Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Long Descriptive Prompts

Benchmarks

Task NameDataset NameSOTA ResultTrend
Video Extrapolation5 long descriptive prompts 4x / 333f train-free extrapolation Wan 2.1 1.3B
VQEval Score62.4
5
Video Extrapolation5 long descriptive prompts (3x / 249f) Wan 2.1 1.3B (train-free extrapolation)
VQeval62.5
5
Video Extrapolation5 long descriptive prompts 2x / 165f train-free extrapolation Wan 2.1 1.3B
VQeval64.1
5
Showing 3 of 3 rows