Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

StoryGen

Benchmarks

Task NameDataset NameSOTA ResultTrend
Regular-Length Story VisualizationStoryGen Regular-Length Story Visualization (Human Evaluation)
Alignment4.11
8
Long Story VisualizationStoryGen Human Evaluation Set Long Story Visualization
Alignment4.35
7
Subject-Consistent Image GenerationStoryGen Human Evaluation Set Subject-Consistent Image Generation
Alignment4.2
6
Audio StorytellingStoryGen-Eval (test)
KAD10.82
4
Speaker DiarizationStoryGen Eval
tcpWER5.5
3
Audio CaptioningStoryGen Eval
multiFLAM88.1
2
Showing 6 of 6 rows