Wan2.6-I2V-Flash - Generate Video (AI Model · By )

API Documentation

API Reference

Videos

Generate Video

Supported Model Code

Loading models...

Wan2.6-I2V-Flash (wan2.6-i2v-flash)

wan2.6-i2v-flash0 models support this endpoint

Wan2.6 image to video flash, faster and more cost-effective generation. Intelligent shot scheduling enables multi‑camera storytelling, supports stable multi‑speaker dialogue with more natural and realistic vocal timbres, and supports generation of clips up to 15 seconds in length. https://bailian.console.alibabacloud.com/cn-beijing?tab=model#/model-market/detail/wan2.6-i2v-flash?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.

img_url*string

Required. The starting reference image for video generation. JPEG/PNG/BMP/WEBP, ≤20MB.

RequiredExample Value: https://static.modelstream.ai/demo/wan/wan2.6-i2v-flash_reference.pngValue Range: 0 ≤ value ≤ 1

prompt*string

Describe the actions, scene changes, and artistic style in the video. Use natural language to control single/multi-shot.

RequiredExample Value: A high-fashion model walking gracefully in a neon-lit futuristic corridor, hair swaying naturally, eyes reflecting flickering lights, cinematic camera movement with a slight tilt, ultra-realistic textures and smooth motion.Placeholder: e.g., A high-fashion model walking in a neon corridor...

audio_url?string

Optional. Upload an audio file (WAV/MP3, 3-30s, ≤15MB) to generate synchronized video effects.

negative_prompt?string

Describe what you do not want to see in the video. Supports Chinese and English, max 500 chars.

Example Value: blurry, low quality, distorted, deformed, watermark, ugly

resolution?string

Video output resolution. Options: 720P, 1080P. Default 1080P.

Example Value: 1080P

Enum/Options:

1080P720P

duration?number

Length of the generated video, an integer in [2, 15], default 5s.

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

prompt_extend?boolean

When enabled, the model intelligently rewrites and refines the input prompt. Enabled by default.

Example Value: true

shot_type?string

Shot type; effective only when Prompt Extend is on. Single outputs a continuous single-shot video; Multi outputs a multi-shot video. Default single.

Example Value: single

Enum/Options:

Single: singleMulti: multi

audio?boolean

Whether to generate an audio track (speech/SFX/BGM). Enabled by default. When a Sync Audio file is provided, the uploaded audio takes precedence.

Example Value: true

watermark?boolean

When enabled, adds an 'AI-generated' watermark in the lower-right corner. Disabled by default.

Example Value: false

seed?number

Controls randomness, range [0, 2147483647]. Leave empty for random.

Placeholder: Leave blank for random

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": "wan2.6-i2v-flash",
  "prompt": "A high-fashion model walking gracefully in a neon-lit futuristic corridor, hair swaying naturally, eyes reflecting flickering lights, cinematic camera movement with a slight tilt, ultra-realistic textures and smooth motion.",
  "duration": 5,
  "metadata": {
    "input": {
      "negative_prompt": "blurry, low quality, distorted, deformed, watermark, ugly",
      "img_url": "https://static.modelstream.ai/demo/wan/wan2.6-i2v-flash_reference.png"
    },
    "parameters": {
      "resolution": "1080P",
      "prompt_extend": true,
      "shot_type": "single",
      "audio": true,
      "watermark": false
    }
  }
}'

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

API Documentation

API Reference

Videos

Generate Video

Supported Model Code

Loading models...

Wan2.6-I2V-Flash (wan2.6-i2v-flash)

wan2.6-i2v-flash0 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.

img_url*string

Required. The starting reference image for video generation. JPEG/PNG/BMP/WEBP, ≤20MB.

RequiredExample Value: https://static.modelstream.ai/demo/wan/wan2.6-i2v-flash_reference.pngValue Range: 0 ≤ value ≤ 1

prompt*string

Describe the actions, scene changes, and artistic style in the video. Use natural language to control single/multi-shot.

audio_url?string

Optional. Upload an audio file (WAV/MP3, 3-30s, ≤15MB) to generate synchronized video effects.

negative_prompt?string

Describe what you do not want to see in the video. Supports Chinese and English, max 500 chars.

Example Value: blurry, low quality, distorted, deformed, watermark, ugly

resolution?string

Video output resolution. Options: 720P, 1080P. Default 1080P.

Example Value: 1080P

Enum/Options:

1080P720P

duration?number

Length of the generated video, an integer in [2, 15], default 5s.

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

prompt_extend?boolean

When enabled, the model intelligently rewrites and refines the input prompt. Enabled by default.

Example Value: true

shot_type?string

Shot type; effective only when Prompt Extend is on. Single outputs a continuous single-shot video; Multi outputs a multi-shot video. Default single.

Example Value: single

Enum/Options:

Single: singleMulti: multi

audio?boolean

Whether to generate an audio track (speech/SFX/BGM). Enabled by default. When a Sync Audio file is provided, the uploaded audio takes precedence.

Example Value: true

watermark?boolean

When enabled, adds an 'AI-generated' watermark in the lower-right corner. Disabled by default.

Example Value: false

seed?number

Controls randomness, range [0, 2147483647]. Leave empty for random.

Placeholder: Leave blank for random

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": "wan2.6-i2v-flash",
  "prompt": "A high-fashion model walking gracefully in a neon-lit futuristic corridor, hair swaying naturally, eyes reflecting flickering lights, cinematic camera movement with a slight tilt, ultra-realistic textures and smooth motion.",
  "duration": 5,
  "metadata": {
    "input": {
      "negative_prompt": "blurry, low quality, distorted, deformed, watermark, ugly",
      "img_url": "https://static.modelstream.ai/demo/wan/wan2.6-i2v-flash_reference.png"
    },
    "parameters": {
      "resolution": "1080P",
      "prompt_extend": true,
      "shot_type": "single",
      "audio": true,
      "watermark": false
    }
  }
}'

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