Controllable Text-to-Video Generation on Targeting Evaluation Dataset benchmark leaderboard · SOTA2 Research

Controllable Text-to-Video Generation on Targeting Evaluation Dataset

0.878Contact ScoreTarget-Aware Video Diffusion Model

Evaluation Results

Method
Target-Aware Video Diffusion Model2025.03	0.878	0.77	0.693	0.783
CogVideoX2025.03	0.638	0.504	0.393	0.54
CogVideoX2025.03	0.56	0.446	0.377	0.474
Attention Modulation2025.03	0.546	0.399	0.34	0.455