ViStoryBench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Cinematic Story Generation | ViStoryBench | CSD (Cross)0.616 | 24 | |
| Visual Storytelling | ViStoryBench Lite 2025 | CSD (Cross)0.735 | 21 | |
| Visual Storytelling Consistency | ViStoryBench | CSD (Self)74.9 | 13 | |
| Story-driven Video Generation | ViStoryBench | Scene Score3.5334 | 6 | |
| Reference-to-Shot Storyboard Synthesis | VistoryBench | CIDS (Character) Self65.6 | 6 | |
| Video Storytelling | ViStoryBench Lite | Style Consistency (Cross)0.499 | 5 | |
| Storyboard Generation | ViStoryBench | Background Consistency (Consecutive)4.83 | 5 | |
| Story-image generation | ViStoryBench Lite | CSD (Cross)0.49 | 5 | |
| Storyboard Generation | ViStoryBench Lite | CSD (Cross)0.49 | 5 | |
| Story Generation | ViStoryBench 2025 | CSD (Style) Cross57.8 | 5 | |
| Manga Generation | ViStoryBench | Object Count100 | 4 | |
| Story Visualization | ViStoryBench Lite | CSD (Self)70 | 4 |
Showing 12 of 12 rows