HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Text To Video Generation On Ucf 101

Metrics

FVD16

Results

Performance results of various models on this benchmark

Model Name
FVD16
Paper TitleRepository
Video LDM (Zero-shot, 320x512)550.61Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
PYoCo (Zero-shot, 64x64)355.19Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models-
W.A.L.T 3B258.1Photorealistic Video Generation with Diffusion Models-
Lumiere (Zero-shot, 1024x1024)332.49Lumiere: A Space-Time Diffusion Model for Video Generation
LAVIE (Zero-shot, 320x512)526.30LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models
PixelDance (Zero-shot, 256x256)242.82Make Pixels Dance: High-Dynamic Video Generation-
Snap Video (Zero-shot, 288×288)260.1Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis-
MagicVideo (Zero-shot, 256x256)699MagicVideo: Efficient Video Generation With Latent Diffusion Models-
Snap Video (Zero-shot, 512x288)200.2Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis-
VideoPoet355VideoPoet: A Large Language Model for Zero-Shot Video Generation
0 of 10 row(s) selected.