Wan2.6-R2V - Generate Video (AI Model · By )

API Documentation

API Reference

Videos

Generate Video

Supported Model Code

Loading models...

Wan2.6-R2V (wan2.6-r2v)

wan2.6-r2v0 models support this endpoint

Wan2.6 reference to video flash, faster and more cost-effective generation. Supports using a specified person or any object as a reference, precisely maintaining consistency of appearance and voice, and allows multi‑character reference for joint performances. https://bailian.console.alibabacloud.com/cn-beijing?tab=model#/model-market/detail/wan2.6-r2v-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.

prompt*string

Describe the content, motion and camera you want. Refer to reference items by order as character1, character2... in the prompt.

RequiredExample Value: A cinematic, slow-motion drone sweep through a massive solarpunk library carved into a hollow redwood tree. The camera glides upward, following the curve of spiraling wooden staircases. Vibrant stained-glass "God rays" cut through the air, illuminating dancing dust motes and rows of leather-bound books. Lush ivy and ferns sway gently in a light breeze from the balconies. Hyper-realistic textures, warm golden hour lighting, ultra-wide angle, high-fidelity architectural cinematography.Placeholder: Describe the content you want to generate...

negative_prompt?string

Describe content you don't want in the video. Supports Chinese and English, max 500 chars.

Example Value: low resolution, bad quality, blurry, distorted, messyPlaceholder: Content you don't want in the video

refs?array

Upload up to 5 items (images + videos), with at most 3 videos. Images: JPEG/PNG/BMP/WEBP (≤20MB); videos: MP4/MOV (1-30s, ≤100MB). Order maps to character1, character2...

Example Value: ["https://static.modelstream.ai/demo/wan/wan2.6-r2v_image_1.png"]Value Range: 0 ≤ value ≤ 5

size?string

Output size (width*height). Default 1920*1080 (16:9 1080P).

Example Value: 1920*1080

Enum/Options:

16:9 (1080P): 1920*10809:16 (1080P): 1080*19201:1 (1080P): 1440*14404:3 (1080P): 1632*12483:4 (1080P): 1248*163216:9 (720P): 1280*7209:16 (720P): 720*12801:1 (720P): 960*9604:3 (720P): 1088*8323:4 (720P): 832*1088

duration?number

Length of the generated video, an integer in [2, 10], default 5s.

Example Value: 5Value Range: 2 ≤ value ≤ 10step: 1

shot_type?string

Single outputs a continuous single-shot video; Multi outputs a multi-shot video. Default single.

Example Value: single

Enum/Options:

Single Shot: singleMulti Shot: multi

audio?boolean

Whether to generate an audio track. Enabled by default.

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-r2v",
  "prompt": "A cinematic, slow-motion drone sweep through a massive solarpunk library carved into a hollow redwood tree. The camera glides upward, following the curve of spiraling wooden staircases. Vibrant stained-glass \"God rays\" cut through the air, illuminating dancing dust motes and rows of leather-bound books. Lush ivy and ferns sway gently in a light breeze from the balconies. Hyper-realistic textures, warm golden hour lighting, ultra-wide angle, high-fidelity architectural cinematography.",
  "size": "1920*1080",
  "duration": 5,
  "metadata": {
    "input": {
      "negative_prompt": "low resolution, bad quality, blurry, distorted, messy",
      "reference_urls": [
        "https://static.modelstream.ai/demo/wan/wan2.6-r2v_image_1.png"
      ]
    },
    "parameters": {
      "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-R2V (wan2.6-r2v)

wan2.6-r2v0 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

Describe the content, motion and camera you want. Refer to reference items by order as character1, character2... in the prompt.

negative_prompt?string

Describe content you don't want in the video. Supports Chinese and English, max 500 chars.

Example Value: low resolution, bad quality, blurry, distorted, messyPlaceholder: Content you don't want in the video

refs?array

Upload up to 5 items (images + videos), with at most 3 videos. Images: JPEG/PNG/BMP/WEBP (≤20MB); videos: MP4/MOV (1-30s, ≤100MB). Order maps to character1, character2...

Example Value: ["https://static.modelstream.ai/demo/wan/wan2.6-r2v_image_1.png"]Value Range: 0 ≤ value ≤ 5

size?string

Output size (width*height). Default 1920*1080 (16:9 1080P).

Example Value: 1920*1080

Enum/Options:

duration?number

Length of the generated video, an integer in [2, 10], default 5s.

Example Value: 5Value Range: 2 ≤ value ≤ 10step: 1

shot_type?string

Single outputs a continuous single-shot video; Multi outputs a multi-shot video. Default single.

Example Value: single

Enum/Options:

Single Shot: singleMulti Shot: multi

audio?boolean

Whether to generate an audio track. Enabled by default.

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-r2v",
  "prompt": "A cinematic, slow-motion drone sweep through a massive solarpunk library carved into a hollow redwood tree. The camera glides upward, following the curve of spiraling wooden staircases. Vibrant stained-glass \"God rays\" cut through the air, illuminating dancing dust motes and rows of leather-bound books. Lush ivy and ferns sway gently in a light breeze from the balconies. Hyper-realistic textures, warm golden hour lighting, ultra-wide angle, high-fidelity architectural cinematography.",
  "size": "1920*1080",
  "duration": 5,
  "metadata": {
    "input": {
      "negative_prompt": "low resolution, bad quality, blurry, distorted, messy",
      "reference_urls": [
        "https://static.modelstream.ai/demo/wan/wan2.6-r2v_image_1.png"
      ]
    },
    "parameters": {
      "shot_type": "single",
      "audio": true,
      "watermark": false
    }
  }
}'

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