TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Audio/1 Image, 2*2 Stitchi/OpenS2V-Eval

1 Image, 2*2 Stitchi on OpenS2V-Eval

Metric: FaceSim (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕FaceSim▼Extra DataPaperDate↕Code
1Wan2.1-VACE-14B0.5509NoVACE: All-in-One Video Creation and Editing2025-03-10Code
2Phantom-Wan-14B0.5148NoPhantom: Subject-consistent video generation via...2025-02-16Code
3Phantom-Wan-1.3B0.4855NoPhantom: Subject-consistent video generation via...2025-02-16Code
4SkyReels-A2-Wan2.1-14B-Preview0.4595NoSkyReels-A2: Compose Anything in Video Diffusion...2025-04-03Code
5Kling 1.60.401NoIdentity-Preserving Text-to-Video Generation by ...2024-11-26Code
6Vidu 2.00.3511NoIdentity-Preserving Text-to-Video Generation by ...2024-11-26Code
7MAGREF-480P0.3083NoMAGREF: Masked Guidance for Any-Reference Video ...2025-05-29Code
8Pika 2.10.308NoIdentity-Preserving Text-to-Video Generation by ...2024-11-26Code
9Wan2.1-VACE-1.3B0.2058NoVACE: All-in-One Video Creation and Editing2025-03-10Code
10Wan2.1-VACE-1.3B-Preview0.1658NoVACE: All-in-One Video Creation and Editing2025-03-10Code