BRASILTradução de apoio para consulta. Código e identificadores técnicos preservados. Consultar referência original ↗
Wan 2.7 -- Gere um vídeo a partir de imagem
Enviar tarefa de imagem para vídeo (wan2.7)
Gere vídeos de até 15 segundos em 1080P a partir de imagens, áudio e clipes de vídeo, com sincronização de áudio opcional e controle do primeiro ao último quadro.
Mudanças de wan2.6
- API unificada: o primeiro quadro, o primeiro e último quadro e a continuação do vídeo compartilham um endpoint por meio do
mediaarray - sem APIs separadas. - Sincronização de áudio e vídeo: fornece um
driving_audioarquivo para sincronização labial. Se omitido, o modelo gera automaticamente efeitos sonoros correspondentes. - Controle de resolução: Definir
resolution(720P/1080P) em vez do pixel exatosize. - Prompts mais longos: até 5.000 caracteres (era 800).
- Prompt negativo movido: Agora em
input.negative_promptem vez deparameters.negative_prompt. - Marca d'água desativada por padrão:
watermarko padrão éfalse(eratrue).
OpenAPI
openapi: 3.1.0
info:
title: Wan 2.7 Image-to-Video API
description: "The Wan 2.7 image-to-video model now supports multi-modal input — including images, audio, and video — and performs three main tasks: video generation from the first frame, video generation from the first and last frames, and video continuation. 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: Singapore
security:
- BearerAuth: []
paths:
/services/aigc/video-generation/video-synthesis:
post:
operationId: createWan27ImageToVideo
summary: Create image-to-video task
description: Submit an image-to-video task. Returns a `task_id` for polling. Requires DashScope Java SDK 2.22.14 or later.
parameters:
- name: X-DashScope-Async
in: header
required: true
description: Must be set to `enable` for asynchronous task submission.
schema:
type: string
enum:
- enable
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/Wan27ImageToVideoRequest"
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: cURL - First frame + audio
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": "wan2.7-i2v",
"input": {
"prompt": "A scene of urban fantasy art. A dynamic graffiti art character. A boy made of spray paint comes to life on a concrete wall. He sings an English rap song at high speed while striking a classic, energetic rapper pose. The scene is set under an urban railway bridge at night. The light comes from a single street lamp, creating a cinematic atmosphere full of high energy and amazing detail. The audio of the video consists entirely of the rap, with no other dialogue or noise.",
"media": [
{
"type": "first_frame",
"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250925/wpimhv/rap.png"
},
{
"type": "driving_audio",
"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250925/ozwpvi/rap.mp3"
}
]
},
"parameters": {
"resolution": "720P",
"duration": 10,
"prompt_extend": true,
"watermark": true
}
}'
- lang: curl
label: cURL - First and last frames
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": "wan2.7-i2v",
"input": {
"prompt": "Realistic style, a small black cat looks up at the sky curiously. The camera angle gradually rises from eye level, finally capturing its curious gaze from a top-down view.",
"media": [
{
"type": "first_frame",
"url": "https://wanx.alicdn.com/material/20250318/first_frame.png"
},
{
"type": "last_frame",
"url": "https://wanx.alicdn.com/material/20250318/last_frame.png"
}
]
},
"parameters": {
"resolution": "720P",
"duration": 10,
"prompt_extend": false,
"watermark": true
}
}'
- lang: curl
label: cURL - Video continuation
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": "wan2.7-i2v",
"input": {
"prompt": "A girl takes a selfie in the mirror, then leaves with her backpack.",
"media": [
{
"type": "first_clip",
"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260129/hfugmr/wan-r2v-role1.mp4"
}
]
},
"parameters": {
"resolution": "720P",
"duration": 10,
"prompt_extend": true,
"watermark": true
}
}'
- lang: python
label: Python - Synchronous call
source: |-
import os
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope
dashscope.base_http_api_url = 'https://maas.qwencloudapi.com/api/v1'
api_key = os.getenv("DASHSCOPE_API_KEY")
def sample_sync_call():
print('Please wait...')
rsp = VideoSynthesis.call(
api_key=api_key,
model='wan2.7-i2v',
prompt='A cat slowly turns its head and looks at the camera',
media=[
{
"type": "first_frame",
"url": "https://cdn.translate.alibaba.com/r/wanx-demo-1.png"
}
],
resolution='720P',
duration=5,
prompt_extend=True,
watermark=True)
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_sync_call()
- lang: python
label: Python - Asynchronous call
source: |-
import os
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope
dashscope.base_http_api_url = 'https://maas.qwencloudapi.com/api/v1'
api_key = os.getenv("DASHSCOPE_API_KEY")
def sample_async_call():
rsp = VideoSynthesis.async_call(
api_key=api_key,
model='wan2.7-i2v',
prompt='A cat slowly turns its head and looks at the camera',
media=[
{
"type": "first_frame",
"url": "https://cdn.translate.alibaba.com/r/wanx-demo-1.png"
}
],
resolution='720P',
duration=5,
prompt_extend=True,
watermark=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))
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()
- lang: java
label: Java - Synchronous call
source: |-
import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesis;
import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisParam;
import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisResult;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.JsonUtils;
import com.alibaba.dashscope.utils.Constants;
import java.util.*;
public class Wan27I2V {
static {
Constants.baseHttpApiUrl = "https://maas.qwencloudapi.com/api/v1";
}
public static void main(String[] args) {
try {
VideoSynthesis vs = new VideoSynthesis();
List<VideoSynthesisParam.Media> media = new ArrayList<VideoSynthesisParam.Media>() {{
add(VideoSynthesisParam.Media.builder()
.url("https://cdn.translate.alibaba.com/r/wanx-demo-1.png")
.type("first_frame").build());
}};
Map<String, Object> parameters = new HashMap<>();
parameters.put("resolution", "720P");
parameters.put("duration", 5);
parameters.put("prompt_extend", true);
parameters.put("watermark", true);
VideoSynthesisParam param = VideoSynthesisParam.builder()
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
.model("wan2.7-i2v")
.prompt("A cat slowly turns its head and looks at the camera")
.media(media)
.parameters(parameters)
.build();
System.out.println("Please wait...");
VideoSynthesisResult result = vs.call(param);
System.out.println(JsonUtils.toJson(result));
} catch (ApiException | NoApiKeyException | InputRequiredException e) {
System.out.println(e.getMessage());
}
}
}
- lang: java
label: Java - Asynchronous call
source: |-
import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesis;
import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisParam;
import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisResult;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.JsonUtils;
import com.alibaba.dashscope.utils.Constants;
import java.util.*;
public class Wan27I2V {
static {
Constants.baseHttpApiUrl = "https://maas.qwencloudapi.com/api/v1";
}
public static void main(String[] args) {
try {
String apiKey = System.getenv("DASHSCOPE_API_KEY");
VideoSynthesis vs = new VideoSynthesis();
List<VideoSynthesisParam.Media> media = new ArrayList<VideoSynthesisParam.Media>() {{
add(VideoSynthesisParam.Media.builder()
.url("https://cdn.translate.alibaba.com/r/wanx-demo-1.png")
.type("first_frame").build());
}};
Map<String, Object> parameters = new HashMap<>();
parameters.put("resolution", "720P");
parameters.put("duration", 5);
parameters.put("prompt_extend", true);
parameters.put("watermark", true);
VideoSynthesisParam param = VideoSynthesisParam.builder()
.apiKey(apiKey)
.model("wan2.7-i2v")
.prompt("A cat slowly turns its head and looks at the camera")
.media(media)
.parameters(parameters)
.build();
VideoSynthesisResult task = vs.asyncCall(param);
System.out.println(JsonUtils.toJson(task));
System.out.println("Please wait...");
VideoSynthesisResult result = vs.wait(task, apiKey);
System.out.println(JsonUtils.toJson(result));
} catch (ApiException | NoApiKeyException | InputRequiredException e) {
System.out.println(e.getMessage());
}
}
}
components:
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: DashScope API Key. Get one from the [QwenCloud console](https://home.qwencloud.com/api-keys).
schemas:
Wan27ImageToVideoRequest:
type: object
required:
- model
- input
properties:
model:
type: string
description: "Model identifier. Supported values: `wan2.7-i2v`, `wan2.7-i2v-2026-04-25`."
enum:
- wan2.7-i2v
- wan2.7-i2v-2026-04-25
example: wan2.7-i2v
input:
type: object
required:
- media
description: The basic input information, such as the prompt.
properties:
prompt:
type: string
description: The text prompt. Describes the elements and visual features of the video you want. Supports Chinese and English, up to 5,000 characters (auto-truncated if exceeded).
example: A kitten runs on the grass.
negative_prompt:
type: string
description: The negative prompt. Describes content you do not want in the video (e.g., `low quality, blurry, extra fingers`). Supports Chinese and English. The prompt can be up to 500 characters long (auto-truncated if exceeded).
example: low resolution, error, worst quality, low quality, deformed, extra fingers, bad proportions
media:
type: array
description: |-
A list of media assets. Specifies reference materials (images, audio, and video) for video generation. Each element in the array is a media object that contains the `type` and `url`. Each `type` can appear at most once.
Only the following asset combinations are supported. Invalid combinations result in an error.
- `first_frame`
- `first_frame` + `driving_audio`
- `first_frame` + `last_frame`
- `first_frame` + `last_frame` + `driving_audio`
- `first_clip`
- `first_clip` + `last_frame`
items:
type: object
required:
- type
- url
properties:
type:
type: string
description: |-
The type of media asset. Valid values:
- `first_frame`: The URL of the first or last frame, or Base64-encoded data. Video generation from the first frame and video generation from the first and last frames are supported. JPEG/JPG/PNG/BMP/WEBP, 240-8000 px per side, 1:8 to 8:1 ratio, max 20 MB.
- `last_frame`: Last frame image. Same limits as `first_frame`.
- `driving_audio`: The URL of the audio file. Pass audio: The model uses the audio as a driving source to generate the video, such as for lip-syncing and action timing. Do not pass audio: The model automatically generates matching background music or sound effects based on the video content. WAV/MP3, 2-30 s, max 15 MB.
- `first_clip`: The URL of the video file. The model generates a continuation based on the video content. The `duration` parameter controls the maximum duration of the continuation. MP4/MOV, 2-10 s, 240-4096 px per side, 1:8 to 8:1 ratio, max 100 MB.
enum:
- first_frame
- last_frame
- driving_audio
- first_clip
url:
type: string
format: uri
description: The URL of the media asset. Assets include images, audio, and video.
parameters:
$ref: "#/components/schemas/Wan27ImageToVideoParameters"
Wan27ImageToVideoParameters:
type: object
description: Video processing parameters, such as resolution, duration, prompt rewriting, and watermarks.
properties:
resolution:
type: string
description: The resolution tier for the generated video. Controls the video definition (total pixels). The resolution directly affects the cost. Before you make a call, confirm the resolution you need. The model automatically scales the video to a total pixel count close to the selected resolution tier. The video's aspect ratio should be as consistent as possible with the input material (first frame or first video segment).
enum:
- 720P
- 1080P
default: 1080P
duration:
type: integer
description: Video duration in seconds (integer, 2-15). Longer videos cost more -- billing is per second. For video continuation (`first_clip`), this is the total output duration including the input clip. For example, if `duration=15` and the input is 3 s, the model generates 12 s of new content.
minimum: 2
maximum: 15
default: 5
prompt_extend:
type: boolean
description: Rewrite the prompt using a Large Language Model before generation. Improves results for short or vague prompts but adds latency. Set to `false` to use your prompt verbatim.
default: true
watermark:
type: boolean
description: Add an "AI Generated" watermark in the lower-right corner.
default: false
seed:
type: integer
description: Seed for reproducible results. Same seed + same parameters produces similar (not identical) output.
minimum: 0
maximum: 2147483647
AsyncTaskSubmitResponse:
type: object
description: Response from an asynchronous task submission.
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 for polling status. Use with `GET /tasks/{task_id}`.
example: 0385dc79-5ff8-4d82-bcb6-xxxxxx
task_status:
type: string
description: Initial task status, typically `PENDING`.
enum:
- PENDING
- RUNNING
- SUCCEEDED
- FAILED
Wan27I2VTaskStatusResponse:
type: object
description: Task status response for wan2.7 image-to-video.
properties:
request_id:
type: string
description: Request ID for troubleshooting. Include this when contacting support.
example: 2ca1c497-f9e0-449d-9a3f-xxxxxx
output:
type: object
properties:
task_id:
type: string
description: Task ID. Queryable for 24 hours after submission.
example: af6efbc0-4bef-4194-8246-xxxxxx
task_status:
type: string
description: "Task lifecycle: `PENDING` -> `RUNNING` -> `SUCCEEDED` or `FAILED`. `CANCELED` if manually stopped. `UNKNOWN` if expired."
enum:
- PENDING
- RUNNING
- SUCCEEDED
- FAILED
- CANCELED
- UNKNOWN
submit_time:
type: string
description: When the task was submitted (UTC+8, `YYYY-MM-DD HH:mm:ss.SSS`).
example: 2025-09-25 11:07:28.590
scheduled_time:
type: string
description: When the task started executing (UTC+8, `YYYY-MM-DD HH:mm:ss.SSS`).
example: 2025-09-25 11:07:35.349
end_time:
type: string
description: When the task finished (UTC+8, `YYYY-MM-DD HH:mm:ss.SSS`). Only present for `SUCCEEDED` or `FAILED` tasks.
example: 2025-09-25 11:17:11.650
orig_prompt:
type: string
description: The original prompt text, corresponding to the request parameter `prompt`.
video_url:
type: string
format: uri
description: URL of the generated video (MP4, H.264 encoding). Only present when `task_status` is `SUCCEEDED`. **Valid for 24 hours** -- download promptly.
example: https://dashscope-result-sh.oss-accelerate.aliyuncs.com/xxx.mp4?Expires=xxx
code:
type: string
description: Error code. Only present when `task_status` is `FAILED`.
message:
type: string
description: Error message. Only present when `task_status` is `FAILED`.
usage:
type: object
description: Resource consumption. Only present when `task_status` is `SUCCEEDED`.
properties:
duration:
type: integer
description: Billable video duration in seconds.
input_video_duration:
type: integer
description: Duration of the input video in seconds. `0` for first-frame tasks.
output_video_duration:
type: integer
description: Output video duration in seconds.
video_count:
type: integer
description: Number of videos generated. Always `1`.
SR:
type: integer
description: Resolution tier used (e.g., `720` for 720P, `1080` for 1080P).
DashScopeErrorResponse:
type: object
description: DashScope API error response.
properties:
request_id:
type: string
description: Unique request identifier for tracing and support.
code:
type: string
description: Machine-readable error code (e.g., `InvalidParameter`, `Throttling`, `Unauthorized`).
example: InvalidParameter
message:
type: string
description: Human-readable error message.
example: Invalid model name