01
Generates video from text prompts using the Wan 2.5 text-to-video model
02
Supports 480p resolution on Coinis (720p and 1080p tiers available upstream)
03
Three aspect ratios: 16:9 landscape, 9:16 portrait, and 1:1 square. Default is 16:9
04
Video duration of 5 seconds or 10 seconds. Default is 5 seconds
05
Text prompts accepted in English or Chinese, up to 800 characters
06
Negative prompt parameter steers output away from unwanted content, up to 500 characters
07
Optional background audio input (WAV or MP3, 3 to 30 seconds, up to 15 MB) mixed directly into the generated clip. Audio longer than the clip is trimmed. Audio shorter than the clip leaves the remainder silent
08
LLM-based prompt expansion enabled by default. The enriched prompt is returned in the output as `actual_prompt`
09
Seed parameter for reproducible video generation
10
Output delivered as an MP4 file via URL, with metadata including width, height, FPS, duration, and frame count
11
Commercial use permitted on the platform