Wan2.7-T2V - Generate Video (AI Model · By )

API Documentation

API Reference

Videos

Generate Video

Supported Model Code

Loading models...

Wan2.7-T2V (wan2.7-t2v)

wan2.7-t2v0 models support this endpoint

Wan2.7 text-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. doc link: https://bailian.console.alibabacloud.com/cn-beijing?tab=model#/model-market/detail/wan2.7-t2v?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.

prompt*string

Required. Up to 5000 characters. Wan2.7 supports multi-shot structure through natural language (e.g., Shot 1 [0-3s]...).

RequiredExample Value: A hyper-realistic, macro slow-motion shot of a single, vibrant green leaf during a heavy tropical rainstorm. A large, perfectly spherical raindrop lands on the tip of the leaf; the leaf bends realistically under the weight, oscillating with natural physics before the droplet slides off. As the drop falls, the camera follows its descent in a 'bullet-time' tracking shot, showing the forest floor reflected upside-down inside the liquid sphere. Soft cinematic bokeh, dappled sunlight breaking through the canopy, 8k, high frame rate, masterful temporal consistency.Placeholder: Describe the video content, subject, actions, scene, camera movement, dialogue, and sound effects...

negative_prompt?string

Optional. Up to 500 characters. Describe content you do not want to see in the video.

Example Value: low resolution, blurry, distorted, deformed, watermark, extra limbs, bad anatomy, flicker, noisyPlaceholder: Describe what should not appear in the video...

audio_url?string

Optional. Custom audio track (wav/mp3, 2-30s, ≤15MB). If empty, the model auto-generates background music.

Placeholder: wav or mp3 link. Leave empty for auto-generation.

resolution?string

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

Example Value: 1080P

Enum/Options:

1080P720P

ratio?string

Output video aspect ratio: 16:9 / 9:16 / 1:1 / 4:3 / 3:4. Default 16:9.

Example Value: 16:9

Enum/Options:

16:99:161:14:33:4

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

When on, adds 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]. Empty means system random; a fixed seed improves reproducibility.

Placeholder: Leave empty for random seed

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-t2v",
  "prompt": "A hyper-realistic, macro slow-motion shot of a single, vibrant green leaf during a heavy tropical rainstorm. A large, perfectly spherical raindrop lands on the tip of the leaf; the leaf bends realistically under the weight, oscillating with natural physics before the droplet slides off. As the drop falls, the camera follows its descent in a 'bullet-time' tracking shot, showing the forest floor reflected upside-down inside the liquid sphere. Soft cinematic bokeh, dappled sunlight breaking through the canopy, 8k, high frame rate, masterful temporal consistency.",
  "size": "1080P",
  "duration": 5,
  "metadata": {
    "input": {
      "negative_prompt": "low resolution, blurry, distorted, deformed, watermark"
    },
    "parameters": {
      "ratio": "16:9",
      "prompt_extend": true,
      "watermark": false
    }
  }
}'

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

API Documentation

API Reference

Videos

Generate Video

Supported Model Code

Loading models...

Wan2.7-T2V (wan2.7-t2v)

wan2.7-t2v0 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.

prompt*string

Required. Up to 5000 characters. Wan2.7 supports multi-shot structure through natural language (e.g., Shot 1 [0-3s]...).

negative_prompt?string

Optional. Up to 500 characters. Describe content you do not want to see in the video.

Example Value: low resolution, blurry, distorted, deformed, watermark, extra limbs, bad anatomy, flicker, noisyPlaceholder: Describe what should not appear in the video...

audio_url?string

Optional. Custom audio track (wav/mp3, 2-30s, ≤15MB). If empty, the model auto-generates background music.

Placeholder: wav or mp3 link. Leave empty for auto-generation.

resolution?string

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

Example Value: 1080P

Enum/Options:

1080P720P

ratio?string

Output video aspect ratio: 16:9 / 9:16 / 1:1 / 4:3 / 3:4. Default 16:9.

Example Value: 16:9

Enum/Options:

16:99:161:14:33:4

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

When on, adds 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]. Empty means system random; a fixed seed improves reproducibility.

Placeholder: Leave empty for random seed

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-t2v",
  "prompt": "A hyper-realistic, macro slow-motion shot of a single, vibrant green leaf during a heavy tropical rainstorm. A large, perfectly spherical raindrop lands on the tip of the leaf; the leaf bends realistically under the weight, oscillating with natural physics before the droplet slides off. As the drop falls, the camera follows its descent in a 'bullet-time' tracking shot, showing the forest floor reflected upside-down inside the liquid sphere. Soft cinematic bokeh, dappled sunlight breaking through the canopy, 8k, high frame rate, masterful temporal consistency.",
  "size": "1080P",
  "duration": 5,
  "metadata": {
    "input": {
      "negative_prompt": "low resolution, blurry, distorted, deformed, watermark"
    },
    "parameters": {
      "ratio": "16:9",
      "prompt_extend": true,
      "watermark": false
    }
  }
}'

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

Wan2.7-T2V - Generate Video (AI Model · By ) | ModelStream