wan2.7

Create Wan2.7 video tasks through POST /v1/video/generations. Choose a workflow below; each workflow uses the same endpoint with a different model ID and input media structure.

Text to video
Image to video
Reference to video

Create task

POST /v1/video/generations

cURL

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
    }
  }'

200

{
  "id": "asyntask_example123",
  "task_id": "asyntask_example123",
  "object": "video",
  "model": "wan2.7-t2v",
  "status": "queued",
  "progress": 0,
  "created_at": 1784520000
}

Request headers

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

default:"application/json"

required

Request body format.

Request parameters

string

required

Must be wan2.7-t2v.

string

required

Video description in Chinese or English. Maximum 5,000 non-Chinese or 2,500 Chinese characters.

string

Content to exclude from the video. Maximum 500 characters.

string

Public WAV or MP3 URL. The audio must be 2-30 seconds and no larger than 15 MB.

string

default:"1080P"

Output resolution: 720P or 1080P.

string

default:"16:9"

Output aspect ratio: 16:9, 9:16, 1:1, 4:3, or 3:4.

integer

default:5

Video duration from 2 to 15 seconds.

boolean

default:true

Whether to rewrite and enrich the prompt. For specific content requests, select the Special-Ns resource group and set this parameter to false.

boolean

default:false

Whether to add an AI Generated watermark.

integer

Random seed in [0, 2147483647].

Create task

POST /v1/video/generations

cURL

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
    }
  }'

200

{
  "id": "asyntask_example123",
  "task_id": "asyntask_example123",
  "object": "video",
  "model": "wan2.7-i2v",
  "status": "queued",
  "progress": 0,
  "created_at": 1784520000
}

Request headers

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

default:"application/json"

required

Request body format.

Request parameters

string

required

Must be wan2.7-i2v.

string

Motion and scene description. Maximum 5,000 non-Chinese or 2,500 Chinese characters.

string

Content to exclude from the video. Maximum 500 characters.

object[]

required

One to three media objects. Use only one object for each media type.

string

required

Media type: first_frame, last_frame, driving_audio, or first_clip.

string

required

Public media URL. first_frame and last_frame also accept Base64 data URLs.

string

default:"1080P"

Output resolution: 720P or 1080P.

integer

default:5

Final output duration from 2 to 15 seconds. For continuation, this includes the input clip.

boolean

default:true

Whether to rewrite and enrich the prompt. For specific content requests, select the Special-Ns resource group and set this parameter to false.

boolean

default:false

Whether to add an AI Generated watermark.

integer

Random seed in [0, 2147483647].

Create task

POST /v1/video/generations

cURL

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
    }
  }'

200

{
  "id": "asyntask_example123",
  "task_id": "asyntask_example123",
  "object": "video",
  "model": "wan2.7-r2v",
  "status": "queued",
  "progress": 0,
  "created_at": 1784520000
}

Request headers

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

default:"application/json"

required

Request body format.

Request parameters

string

required

Must be wan2.7-r2v.

string

required

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.

string

Content to exclude from the video. Maximum 500 characters.

object[]

required

One to six media objects. Reference images and videos together must not exceed five.

string

required

Media type: reference_image, reference_video, or first_frame.

string

required

Reference media URL. Images also accept Base64 data URLs.

string

Optional public WAV or MP3 voice-reference URL for a reference image or video.

string

default:"1080P"

Output resolution: 720P or 1080P.

string

default:"16:9"

Output aspect ratio: 16:9, 9:16, 1:1, 4:3, or 3:4. Ignored when a first_frame is provided.

integer

default:5

Video duration from 2 to 15 seconds. When a reference video is present, the maximum is 10 seconds.

boolean

default:true

Whether to rewrite and enrich the prompt. For specific content requests, select the Special-Ns resource group and set this parameter to false.

boolean

default:false

Whether to add an AI Generated watermark.

integer

Random seed in [0, 2147483647].

Response

string

Created task ID.

string

Created task ID; use it for task queries.

string

Response object type, returned as video.

string

Model used for task creation.

string

Initial task status, normally queued.

integer

Initial task progress, normally 0.

integer

Task creation time as a Unix timestamp.

Error responses

400 Bad Request - Invalid input or unsupported parameter or media combination.
401 Unauthorized - API key is missing or invalid.
429 Rate limit exceeded - Request rate exceeded the applicable limit.

Overview

Native Compatible Endpoints

Model APIs

Create task

Request headers

Request parameters

Create task

Request headers

Request parameters

Create task

Request headers

Request parameters

Response

Error responses

​Create task

​Request headers

​Request parameters

​Create task

​Request headers

​Request parameters

​Create task

​Request headers

​Request parameters

​Response

​Error responses

Create task

Request headers

Request parameters

Create task

Request headers

Request parameters

Create task

Request headers

Request parameters

Response

Error responses