List your company

Video Generation on Kinetics-600

4.3FVDDFoT
-10.898891.6931194.285296.8769May 18, 2025Jun 12, 2025Jul 7, 2025Aug 1, 2025Aug 26, 2025Sep 20, 2025Oct 15, 2025

Evaluation results

MethodLinks
DFoTType=Diffusion, Resolution=128 x 1282025.104.3
MAGVIT-v2Type=Autoregressive, Resolution=64 x 642025.104.3
Rolling DiffusionType=Diffusion, Resolution=64 x 642025.105.2
CanvasMARType=Autoregressive, Resolution=64 x 64, NAR=122025.106.2
CanvasMARType=Autoregressive, Resolution=64 x 64, NAR=102025.106.3
CanvasMARType=Autoregressive, Resolution=64 x 64, NAR=112025.106.3
MAGVITType=Autoregressive, Resolution=64 x 642025.109.9
MAGIType=Autoregressive, Resolution=64 x 642025.1011.5
VDMType=Diffusion, Resolution=64 x 642025.1016.2
RaMViDType=Diffusion, Resolution=64 x 642025.1016.5
TransframerType=Autoregressive, Resolution=64 x 642025.1025.4
TrIVD-GAN-FPType=GAN, Resolution=64 x 642025.1025.74
PhenakiType=Autoregressive, Resolution=128 x 1282025.1036.4
CCVSType=Autoregressive, Resolution=64 x 642025.1055
Video VQ-VAEType=Autoregressive, Resolution=64 x 642025.1064.3
DVD-GAN-FPType=GAN, Resolution=64 x 642025.1069.1
CogVideoType=Autoregressive, Resolution=64 x 642025.10109.2
Video TransformerType=Autoregressive, Resolution=64 x 642025.10170
Video-GPTParameters=3.8B, Architecture=Vanilla Transformer2025.05315.4
SeineParameters=0.9B, Architecture=U-Net, Text Encoder=CLIP-VIT-L [59]2025.05332.8
LVMParameters=7B, Architecture=Vanilla Transformer2025.05356.48
Open-Sora-Plan v1.3.0Parameters=2B, Architecture=DiT, Text Encoder=mT5-XXL [86]2025.05384.27