Alibaba

Wan 2.7 Image

wan2.7-image-standard

An image generation and editing model launched by Alibaba that integrates text-to-image, multi-reference image composition, and instruction-based editing into a single workflow, with support for long-text rendering and brand color control

wan2.7-image-standard wan2.7-image/text-to-image

Try wan2.7-image-standard

Input

Showcases

View all showcases

Output

image

Fill in the parameters and run — results show up here.

Pricing

wan2.7-image-standard per image

Specifications	Unit Price
1K	$0.0345
2K	$0.0345

Positioning Overview

Wan 2.7 Image Standard Edition is an image generation and editing model launched by Alibaba, offering text-to-image and image-to-image capabilities through the unified HiAPI.ai interface. It supports up to 9 reference images as input, two resolution tiers (1K/2K), a variety of aspect ratios, and random seed control, making it suitable for developers who need complete sets of visual outputs or instruction-based image modifications, in scenarios such as brand materials, e-commerce image collections, and concept design.

Key Highlights

Unified text-to-image and reference-image editing — the same model can generate images directly from text or perform composition and instruction-based modifications based on up to 9 reference images, reducing tool switching.
Multi-reference-image input maintains consistency — supports up to 9 public images as references; the output aspect ratio follows the last reference image, making it easy to produce complete sets of serialized visuals.
Controllable resolution and aspect-ratio parameters — choose 1K or 2K output; for text-to-image, multiple aspect ratios from 1:1 to 8:1 are supported, making it easy to fit sizes to display placements.

Capability Description

Text-to-image: generate an image from a text prompt alone; you can specify the resolution tier and aspect ratio, and prompts of up to 5,000 characters are supported, making it suitable for getting usable visuals directly from conceptual descriptions.

Reference-image instruction editing: pass in a public URL of a reference image or an image to be edited, describe the modification requirements in natural language, and the model outputs the edited image, with the aspect ratio following the last reference image.

Multi-image reference composition: accepts up to 9 reference images, each no larger than 20 MB, supporting JPEG, PNG, BMP, and WebP; visual elements from multiple reference images can be fused into a single output.

Resolution and seed control: choose a 1K or 2K output tier; a random seed from 0–2147483647 can yield relatively stable results under the same input, facilitating reproduction and batch iteration.

Applicable Scenarios

Marketers producing complete sets of campaign visual materials — input brand descriptions and multiple style reference images to produce banners, accompanying images, and other assets with a consistent tone for campaign landing pages and social media placements.
E-commerce operations: product and scene image production — upload product photos and describe scene transformation requirements to obtain product scene images that meet display specifications, for use in product detail pages and advertising materials.
Designers: concept sketches and storyboard generation — use text descriptions or reference-image input to generate storyboard sketches and character concept art for early-stage proposal discussions and storyboard drawing.
Developers: batch image generation API integration — call through the unified HiAPI.ai interface to embed text-to-image or image-to-image capabilities into your own workflows and generate 1K/2K image assets on demand.

Limitations and Selection Advice

The Standard Edition's output resolution is limited to 1K and 2K, with no higher tiers available; if you need higher resolution or stronger composition stability, consider the Pro version in the same series. Reference images must be publicly accessible URLs, each no larger than 20 MB; once reference images are uploaded, the aspect ratio is determined by the last reference image and can no longer be specified via parameters. A fixed seed only makes results relatively stable and does not guarantee exact reproduction. For scenarios involving long-text layout or precise brand-color control, it is recommended to validate results with a small batch of samples before scaling up usage.

What's new

View changelog →

New model wan2.7-image-standard image generation model now available Nov 3, 2026

Frequently asked questions

View all FAQs →

Which unusual ratios does Wan 2.7 Image support?

Alongside common ratios, it supports 21:9, 8:1, and 1:8 for extreme wide or tall output.
What does Thinking Mode do?

It adds latency to improve reasoning and composition for complex prompts. Leave it off for fast drafts.
How should I choose 1K, 2K, or 4K?

Validate direction at 1K or 2K, then move to 4K for larger final output. Current page pricing is flat per image.
Does it accept references?

No. This model ID is text-to-image only.

Create a generation task

POST https://api.hiapi.ai/v1/tasks

Headers

AuthorizationstringRequired

Account API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key

Content-TypestringOptional

The request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.

Idempotency-KeystringOptional

Idempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.

Idempotency key

On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.

Body

modelstringRequired

Current fixed value: wan2.7-image-standard

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for wan2.7-image-standard and route default — see the parameter table below.

seedintegerOptionalmin 0max 2147483647

Random seed, value range 0–2147483647; fixing the seed makes results relatively stable, random if not provided.

promptstringRequiredminLength 1maxLength 5000

Describe the image to generate, or explain what modifications to make to the reference image; Chinese or English both accepted, maximum 5000 characters.

image_urlsarrayOptionalminItems 1maxItems 9

Array of public URLs of reference images or images to edit, up to 9 images; omit for text-to-image; supports JPEG, PNG, BMP, WebP, each file no larger than 20 MB, side length 240–8000 pixels, aspect ratio 1:8–8:1. When images are provided, the output canvas follows the last reference image.

Array [ string ]

resolutionstringOptionalDefault: "2K"

Output resolution tier, options are 1K or 2K; 1K is roughly 1024² and 2K roughly 2048² in total pixel magnitude; default 2K.

Options:1K2K

aspect_ratiostringOptionalDefault: "1:1"

Output canvas, only effective when no reference image is uploaded; once a reference image is uploaded the canvas is determined by the reference image and no setting is needed. Default 1:1.

Options:1:116:94:321:93:49:168:11:8

callbackobjectOptional

Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.

Callbacks (Webhook)

Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.

urlstringRequired

Required when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.

whenstringOptionalDefault: "final"

Only final is supported today — notified on both success and fail.

Options:final

storagestringOptionalDefault: "temp"

Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.

Options:temppersistent

Request examples

# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer $HIAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan2.7-image-standard",
  "input": {
    "prompt": "…",
    "resolution": "2K",
    "aspect_ratio": "1:1"
  }
}'

const res = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "wan2.7-image-standard",
    input: {
      "prompt": "…",
      "resolution": "2K",
      "aspect_ratio": "1:1"
    }
  }),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } }

import os, requests

res = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
    json={
        "model": "wan2.7-image-standard",
        "input": {
          "prompt": "…",
          "resolution": "2K",
          "aspect_ratio": "1:1"
        }
    },
)
print(res.json())  # { code, message, data: { taskId } }

200 OK

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
  }
}

400 Bad Request

{
  "code": 400,
  "message": "invalid request",
  "data": null,
  "error_code": "INVALID_REQUEST"
}

Get task detail

GET https://api.hiapi.ai/v1/tasks/:id

Response fields

taskIdstringRequired

Task ID, always prefixed with tk-hiapi-.

modelstringRequired

Resolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.

routestringOptional

Present only when the task was submitted with an explicit route parameter; echoes the submitted value.

statusstringRequired

Task status.

Status values

queued Queued, not started yet. handling Being processed. archiving Processing finished, artifacts being prepared. success Terminal: completed, artifacts available (output returned). fail Terminal: failed (error returned). After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.

creatednumberRequired

Task creation time (Unix seconds).

completednumberRequired

Unix seconds when the task reached a terminal state; fixed to 0 while not terminal.

outputarrayOptional

Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).

Array [ object ]

Array items

urlstringRequired

Artifact URL, directly downloadable.

typestringRequired

Current possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.

expireAtnumberRequired

Unix seconds until which the artifact remains accessible; download or transfer before it expires.

errorobjectOptional

Present only when status == fail.

codestringRequired

Business error code.

messagestringRequired

Error description.

Response examples

Success

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
    "model": "happyhorse-1-0",
    "status": "success",
    "created": 1777282033,
    "completed": 1777282099,
    "output": [
      {
        "url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
        "type": "video",
        "expireAt": 1777886899
      }
    ]
  }
}

Processing (non-terminal)

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "archiving",
    "created": 1777282033,
    "completed": 0
  }
}

Failed

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "fail",
    "created": 1777282033,
    "completed": 1777282099,
    "error": {
      "code": "TASK_FAILED",
      "message": "task failed"
    }
  }
}