Model
Modes
| Mode | Description |
|---|---|
t2v | Generate video from a text prompt |
i2v | Generate video from a first frame image |
r2v | Generate video from reference images. Use characterN in prompt to reference them |
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
mode | string | No | "t2v" | "t2v", "i2v", or "r2v" |
prompt | string | No | "" | Text prompt describing the desired video. Supports any language. Max 5,000 non-Chinese characters or 2,500 Chinese characters; excess is truncated |
first_frame_url | string | No | null | URL of the first frame image for I2V mode |
reference_image_urls | string[] | No | null | Reference image URLs for R2V mode (1-9). Use characterN in prompt to reference them |
ratio | string | No | null | Aspect ratio (T2V/R2V only): "16:9", "9:16", "1:1", "4:3", "3:4" |
resolution | string | No | "1080P" | "720P" or "1080P" |
duration | integer | No | 5 | Output duration in seconds (3-15) |
watermark | boolean | No | false | Add watermark to the output |
seed | integer | No | null | Random seed for reproducible generation (0-2147483647) |
