BRASILTradução de apoio para consulta. Código e identificadores técnicos preservados. Consultar referência original ↗
Wan 2.6 — Recuperar resultado da imagem
Verifique Wan 2.6 status da tarefa de imagem
Consulte o status e os resultados da tarefa.
Estratégia de votação
Pesquise este endpoint com o retornado task_id. Recomendamos pesquisas a cada 5 a 10 segundos.
Notas importantes
- Expiração de URL: URLs de imagem expiram em 24 horas. Baixe imediatamente.
- Fluxo de status da tarefa:
PENDING→RUNNING→SUCCEEDEDouFAILED. - Outros status:
CANCELED(tarefa cancelada),UNKNOWN(ID de tarefa inválida ou expirada). - Validade do ID da tarefa: os IDs das tarefas são válidos por 24 horas. Depois que o ID da tarefa expirar, o status e os resultados não poderão ser consultados.
- Evite tarefas duplicadas: use pesquisas para recuperar resultados. Não reenvie solicitações.
OpenAPI
openapi: 3.1.0
info:
title: Wan2.6 Image Generation and Editing API
description: Wan2.6 image generation and editing API. Supports multi-image input, image editing, and interleaved text-image output.
version: 1.0.0
servers:
- url: https://maas.qwencloudapi.com/api/v1
description: Singapore
security:
- BearerAuth: []
paths:
/tasks/{task_id}:
get:
operationId: getWan26ImageTaskResult
summary: Query task result
description: Query the status and result of an async image task.
parameters:
- name: task_id
in: path
required: true
description: Task identifier returned by the async task creation endpoint.
schema:
type: string
responses:
"200":
description: Task status retrieved successfully.
content:
application/json:
schema:
$ref: "#/components/schemas/Wan26TaskStatusResponse"
examples:
SUCCEEDED:
summary: Task succeeded
value:
request_id: 43d9e959-25bc-4dc7-9888-xxxxxx
output:
task_id: 858cad55-4bdc-4ba3-ae6c-xxxxxx
task_status: SUCCEEDED
submit_time: 2025-12-16 04:21:02.275
scheduled_time: 2025-12-16 04:21:02.304
end_time: 2025-12-16 04:24:46.658
finished: true
choices:
- finish_reason: stop
message:
role: assistant
content:
- image: https://dashscope-result-intl.oss-cn-singapore.aliyuncs.com/1xxx.png?Expires=xxx
type: image
- finish_reason: stop
message:
role: assistant
content:
- image: https://dashscope-result-intl.oss-cn-singapore.aliyuncs.com/2xxx.png?Expires=xxx
type: image
usage:
size: 1376*768
total_tokens: 0
image_count: 2
output_tokens: 0
input_tokens: 0
FAILED:
summary: Task failed
value:
request_id: a4d78a5f-655f-9639-8437-xxxxxx
output:
task_id: 858cad55-4bdc-4ba3-ae6c-xxxxxx
task_status: FAILED
code: InvalidParameter
message: num_images_per_prompt must be 1
RUNNING:
summary: Task running
value:
request_id: c1209113-8437-424f-a386-xxxxxx
output:
task_id: 858cad55-4bdc-4ba3-ae6c-xxxxxx
task_status: RUNNING
"400":
description: Invalid request parameters.
content:
application/json:
schema:
$ref: "#/components/schemas/DashScopeErrorResponse"
x-codeSamples:
- lang: curl
label: cURL - Query task result
source: |-
# Replace {task_id} with the task_id value returned by the previous API call.
# task_id is valid for queries within 24 hours.
curl -X GET https://maas.qwencloudapi.com/api/v1/tasks/{task_id} \
--header "Authorization: Bearer $DASHSCOPE_API_KEY"
components:
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: DashScope API Key. Create one in the [QwenCloud console](https://home.qwencloud.com/api-keys).
schemas:
Wan26ImageRequest:
type: object
required:
- model
- input
properties:
model:
type: string
description: Model name. Set to `wan2.6-image`.
enum:
- wan2.6-image
example: wan2.6-image
input:
type: object
required:
- messages
description: Input data containing the messages array.
properties:
messages:
type: array
description: "Array of request content. Only single-turn conversations are supported. Provide one message with `role: user`."
minItems: 1
maxItems: 1
items:
$ref: "#/components/schemas/Wan26ImageMessage"
parameters:
$ref: "#/components/schemas/Wan26ImageParameters"
Wan26ImageMessage:
type: object
required:
- role
- content
properties:
role:
type: string
enum:
- user
description: Message role. Must be `user`.
content:
type: array
description: |-
Message content array. Must contain exactly one `text` object. Image objects depend on the mode:
- Image editing (`enable_interleave=false`): **1 to 4** image objects required.
- Interleaved text-image (`enable_interleave=true`): **0 to 1** image objects.
When using multiple images, include multiple `image` objects in the array. Image order is determined by array position.
items:
$ref: "#/components/schemas/Wan26ImageContentPart"
Wan26ImageContentPart:
type: object
description: Either an image or text content part.
properties:
text:
type: string
description: Positive prompt describing the desired image content, style, and composition. Supports Chinese and English. Maximum 2,000 characters (each Chinese character, letter, digit, or symbol counts as one character). Excess is auto-truncated. The `content` array must contain exactly one `text` object.
maxLength: 2000
example: Generate a tomato and egg stir-fry based on the style of image 1 and the background of image 2
image:
type: string
description: |-
Input image as a public URL (HTTP/HTTPS) or Base64-encoded string (`data:{mime_type};base64,{data}`).
**Image constraints:**
- Formats: JPEG, JPG, PNG (alpha channel not supported), BMP, WEBP.
- Resolution: Width and height each between 240 and 8,000 pixels.
- File size: Max 10 MB.
**Image quantity limits:**
- When `enable_interleave=false` (image editing): must input 1 to 4 images.
- When `enable_interleave=true` (interleaved text-image): can input 0 to 1 images.
example: https://cdn.wanx.aliyuncs.com/tmp/pressure/umbrella1.png
Wan26ImageParameters:
type: object
description: Image processing parameters.
properties:
negative_prompt:
type: string
description: |-
Negative prompt describing content you do NOT want in the image. Supports Chinese and English. Maximum 500 characters. Excess is auto-truncated.
Example: `Low resolution, low quality, deformed limbs, deformed fingers, oversaturated colors, wax-like appearance, no facial details, overly smooth skin, AI-looking artifacts, chaotic composition, blurry or distorted text.`
maxLength: 500
size:
type: string
description: |-
Output image resolution. Supports two methods: referencing input image proportions or directly specifying dimensions.
**Image editing mode** (`enable_interleave=false`):
- Method 1 (recommended): `1K` (default) or `2K`. Output total pixels close to 1280\*1280 or 2048\*2048, maintaining the aspect ratio of the last input image.
- Method 2: Specify `width*height` in pixels. Total pixels must be between [768\*768, 2048\*2048], aspect ratio [1:4, 4:1]. Actual values are multiples of 16.
**Interleaved text-image mode** (`enable_interleave=true`):
- Method 1 (default): References input image proportions. If total pixels <= 1280\*1280, output matches input. If > 1280\*1280, output scales to ~1280\*1280.
- Method 2: Specify `width*height`. Total pixels must be between [768\*768, 1280\*1280], aspect ratio [1:4, 4:1].
**Recommended resolutions:** 1280\*1280 (1:1), 800\*1200 (2:3), 1200\*800 (3:2), 960\*1280 (3:4), 1280\*960 (4:3), 720\*1280 (9:16), 1280\*720 (16:9), 1344\*576 (21:9).
example: 1K
enable_interleave:
type: boolean
description: |-
Controls image generation mode:
- `false` (default): Image editing mode. Supports multi-image input (1-4 images) and subject consistency generation. Can generate 1 to 4 result images.
- `true`: Interleaved text-image output mode. Supports 0-1 input images. Generates mixed content containing both text and images. **Requires** `stream=true` and `X-DashScope-Sse: enable` header.
default: false
n:
type: integer
description: |-
Number of images to generate. Behavior depends on mode:
- Image editing (`enable_interleave=false`): Range 1-4. Default: 4.
- Interleaved text-image (`enable_interleave=true`): Must be 1. Use `max_images` to control image count instead.
**Note:** `n` directly affects cost. Cost = unit price x number of successfully generated images.
minimum: 1
maximum: 4
default: 4
max_images:
type: integer
description: |-
Only effective in interleaved text-image mode (`enable_interleave=true`). Specifies the maximum number of images the model can generate in a single response. Range: 1-5. Default: 5. The actual number of generated images is determined by model inference and may be less than this value.
**Note:** `max_images` affects cost. Cost = unit price x number of successfully generated images.
minimum: 1
maximum: 5
default: 5
prompt_extend:
type: boolean
description: Only effective in image editing mode (`enable_interleave=false`). Enables intelligent prompt rewriting that optimizes and refines the positive prompt. The negative prompt is not affected.
default: true
stream:
type: boolean
description: Controls whether the response uses streaming output. In interleaved text-image mode (`enable_interleave=true`), you **must** set this to `true`.
default: false
watermark:
type: boolean
description: Adds a watermark label in the bottom-right corner of the image with fixed text "AI Generated".
default: false
seed:
type: integer
description: "Random number seed. Range: [0, 2147483647]. Same seed produces more consistent (but not identical) results. If omitted, a random seed is used."
minimum: 0
maximum: 2147483647
Wan26ImageResponse:
type: object
description: Wan2.6 image generation response.
example:
output:
choices:
- finish_reason: stop
message:
content:
- image: https://dashscope-result-intl.oss-cn-singapore.aliyuncs.com/xxx.png?Expires=xxx
type: image
role: assistant
finished: true
usage:
image_count: 1
input_tokens: 0
output_tokens: 0
size: 1376*768
total_tokens: 0
request_id: a3f4befe-cacd-49c9-8298-xxxxxx
properties:
output:
type: object
properties:
choices:
type: array
description: List of generated results.
items:
$ref: "#/components/schemas/Wan26ImageChoice"
finished:
type: boolean
description: Whether the generation has completed.
usage:
type: object
description: 'Usage statistics. Returned in the top-level `usage` field, at the same level as `output`. Read them as `response.usage["image_count"]`. The `output` object does not carry statistics: `response.output.usage` is returned as `{}` and contains no `image_count`.'
properties:
image_count:
type: integer
description: Number of images generated.
input_tokens:
type: integer
description: Number of input tokens consumed.
output_tokens:
type: integer
description: Number of output tokens consumed.
size:
type: string
description: Resolution of the generated image(s).
total_tokens:
type: integer
description: Total tokens consumed (input + output).
request_id:
type: string
description: Unique request identifier for tracing and troubleshooting.
example: a3f4befe-cacd-49c9-8298-xxxxxx
Wan26ImageChoice:
type: object
properties:
finish_reason:
type: string
description: "`stop` means normal completion. `null` indicates streaming is still in progress."
example: stop
message:
type: object
properties:
role:
type: string
description: Always `assistant`.
enum:
- assistant
content:
type: array
description: Response content array containing generated image URLs and/or text (in interleaved mode).
items:
$ref: "#/components/schemas/Wan26ImageResponseContentPart"
Wan26ImageResponseContentPart:
type: object
description: Content part in the response. Can be an image or text.
properties:
type:
type: string
description: "Content type: `image` or `text`."
enum:
- image
- text
image:
type: string
description: URL of the generated image (PNG). **Valid for 24 hours.** Download promptly.
text:
type: string
description: Text content (only present in interleaved text-image output mode).
Wan26ImageAsyncRequest:
type: object
description: Request body for async Wan2.6 image generation/editing task.
required:
- model
- input
properties:
model:
type: string
description: Model name. Set to `wan2.6-image`.
enum:
- wan2.6-image
example: wan2.6-image
input:
type: object
required:
- messages
description: Input data containing the messages array.
properties:
messages:
type: array
description: "Array of request content. Only single-turn conversations are supported. Provide one message with `role: user`."
minItems: 1
maxItems: 1
items:
$ref: "#/components/schemas/Wan26ImageMessage"
parameters:
$ref: "#/components/schemas/Wan26ImageParameters"
AsyncTaskSubmitResponse:
type: object
description: Response returned when an asynchronous task is created successfully.
example:
output:
task_status: PENDING
task_id: 0385dc79-5ff8-4d82-bcb6-xxxxxx
request_id: 4909100c-7b5a-9f92-bfe5-xxxxxx
properties:
request_id:
type: string
description: Unique request identifier for troubleshooting.
output:
type: object
properties:
task_id:
type: string
description: The task identifier. Use this to query the task status via `GET /tasks/{task_id}`. Valid for 24 hours.
task_status:
type: string
description: The initial task status. Typically `PENDING`.
enum:
- PENDING
Wan26TaskStatusResponse:
type: object
description: Response returned when querying async task status.
properties:
request_id:
type: string
description: Unique request identifier for troubleshooting.
output:
type: object
description: Task output information.
properties:
task_id:
type: string
description: The task identifier.
task_status:
type: string
description: The current task status.
enum:
- PENDING
- RUNNING
- SUCCEEDED
- FAILED
- CANCELED
- UNKNOWN
submit_time:
type: string
description: "Task submission time. Time is in UTC+8. Format: `YYYY-MM-DD HH:mm:ss.SSS`."
scheduled_time:
type: string
description: "Time when the task started running. Format: `YYYY-MM-DD HH:mm:ss.SSS`."
end_time:
type: string
description: "Time when the task completed. Format: `YYYY-MM-DD HH:mm:ss.SSS`."
finished:
type: boolean
description: Whether the task has completed.
choices:
type: array
description: List of generated results. Returned when `task_status` is `SUCCEEDED`.
items:
$ref: "#/components/schemas/Wan26ImageChoice"
usage:
type: object
description: 'Usage statistics. Counts only successful results. Returned in the top-level `usage` field, at the same level as `output`. Read them as `response.usage["image_count"]`, where `image_count` is the total number of images generated by the task. The `output` object does not carry statistics: `response.output.usage` is returned as `{}` and contains no `image_count`.'
properties:
image_count:
type: integer
description: Number of images generated.
input_tokens:
type: integer
description: Number of input tokens consumed.
output_tokens:
type: integer
description: Number of output tokens consumed.
size:
type: string
description: Resolution of the generated image(s).
total_tokens:
type: integer
description: Total tokens consumed (input + output).
code:
type: string
description: Error code. Returned only when the request fails.
message:
type: string
description: Detailed error message. Returned only when the request fails.
DashScopeErrorResponse:
type: object
description: DashScope API error response.
example:
request_id: a4d78a5f-655f-9639-8437-xxxxxx
code: InvalidParameter
message: num_images_per_prompt must be 1
properties:
request_id:
type: string
description: Unique request identifier.
code:
type: string
description: Error code (e.g., `InvalidParameter`, `Throttling`, `InvalidApiKey`).
example: InvalidParameter
message:
type: string
description: Human-readable error message.
example: num_images_per_prompt must be 1