Hailuo 2.3 T2V
[Core Function] Hailuo 2.3 T2V is a flagship text-to-video generation model optimized for human performance and stylization. [Strengths] It excels at capturing intricate human motion, nuanced facial micro-expressions, prompt adherence, and applying highly stylized aesthetics (e.g., anime, ink wash, game CG) to video. [Best For] Highly recommended for: character-driven storytelling, close-up emotional shots, stylized artistic videos, and dialogue scenes. [Limitations] Do NOT use this model if you need native 1080p resolution for 10 full seconds (1080p is capped at 6 seconds; generating 10s forces 768p resolution). [Routing] Use this model by default for text-to-video requests involving humans, faces, or specific art styles. If the user requires strict physical realism/world dynamics or native 1080p for 10 seconds, route to Hailuo 02 T2V instead.
Authorizations
API Key authentication. Format: Bearer YOUR_API_KEY.
Body
Video content description, supports Chinese and English, supports camera control instructions (e.g., 'close-up shot', 'tracking shot', 'pan left/right', 'zoom in/out', 'tilt up/down')
1 - 2000"A cat playing in the garden under sunny day"
Enable automatic prompt optimization to improve video quality
true
Fast pretreatment mode (only effective when prompt_optimizer=true). Speeds up processing with slight quality trade-off
false
Video duration in seconds. Note: 10 seconds only supports 768P resolution
6, 10 6
Video resolution. Note: 10 seconds duration only supports 768P
768P, 1080P "768P"