Video on Kinetics-600 12 frames, 64x64
Metric: Cond (higher is better)
Metric: Cond (higher is better)
| # | Model↕ | Cond▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | SiD2 | 5 | No | Simpler Diffusion (SiD2): 1.5 FID on ImageNet512... | 2024-10-25 | - |
| 2 | LARP | 5 | No | LARP: Tokenizing Videos with a Learned Autoregre... | 2024-10-28 | Code |
| 3 | MAGVIT (-L-FP) | 5 | No | MAGVIT: Masked Generative Video Transformer | 2022-12-10 | Code |
| 4 | RaMViD | 5 | No | Diffusion Models for Video Prediction and Infill... | 2022-06-15 | Code |
| 5 | MAGVIT (-B-FP) | 5 | No | MAGVIT: Masked Generative Video Transformer | 2022-12-10 | Code |
| 6 | TriVD-GAN-FP | 5 | No | Transformation-based Adversarial Video Predictio... | 2020-03-09 | - |
| 7 | CCVS | 5 | No | CCVS: Context-aware Controllable Video Synthesis | 2021-07-16 | Code |
| 8 | DVD-GAN-FP | 5 | No | Adversarial Video Generation on Complex Datasets | 2019-07-15 | Code |
| 9 | Video Transformer | 5 | No | Scaling Autoregressive Video Models | 2019-06-06 | Code |
| 10 | LVT | 5 | No | Latent Video Transformer | 2020-06-18 | Code |
| 11 | Video VQ-VAE FVD | 4 | No | Predicting Video with VQVAE | 2021-03-02 | Code |