Wan2.7-I2V - Generate Video (AI Model · By )

API Documentation

API Reference

Videos

Generate Video

Supported Model Code

Loading models...

Wan2.7-I2V (wan2.7-i2v)

wan2.7-i2v0 models support this endpoint

Wan2.7 image-to-video, performance fully reimagined. Delivers nuanced and organic emotional depth in narrative arcs, along with visceral, bone-crunching impact in action sequences. Enhanced by rhythmic cinematic cuts for unparalleled storytelling power. https://bailian.console.alibabacloud.com/cn-beijing?tab=model#/model-market/detail/wan2.7-i2v?serviceSite=asia-pacific-china

Generate video

https://api.modelstream.ai

POST/v1/video/generations

Authentication

BearerAuth

AuthenticationBearer <token>

All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx

Parameter Location: Header Param

Request Body

application/json

These parameters come from the selected model form_schema. Switching models updates this list and the request example.

first_frame?string

The first frame image (JPEG/PNG/BMP/WEBP, 240-8000px, ≤20MB). Required for image-to-video when no first clip is provided.

Example Value: https://static.modelstream.ai/demo/wan/wan2.7-i2v_first.png

last_frame?string

Optional. The last frame image for first-and-last-frame video generation (same specs as the first frame).

driving_audio?string

Optional. Audio file (wav/mp3, 2-30s, ≤15MB) to drive video generation, e.g., for lip-syncing.

Placeholder: https://...

first_clip?string

Optional. Video file (MP4 or MOV, 2-10s, ≤100MB) for video continuation tasks.

Placeholder: https://...

prompt?string

Describe elements and visual characteristics for the video. Max 5,000 chars.

Example Value: Starting from the static frame, the character slowly draws a deep breath, their chest rising realistically while the wind gently tousles their hair and the fibers of their clothing. In the background, environmental elements like leaves or embers drift through the 3D space, catching the light with realistic motion blur. The camera performs a smooth 'dolly-in' toward the subject's eyes, maintaining perfect facial consistency and skin texture throughout the movement. 4k, cinematic 24fps, masterful temporal stability.Placeholder: e.g., A kitten runs on the grass.

negative_prompt?string

Describe content to exclude from the video. Max 500 chars.

resolution?string

Output resolution tier, 720P or 1080P; directly affects cost. Default 1080P.

Example Value: 1080P

Enum/Options:

720P1080P

duration?number

Video duration, range 2-15 seconds, billed per second. Default 5s.

Example Value: 5Value Range: 2 ≤ value ≤ 15step: 1

prompt_extend?boolean

When on, an LLM intelligently rewrites your prompt to improve results. Enabled by default.

Example Value: true

watermark?boolean

Add a fixed 'AI生成' watermark to the bottom-right of the video. Disabled by default.

Example Value: false

seed?number

Random seed, range [0, 2147483647]. A fixed seed improves reproducibility.

Response Parameters

application/json

200apiDocs.responses.successCreateVideoGenTask

task_id?string

Parameter description for Task Id

status?string

Parameter description for Status

400apiDocs.responses.badRequestParams

error?object

Parameter description for Error

message?string

Error Message

type?string

Error Type

param?string

Related Parameters

code?string

Error Code

curl -X POST "https://api.modelstream.ai/v1/video/generations" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan2.7-i2v",
  "prompt": "Starting from the static frame, the character slowly draws a deep breath, their chest rising realistically while the wind gently tousles their hair and the fibers of their clothing. In the background, environmental elements like leaves or embers drift through the 3D space, catching the light with realistic motion blur. The camera performs a smooth 'dolly-in' toward the subject's eyes, maintaining perfect facial consistency and skin texture throughout the movement. 4k, cinematic 24fps, masterful temporal stability.",
  "size": "720P",
  "duration": 5,
  "metadata": {
    "input": {
      "media": [
        {
          "type": "first_frame",
          "url": "https://static.modelstream.ai/demo/wan/wan2.7-i2v_first.png"
        }
      ]
    },
    "parameters": {
      "prompt_extend": true,
      "watermark": true
    }
  }
}'

{
  "task_id": "abcd1234efgh",
  "status": "queued"
}

API Documentation

API Reference

Videos

Generate Video

Supported Model Code

Loading models...

Wan2.7-I2V (wan2.7-i2v)

wan2.7-i2v0 models support this endpoint

Generate video

https://api.modelstream.ai

POST/v1/video/generations

Authentication

BearerAuth

AuthenticationBearer <token>

All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx

Parameter Location: Header Param

Request Body

application/json

These parameters come from the selected model form_schema. Switching models updates this list and the request example.

first_frame?string

The first frame image (JPEG/PNG/BMP/WEBP, 240-8000px, ≤20MB). Required for image-to-video when no first clip is provided.

Example Value: https://static.modelstream.ai/demo/wan/wan2.7-i2v_first.png

last_frame?string

Optional. The last frame image for first-and-last-frame video generation (same specs as the first frame).

driving_audio?string

Optional. Audio file (wav/mp3, 2-30s, ≤15MB) to drive video generation, e.g., for lip-syncing.

Placeholder: https://...

first_clip?string

Optional. Video file (MP4 or MOV, 2-10s, ≤100MB) for video continuation tasks.

Placeholder: https://...

prompt?string

Describe elements and visual characteristics for the video. Max 5,000 chars.

negative_prompt?string

Describe content to exclude from the video. Max 500 chars.

resolution?string

Output resolution tier, 720P or 1080P; directly affects cost. Default 1080P.

Example Value: 1080P

Enum/Options:

720P1080P

duration?number

Video duration, range 2-15 seconds, billed per second. Default 5s.

Example Value: 5Value Range: 2 ≤ value ≤ 15step: 1

prompt_extend?boolean

When on, an LLM intelligently rewrites your prompt to improve results. Enabled by default.

Example Value: true

watermark?boolean

Add a fixed 'AI生成' watermark to the bottom-right of the video. Disabled by default.

Example Value: false

seed?number

Random seed, range [0, 2147483647]. A fixed seed improves reproducibility.

Response Parameters

application/json

200apiDocs.responses.successCreateVideoGenTask

task_id?string

Parameter description for Task Id

status?string

Parameter description for Status

400apiDocs.responses.badRequestParams

error?object

Parameter description for Error

message?string

Error Message

type?string

Error Type

param?string

Related Parameters

code?string

Error Code

curl -X POST "https://api.modelstream.ai/v1/video/generations" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan2.7-i2v",
  "prompt": "Starting from the static frame, the character slowly draws a deep breath, their chest rising realistically while the wind gently tousles their hair and the fibers of their clothing. In the background, environmental elements like leaves or embers drift through the 3D space, catching the light with realistic motion blur. The camera performs a smooth 'dolly-in' toward the subject's eyes, maintaining perfect facial consistency and skin texture throughout the movement. 4k, cinematic 24fps, masterful temporal stability.",
  "size": "720P",
  "duration": 5,
  "metadata": {
    "input": {
      "media": [
        {
          "type": "first_frame",
          "url": "https://static.modelstream.ai/demo/wan/wan2.7-i2v_first.png"
        }
      ]
    },
    "parameters": {
      "prompt_extend": true,
      "watermark": true
    }
  }
}'

{
  "task_id": "abcd1234efgh",
  "status": "queued"
}

Wan2.7-I2V - Generate Video (AI Model · By ) | ModelStream