## Create task
`POST /v1/video/generations`
```bash cURL theme={null}
curl --request POST \
--url https://www.anyfast.ai/v1/video/generations \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model": "wan2.7-t2v",
"input": {
"prompt": "A paper boat sails through a neon-lit rainy city, cinematic tracking shot.",
"negative_prompt": "blurry, distorted, low quality",
"audio_url": "https://example.com/music.mp3"
},
"parameters": {
"resolution": "720P",
"ratio": "16:9",
"duration": 5,
"prompt_extend": true,
"watermark": false,
"seed": 42
}
}'
```
```json 200 theme={null}
{
"id": "asyntask_example123",
"task_id": "asyntask_example123",
"object": "video",
"model": "wan2.7-t2v",
"status": "queued",
"progress": 0,
"created_at": 1784520000
}
```
## Request headers
Bearer authentication in the form `Bearer YOUR_API_KEY`.
Request body format.
## Request parameters
Must be `wan2.7-t2v`.
Video description in Chinese or English. Maximum 5,000 non-Chinese or 2,500 Chinese characters.
Content to exclude from the video. Maximum 500 characters.
Public WAV or MP3 URL. The audio must be 2-30 seconds and no larger than 15 MB.
Output resolution: `720P` or `1080P`.
Output aspect ratio: `16:9`, `9:16`, `1:1`, `4:3`, or `3:4`.
Video duration from 2 to 15 seconds.
Whether to rewrite and enrich the prompt. For specific content requests, select the `Special-Ns` resource group and set this parameter to `false`.
Whether to add an AI Generated watermark.
Random seed in `[0, 2147483647]`.
## Create task
`POST /v1/video/generations`
```bash cURL theme={null}
curl --request POST \
--url https://www.anyfast.ai/v1/video/generations \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model": "wan2.7-i2v",
"input": {
"prompt": "The camera moves closer as the lanterns begin to glow.",
"negative_prompt": "blurry, distorted, low quality",
"media": [
{
"type": "first_frame",
"url": "https://example.com/first-frame.png"
},
{
"type": "driving_audio",
"url": "https://example.com/driving-audio.mp3"
}
]
},
"parameters": {
"resolution": "720P",
"duration": 5,
"prompt_extend": true,
"watermark": false,
"seed": 42
}
}'
```
```json 200 theme={null}
{
"id": "asyntask_example123",
"task_id": "asyntask_example123",
"object": "video",
"model": "wan2.7-i2v",
"status": "queued",
"progress": 0,
"created_at": 1784520000
}
```
## Request headers
Bearer authentication in the form `Bearer YOUR_API_KEY`.
Request body format.
## Request parameters
Must be `wan2.7-i2v`.
Motion and scene description. Maximum 5,000 non-Chinese or 2,500 Chinese characters.
Content to exclude from the video. Maximum 500 characters.
One to three media objects. Use only one object for each media type.
Media type: `first_frame`, `last_frame`, `driving_audio`, or `first_clip`.
Public media URL. `first_frame` and `last_frame` also accept Base64 data URLs.
Output resolution: `720P` or `1080P`.
Final output duration from 2 to 15 seconds. For continuation, this includes the input clip.
Whether to rewrite and enrich the prompt. For specific content requests, select the `Special-Ns` resource group and set this parameter to `false`.
Whether to add an AI Generated watermark.
Random seed in `[0, 2147483647]`.
## Create task
`POST /v1/video/generations`
```bash cURL theme={null}
curl --request POST \
--url https://www.anyfast.ai/v1/video/generations \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model": "wan2.7-r2v",
"input": {
"prompt": "The character from Image 1 walks through the street from Video 1.",
"negative_prompt": "blurry, distorted, low quality",
"media": [
{
"type": "reference_image",
"url": "https://example.com/character.png",
"reference_voice": "https://example.com/voice.mp3"
},
{
"type": "reference_video",
"url": "https://example.com/street.mp4"
}
]
},
"parameters": {
"resolution": "720P",
"ratio": "16:9",
"duration": 5,
"prompt_extend": true,
"watermark": false,
"seed": 42
}
}'
```
```json 200 theme={null}
{
"id": "asyntask_example123",
"task_id": "asyntask_example123",
"object": "video",
"model": "wan2.7-r2v",
"status": "queued",
"progress": 0,
"created_at": 1784520000
}
```
## Request headers
Bearer authentication in the form `Bearer YOUR_API_KEY`.
Request body format.
## Request parameters
Must be `wan2.7-r2v`.
Describe the scene and refer to assets as `Image 1`, `Image 2`, `Video 1`, and `Video 2`. Maximum 5,000 non-Chinese or 2,500 Chinese characters.
Content to exclude from the video. Maximum 500 characters.
One to six media objects. Reference images and videos together must not exceed five.
Media type: `reference_image`, `reference_video`, or `first_frame`.
Reference media URL. Images also accept Base64 data URLs.
Optional public WAV or MP3 voice-reference URL for a reference image or video.
Output resolution: `720P` or `1080P`.
Output aspect ratio: `16:9`, `9:16`, `1:1`, `4:3`, or `3:4`. Ignored when a `first_frame` is provided.
Video duration from 2 to 15 seconds. When a reference video is present, the maximum is 10 seconds.
Whether to rewrite and enrich the prompt. For specific content requests, select the `Special-Ns` resource group and set this parameter to `false`.
Whether to add an AI Generated watermark.
Random seed in `[0, 2147483647]`.
## Response