed using Text Similarity, Motion Fidelity, and Temporal 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 | Video Motion Transfer |
| Dataset (including any stated split) | Video Motion Transfer Dataset 50 videos 1.0 (test) |
| Metric | Text Similarity |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Text Similarity](<https://www.sota2.com/research/sota/video-motion-transfer-on-video-motion-transfer-dataset-50-videos-1-0-test.md?metric=Text%20Similarity>): Higher is better; unit: PERCENT.

- [Motion Fidelity](<https://www.sota2.com/research/sota/video-motion-transfer-on-video-motion-transfer-dataset-50-videos-1-0-test.md?metric=Motion%20Fidelity>): Higher is better; unit: PERCENT.

- [Temporal Consistency](<https://www.sota2.com/research/sota/video-motion-transfer-on-video-motion-transfer-dataset-50-videos-1-0-test.md?metric=Temporal%20Consistency>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Text Similarity | Result date | Report paper |
| --- | --- | --- | --- |
| DiTFlow | 35 | Not recorded | 69ae53e72d603e6de3e4297b |
| FlowMotion | 34.7 | Not recorded | 69ae53e72d603e6de3e4297b |
| DeT | 34 | Not recorded | 69ae53e72d603e6de3e4297b |
| MOFT | 33.8 | Not recorded | 69ae53e72d603e6de3e4297b |
| MotionDirector | 33.5 | Not recorded | 69ae53e72d603e6de3e4297b |
| MotionClone | 33.2 | Not recorded | 69ae53e72d603e6de3e4297b |
| MotionInversion | 32.8 | Not recorded | 69ae53e72d603e6de3e4297b |
| LoRA Tuning | 32.7 | Not recorded | 69ae53e72d603e6de3e4297b |
| SMM | 32.2 | Not recorded | 69ae53e72d603e6de3e4297b |

### DiTFlow

Text Similarity: 35. Result ID: 69ae88166dbb7075b956b80c.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e72d603e6de3e4297b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a51e209131cea74956.md>)

[Implementation](<https://www.sota2.com/ditflow.github.io>)

Recorded evaluation configuration: {"Backbone":"CogVideoX","Param":"2B","Training Protocol":"Training-free","Inference Time (s)":"349","GPU Memory (G)":"63.5"}. This record does not assert independent reproduction.

### FlowMotion

Text Similarity: 34.7. Result ID: 69ae88166dbb7075b956b80d.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e72d603e6de3e4297b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ae53e72d603e6de3e4297b.md>)

Recorded evaluation configuration: {"Backbone":"Wan2.1","Param":"1.3B","Training Protocol":"Training-free","Inference Time (s)":"213","GPU Memory (G)":"19.3"}. This record does not assert independent reproduction.

### DeT

Text Similarity: 34. Result ID: 69ae88166dbb7075b956b808.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e72d603e6de3e4297b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a611e209131cea82b84.md>)

Recorded evaluation configuration: {"Backbone":"CogVideoX","Param":"2B","Training Protocol":"Training-based","Training Time (s)":"2760","Inference Time (s)":"133","GPU Memory (G)":"20.0"}. This record does not assert independent reproduction.

### MOFT

Text Similarity: 33.8. Result ID: 69ae88166dbb7075b956b80a.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e72d603e6de3e4297b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75b61e209131cea697db.md>)

Recorded evaluation configuration: {"Backbone":"AnimateDiff","Param":"1.3B","Training Protocol":"Training-free","Inference Time (s)":"576","GPU Memory (G)":"75.0"}. This record does not assert independent reproduction.

### MotionDirector

Text Similarity: 33.5. Result ID: 69ae88166dbb7075b956b806.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e72d603e6de3e4297b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d31e209131cea4d6fc.md>)

Recorded evaluation configuration: {"Backbone":"ZeroScope","Param":"0.7B","Training Protocol":"Training-based","Training Time (s)":"1662","Inference Time (s)":"140","GPU Memory (G)":"28.0"}. This record does not assert independent reproduction.

### MotionClone

Text Similarity: 33.2. Result ID: 69ae88166dbb7075b956b809.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e72d603e6de3e4297b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa754d1e209131cea66f56.md>)

Recorded evaluation configuration: {"Backbone":"AnimateDiff","Param":"1.3B","Training Protocol":"Training-free","Inference Time (s)":"804","GPU Memory (G)":"51.5"}. This record does not assert independent reproduction.

### MotionInversion

Text Similarity: 32.8. Result ID: 69ae88166dbb7075b956b807.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e72d603e6de3e4297b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75401e209131cea66d33.md>)

Recorded evaluation configuration: {"Backbone":"ZeroScope","Param":"0.7B","Training Protocol":"Training-based","Training Time (s)":"1170","Inference Time (s)":"115","GPU Memory (G)":"24.0"}. This record does not assert independent reproduction.

### LoRA Tuning

Text Similarity: 32.7. Result ID: 69ae88166dbb7075b956b805.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e72d603e6de3e4297b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"Backbone":"Wan2.1","Param":"1.3B","Training Protocol":"Training-based","Training Time (s)":"8100","Inference Time (s)":"135","GPU Memory (G)":"25.0"}. This record does not assert independent reproduction.

### SMM

Text Similarity: 32.2. Result ID: 69ae88166dbb7075b956b80b.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53e72d603e6de3e4297b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71561e209131cea509b5.md>)

[Implementation](<https://diffusion-motion-transfer.github.io/>)

Recorded evaluation configuration: {"Backbone":"ZeroScope","Param":"0.7B","Training Protocol":"Training-free","Inference Time (s)":"1839","GPU Memory (G)":"89.4"}. This record does not assert independent reproduction.

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