Text To Video Generation On Ucf 101
评估指标
FVD16
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | FVD16 |
|---|---|
| align-your-latents-high-resolution-video | 550.61 |
| preserve-your-own-correlation-a-noise-prior | 355.19 |
| photorealistic-video-generation-with | 258.1 |
| lumiere-a-space-time-diffusion-model-for | 332.49 |
| lavie-high-quality-video-generation-with | 526.30 |
| make-pixels-dance-high-dynamic-video | 242.82 |
| snap-video-scaled-spatiotemporal-transformers | 260.1 |
| magicvideo-efficient-video-generation-with | 699 |
| snap-video-scaled-spatiotemporal-transformers | 200.2 |
| videopoet-a-large-language-model-for-zero | 355 |