BRASILTradução de apoio para consulta. Código e identificadores técnicos preservados. Consultar referência original ↗
wan3.0-video Geração de Vídeo
wan3.0-video Modelo de geração de vídeo tudo-em-um. Suporta texto para vídeo, primeiro quadro/primeiro+último quadro, referência tudo-em-um, áudio e muito mais.
Python SDK
```python expandable
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope
import os
# If you have not set environment variables, replace the following line with your API Key: api_key="sk-xxx"
# Get API Key: https://www.alibabacloud.com/help/model-studio/get-api-key
api_key = os.getenv("DASHSCOPE_API_KEY")
media = [{'type': 'file', 'url': 'https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260806/ebapmr/glass.pptx'}]
def sample_async_call():
# Submit video generation task asynchronously
rsp = VideoSynthesis.async_call(api_key=api_key,
model='wan3.0-video',
prompt='A high-end smart glasses product advertisement with a minimalist, futuristic, and fashionable style. The color palette features black, silver-gray, and ice-blue tones with subtle white light accents and parameter UI graphics. Opening in pure black background, a pair of smart glasses slowly emerges from darkness with refined highlights on the temple edges. The camera captures ultra-close details of lenses, nose pads, hinges, temples, and material textures, showcasing metal and high-performance composite materials. The product then rotates slowly in mid-air with minimalist motion graphics displaying core parameters. Then the camera pulls back as all parts precisely reassemble into the complete product, transitioning to a young model wearing demonstration in minimalist spaces and urban lighting environments.',
media=media,
resolution='480P',
ratio='adaptive',
duration=10,
prompt_extend=True)
print(rsp)
if rsp.status_code == HTTPStatus.OK:
print("task_id: %s" % rsp.output.task_id)
else:
print('Failed, status_code: %s, code: %s, message: %s' %
(rsp.status_code, rsp.code, rsp.message))
# Query task status
status = VideoSynthesis.fetch(task=rsp, api_key=api_key)
if status.status_code == HTTPStatus.OK:
print(status.output.task_status)
else:
print('Failed, status_code: %s, code: %s, message: %s' %
(status.status_code, status.code, status.message))
# Wait for task completion
rsp = VideoSynthesis.wait(task=rsp, api_key=api_key)
print(rsp)
if rsp.status_code == HTTPStatus.OK:
print(rsp.output.video_url)
else:
print('Failed, status_code: %s, code: %s, message: %s' %
(rsp.status_code, rsp.code, rsp.message))
if __name__ == '__main__':
sample_async_call()
```
OpenAPI
openapi: 3.1.0
info:
title: Wan 3.0 Video Generation API
description: Wan 3.0 is an All-in-One video generation model that supports text-to-video, image-to-video (first-frame / first+last-frame), reference-to-video, and file-to-video, generating videos up to 30 seconds. Submit a task asynchronously, then poll `GET /tasks/{task_id}` for the result.
version: 1.0.0
servers:
- url: https://maas.qwencloudapi.com/api/v1
description: QwenCloud
security:
- BearerAuth: []
paths:
/services/aigc/video-generation/video-synthesis:
post:
operationId: createWan30VideoTask
summary: Create video generation task
description: Submit a video generation task. Returns a `task_id` for polling. Supports text-to-video, first-frame/first+last-frame, all-in-one reference modes, and file-to-video.
parameters:
- name: X-DashScope-Async
in: header
required: true
description: 'Must be set to `enable` for asynchronous task submission. Missing this header causes: "current user api does not support synchronous calls".'
schema:
type: string
enum:
- enable
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/Wan30VideoRequest"
responses:
"200":
description: Task submitted successfully
content:
application/json:
schema:
$ref: "#/components/schemas/AsyncTaskSubmitResponse"
"400":
description: Invalid request parameters
content:
application/json:
schema:
$ref: "#/components/schemas/DashScopeErrorResponse"
x-codeSamples:
- lang: curl
label: File to video
source: |-
curl --location 'https://maas.qwencloudapi.com/api/v1/services/aigc/video-generation/video-synthesis' \
-H 'X-DashScope-Async: enable' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "wan3.0-video",
"input": {
"prompt": "A premium smart glasses product ad with a minimalist, futuristic, and fashionably sophisticated style. Restrained lighting with black, silver-gray, and ice-blue as the primary palette, accented by soft white light and parametric UI graphics. Opening on a pure black background, smart glasses slowly emerge from darkness with refined highlights along the temple edges, the frame outlined by cool rim lighting. The camera captures ultra-close-up shots of the lens, nose pads, hinges, temples, and material details, showcasing the delicate texture of metal and high-performance composites. Subsequently the product rotates slowly in mid-air while minimalist motion graphics display core specs. Then the camera quickly converges, all components precisely reassembling into the complete product, cutting to a young model wearing them—sharp features, confident demeanor, in clean urban fashion, naturally turning, raising a hand, walking, and smiling in a minimal space with city light and shadow. The closing shot shows the product suspended on a solid background as the camera slowly pushes into the brand logo and core slogan.",
"media": [
{
"type": "file",
"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260806/ebapmr/glass.pptx"
}
]
},
"parameters": {
"resolution": "480P",
"ratio": "adaptive",
"duration": 10,
"prompt_extend": true
}
}'
- lang: curl
label: Reference to video
source: |-
curl --location 'https://maas.qwencloudapi.com/api/v1/services/aigc/video-generation/video-synthesis' \
-H 'X-DashScope-Async: enable' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "wan3.0-video",
"input": {
"prompt": "Video1 holds Image3, playing a soothing folk song on the chair in Image4, saying: \"The sunshine is wonderful today.\" Image1 holds Image2, walks past Video1, places Image2 on the table next to Video1, and says: \"That sounds great, can you play it again?\"",
"media": [
{
"type": "reference_image",
"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260408/sjuytr/wan-r2v-object-girl.jpg"
},
{
"type": "reference_video",
"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260129/qigswt/wan-r2v-role2.mp4"
},
{
"type": "reference_image",
"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260129/rtjeqf/wan-r2v-object3.png"
},
{
"type": "reference_image",
"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260129/qpzxps/wan-r2v-object4.png"
},
{
"type": "reference_image",
"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260129/wfjikw/wan-r2v-backgroud5.png"
}
]
},
"parameters": {
"resolution": "480P",
"ratio": "adaptive",
"duration": 5,
"prompt_extend": true
}
}'
- lang: curl
label: Text-to-video
source: |-
curl --location 'https://maas.qwencloudapi.com/api/v1/services/aigc/video-generation/video-synthesis' \
-H 'X-DashScope-Async: enable' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "wan3.0-video",
"input": {
"prompt": "A kitten running on rooftops under moonlight, neon lights flickering in the distance, cinematic quality, smooth camera movement."
},
"parameters": {
"resolution": "480P",
"ratio": "adaptive",
"duration": 5,
"prompt_extend": true
}
}'
- lang: curl
label: First-frame to video
source: |-
curl --location 'https://maas.qwencloudapi.com/api/v1/services/aigc/video-generation/video-synthesis' \
-H 'X-DashScope-Async: enable' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "wan3.0-video",
"input": {
"prompt": "An urban fantasy art scene. A dynamic graffiti character—a spray-painted boy—comes alive from a concrete wall, rapping energetically with a classic hip-hop pose under a railway bridge at night, illuminated by a lone streetlight with cinematic atmosphere.",
"media": [
{
"type": "first_frame",
"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250925/wpimhv/rap.png"
}
]
},
"parameters": {
"resolution": "480P",
"ratio": "adaptive",
"duration": 5,
"prompt_extend": true
}
}'
- lang: curl
label: First+last-frame to video
source: |-
curl --location 'https://maas.qwencloudapi.com/api/v1/services/aigc/video-generation/video-synthesis' \
-H 'X-DashScope-Async: enable' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "wan3.0-video",
"input": {
"prompt": "A young girl transitions from a smile to laughter, camera slowly pushing in, background lighting shifting from cool to warm tones.",
"media": [
{
"type": "first_frame",
"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250925/wpimhv/rap.png"
},
{
"type": "last_frame",
"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260408/sjuytr/wan-r2v-object-girl.jpg"
}
]
},
"parameters": {
"resolution": "480P",
"ratio": "adaptive",
"duration": 5,
"prompt_extend": true
}
}'
- lang: curl
label: Video editing
source: |-
curl --location 'https://maas.qwencloudapi.com/api/v1/services/aigc/video-generation/video-synthesis' \
-H 'X-DashScope-Async: enable' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "wan3.0-video",
"input": {
"prompt": "Transform the entire scene into a clay art style",
"media": [
{
"type": "reference_video",
"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260402/ldnfdf/wan2.7-videoedit-style-change.mp4"
}
]
},
"parameters": {
"resolution": "720P",
"prompt_extend": true
}
}'
- lang: curl
label: Video extension
source: |-
curl --location 'https://maas.qwencloudapi.com/api/v1/services/aigc/video-generation/video-synthesis' \
-H 'X-DashScope-Async: enable' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "wan3.0-video",
"input": {
"prompt": "Extend Video 1 forward: the baker brings out the brushed bread, sets the brush aside, and the camera follows the baker to the oven in the back for baking",
"media": [
{
"type": "reference_video",
"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260402/ldnfdf/wan2.7-videoedit-style-change.mp4"
}
]
},
"parameters": {
"resolution": "720P",
"ratio": "adaptive",
"prompt_extend": true
}
}'
- lang: python
label: Python SDK
source: |-
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope
import os
# If you have not set environment variables, replace the following line with your API Key: api_key="sk-xxx"
# Get API Key: https://home.qwencloud.com
api_key = os.getenv("DASHSCOPE_API_KEY")
media = [{'type': 'file', 'url': 'https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260806/ebapmr/glass.pptx'}]
def sample_async_call():
# Submit video generation task asynchronously
rsp = VideoSynthesis.async_call(api_key=api_key,
model='wan3.0-video',
prompt='A high-end smart glasses product advertisement with a minimalist, futuristic, and fashionable style. The color palette features black, silver-gray, and ice-blue tones with subtle white light accents and parameter UI graphics. Opening in pure black background, a pair of smart glasses slowly emerges from darkness with refined highlights on the temple edges. The camera captures ultra-close details of lenses, nose pads, hinges, temples, and material textures, showcasing metal and high-performance composite materials. The product then rotates slowly in mid-air with minimalist motion graphics displaying core parameters. Then the camera pulls back as all parts precisely reassemble into the complete product, transitioning to a young model wearing demonstration in minimalist spaces and urban lighting environments.',
media=media,
resolution='480P',
ratio='adaptive',
duration=10,
prompt_extend=True)
print(rsp)
if rsp.status_code == HTTPStatus.OK:
print("task_id: %s" % rsp.output.task_id)
else:
print('Failed, status_code: %s, code: %s, message: %s' %
(rsp.status_code, rsp.code, rsp.message))
# Query task status
status = VideoSynthesis.fetch(task=rsp, api_key=api_key)
if status.status_code == HTTPStatus.OK:
print(status.output.task_status)
else:
print('Failed, status_code: %s, code: %s, message: %s' %
(status.status_code, status.code, status.message))
# Wait for task completion
rsp = VideoSynthesis.wait(task=rsp, api_key=api_key)
print(rsp)
if rsp.status_code == HTTPStatus.OK:
print(rsp.output.video_url)
else:
print('Failed, status_code: %s, code: %s, message: %s' %
(rsp.status_code, rsp.code, rsp.message))
if __name__ == '__main__':
sample_async_call()
components:
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: QwenCloud API Key. See [Get an API Key](/api-reference/preparation/api-key).
schemas:
Wan30VideoRequest:
type: object
required:
- model
- input
properties:
model:
type: string
description: |-
Model name. Valid values:
- `wan3.0-video-prime`: High-speed version with capabilities aligned to the standard version, with significantly improved end-to-end speed.
- `wan3.0-video`: Standard version.
enum:
- wan3.0-video-prime
- wan3.0-video
example: wan3.0-video
input:
type: object
description: Input information. Either `prompt` or `media` is required.
properties:
prompt:
type: string
description: Text prompt describing the desired video content. Either this or `media` is required. Supports Chinese and English, up to 20,000 characters (auto-truncated beyond). In all-in-one reference mode, use "Image1", "Video1", "Audio1" etc. in the prompt to refer to media items by their array order.
maxLength: 20000
example: A kitten running on rooftops under moonlight, neon lights flickering in the distance, cinematic quality, smooth camera movement.
media:
type: array
description: Media array supporting images, videos, audio, files, and web links as input. Either this or `prompt` is required. In reference mode, array order defines the numbering in prompts (images and videos are counted separately). `reference_xx`/`file`/`link` types and `first_frame`/`last_frame` types are mutually exclusive.
items:
$ref: "#/components/schemas/MediaItem"
parameters:
$ref: "#/components/schemas/Wan30VideoParameters"
MediaItem:
type: object
required:
- type
- url
properties:
type:
type: string
description: |-
Media type. `reference_xx`/`file`/`link` types and `first_frame`/`last_frame` types are mutually exclusive within the same request.
Media limits by type:
- `reference_image` / `first_frame` / `last_frame` (image): JPEG/JPG/PNG/BMP/WEBP; resolution [240, 8000] per side; aspect ratio ≤ 8:1; file size ≤ 20MB.
- `reference_video` (video): mp4/mov; duration [1, 15]s per clip, total ≤ 15s; frame rate ≥ 16 fps; resolution [240, 4096] per side; aspect ratio ≤ 8:1; file size ≤ 100MB per clip.
- `reference_audio` (audio): wav/mp3; duration [1, 15]s per clip, total ≤ 15s; file size ≤ 15MB.
- `file`: docx/doc/xlsx/xls/pptx/ppt/pdf/txt/key/pages/numbers/md; file size ≤ 100MB; page limit ≤ 50 pages (validated for pdf/docx/doc/pptx/ppt/key/pages).
enum:
- first_frame
- last_frame
- reference_image
- reference_video
- reference_audio
- file
- link
url:
type: string
description: Media URL or Base64-encoded data. Supports public URLs (HTTP/HTTPS) and Base64 encoding (`data:{MIME_type};base64,{data}`).
Wan30VideoParameters:
type: object
description: Video generation parameters.
properties:
resolution:
type: string
description: Output video resolution tier.
enum:
- 480P
- 720P
- 1080P
default: 1080P
ratio:
type: string
description: Output video aspect ratio. `adaptive` automatically selects the best ratio based on input media and intent.
enum:
- adaptive
- 21:9
- 16:9
- 4:3
- 1:1
- 3:4
- 9:16
default: adaptive
duration:
type: integer
description: "Output video duration in seconds. Without video input: integer in [2, 30]. With video input: input + output duration must not exceed 30s. Set to `-1` for smart duration mode (model selects optimal length)."
default: 5
audio:
type: boolean
description: "Whether the output video includes audio. `true` (default): includes sound. `false`: no audio track. Pricing is the same regardless of this setting."
default: true
seed:
type: integer
description: "Random seed. Used to reproduce generation results. Value range: -1 or [0, 2147483647]. When set to -1 or not specified, the system automatically generates a random seed. Even with the same seed value, generation results may not be perfectly identical."
minimum: -1
maximum: 2147483647
watermark:
type: boolean
description: Whether to add a watermark.
default: false
prompt_extend:
type: boolean
description: Whether to enable intelligent prompt rewriting. When enabled, a large language model rewrites the input prompt to improve video generation quality. Recommended for shorter prompts; increases latency slightly. When a document (`file`) or webpage (`link`) is provided as input, `prompt_extend` must be set to `true`.
default: true
AsyncTaskSubmitResponse:
type: object
description: Async task submission response.
properties:
request_id:
type: string
description: Unique request identifier for tracing and troubleshooting.
example: 4909100c-7b5a-9f92-bfe5-xxxxxx
output:
type: object
properties:
task_id:
type: string
description: Task ID, valid for 24 hours. Use with `GET /tasks/{task_id}`. Do not re-create the task; poll instead.
example: 0385dc79-5ff8-4d82-bcb6-xxxxxx
task_status:
type: string
description: Initial task status, typically `PENDING`.
enum:
- PENDING
- RUNNING
- SUCCEEDED
- FAILED
- CANCELED
- UNKNOWN
Wan30VideoTaskStatusResponse:
type: object
description: Wan 3.0 video generation task status response.
properties:
request_id:
type: string
description: Unique request identifier for tracing and troubleshooting.
example: 78c9b768-0285-996c-b682-xxxxxx
output:
type: object
properties:
task_id:
type: string
description: Task ID.
example: 17ed7e50-00cf-4509-aea1-xxxxxx
task_status:
type: string
description: "Task status. Flow: `PENDING` (queued) -> `RUNNING` (processing) -> `SUCCEEDED` / `FAILED`. Manually canceled: `CANCELED`. Expired: `UNKNOWN`."
enum:
- PENDING
- RUNNING
- SUCCEEDED
- FAILED
- CANCELED
- UNKNOWN
submit_time:
type: string
description: "Task submission time. Format: YYYY-MM-DD HH:mm:ss.SSS."
example: 2026-08-06 10:01:35.452
scheduled_time:
type: string
description: "Task execution start time. Format: YYYY-MM-DD HH:mm:ss.SSS."
example: 2026-08-06 10:01:35.507
end_time:
type: string
description: "Task completion time. Format: YYYY-MM-DD HH:mm:ss.SSS. Only returned for `SUCCEEDED` or `FAILED`."
example: 2026-08-06 10:13:33.838
orig_prompt:
type: string
description: Original input prompt text.
video_url:
type: string
format: uri
description: Generated video URL. Only returned when `task_status` is `SUCCEEDED`. Valid for 24 hours — download promptly.
example: https://dashscope-result-sg.oss-ap-southeast-1.aliyuncs.com/xxx/video.mp4
code:
type: string
description: Error code. Only returned when `task_status` is `FAILED`.
message:
type: string
description: Error message. Only returned when `task_status` is `FAILED`.
usage:
type: object
description: Usage statistics. Only counted for successful results.
properties:
video_count:
type: integer
description: Number of generated videos. Fixed at 1.
duration:
type: number
description: Total video duration in seconds. When no input reference video is provided, it equals the output video duration; when an input reference video is provided, it equals the sum of the input video duration and the output video duration.
input_video_duration:
type: number
description: Input video duration in seconds. Returns 0.0 when no video is provided as input.
output_video_duration:
type: number
description: Output video duration in seconds.
fps:
type: integer
description: "Generated video frame rate. Default value: 30."
SR:
type: integer
description: Generated video resolution tier (e.g. 720 for 720P).
ratio:
type: string
description: Generated video aspect ratio (e.g. 16:9).
DashScopeErrorResponse:
type: object
description: API error response.
properties:
request_id:
type: string
description: Unique request identifier for tracing and troubleshooting.
code:
type: string
description: Error code.
example: InvalidApiKey
message:
type: string
description: Error description.
example: Invalid API-key provided.