| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Editing | VACE-Benchmark (test) | SC Score94.56 | 8 | |
| Pose-to-Video Generation | VACE-Benchmark | Aesthetic Quality66.71 | 8 | |
| Depth-to-Video Generation | VACE-Benchmark | Aesthetic Quality63.3 | 8 | |
| Video Outpainting | VACE-Benchmark | Aesthetic Quality58.86 | 7 | |
| Video Inpainting | VACE | AQ59.7 | 3 | |
| Video Outpainting | VACE-Benchmark | PSNR19.62 | 3 | |
| Video Inpainting | VACE-Benchmark Higher-resolution 25 x 720P | PSNR13.03 | 3 | |
| Text-to-Video Generation | VACE-Benchmark | Aesthetic Quality64.37 | 3 | |
| Reference-to-Video Generation | VACE Benchmark | Aesthetic Quality65.99 | 3 | |
| Video Extension | VACE-Benchmark | Aesthetic Quality61.34 | 3 | |
| Grey-to-Video Generation | VACE Benchmark | Aesthetic Quality62.87 | 3 | |
| Scribble-to-Video Generation | VACE-Benchmark | Aesthetic Quality59.44 | 3 | |
| Flow-to-Video Generation | VACE-Benchmark | Aesthetic Quality60.44 | 3 | |
| Video Inpainting | VACE-Benchmark | PSNR15.28 | 2 |