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/Natural Language Processing/Text-to-Video Generation/UCF-101

Text-to-Video Generation on UCF-101

Metric: FVD16 (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕FVD16▼Extra DataPaperDate↕Code
1MagicVideo (Zero-shot, 256x256)699NoMagicVideo: Efficient Video Generation With Late...2022-11-20-
2Video LDM (Zero-shot, 320x512)550.61NoAlign your Latents: High-Resolution Video Synthe...2023-04-18Code
3LAVIE (Zero-shot, 320x512)526.3NoLAVIE: High-Quality Video Generation with Cascad...2023-09-26Code
4PYoCo (Zero-shot, 64x64)355.19NoPreserve Your Own Correlation: A Noise Prior for...2023-05-17-
5VideoPoet355NoVideoPoet: A Large Language Model for Zero-Shot ...2023-12-21-
6Lumiere (Zero-shot, 1024x1024)332.49NoLumiere: A Space-Time Diffusion Model for Video ...2024-01-23Code
7Snap Video (Zero-shot, 288×288)260.1NoSnap Video: Scaled Spatiotemporal Transformers f...2024-02-22-
8W.A.L.T 3B258.1NoPhotorealistic Video Generation with Diffusion M...2023-12-11-
9PixelDance (Zero-shot, 256x256)242.82NoMake Pixels Dance: High-Dynamic Video Generation2023-11-18-
10Snap Video (Zero-shot, 512x288)200.2NoSnap Video: Scaled Spatiotemporal Transformers f...2024-02-22-