An improved text-to-video model with significantly better prompt adherence and visual quality over V1.5, supporting dual standard/professional generation modes.
API Key authentication. Format: Bearer YOUR_API_KEY.
Video description text, supports Chinese and English
1 - 2500"Ocean waves crashing on rocky shore at sunrise"
Negative prompt describing undesired elements
1 - 2500"static, boring"
Prompt relevance (0.0-1.0). Only supported by V1 and V1.6.
0 <= x <= 10.6
Generation mode: std (standard) or pro (professional)
std, pro "pro"
Video aspect ratio
16:9, 9:16, 1:1 "9:16"
Video duration in seconds
5, 10 10