Wan 2.7 Image Standard

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

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name	wan2.7-image-standard
Type	Text-to-image / Reference editing
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

Wan 2.7 Image Standard covers text-to-image and reference-based editing (up to nine references) at 1K/2K through the unified asynchronous API.

Production guidance

Prefer callback.url for terminal notifications in production; use GET /v1/tasks/:id for local debugging or compensation.
For reference editing, put the source image first and append additional references in order; refer to them by index in the prompt.
Do not rely on aspect_ratio when references are supplied; the ratio follows the last reference image.

Best suited for

Generation and editing in one ID

Cover prompt-only generation and reference-based editing without switching routes.

promptimage_urls

Chinese and English prompts

Both languages work, including bilingual posters and signage.

prompt

Flexible ratios with 1K/2K

Eight ratios cover square, landscape, portrait, and ultra-wide banners; use 1K for early iterations and 2K for finals.

aspect_ratioresolution

Repeatable iteration

Fix the seed while comparing prompt variations to converge on a direction.

seed

Request parameters

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

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan2.7-image-standard",
  "input": {
    "prompt": "A quiet Shanghai lane at blue hour after rain, a small ceramic studio with warm paper lanterns, glazed teapots in the window, wet stone reflections, a bicycle leaning against the wall, cinematic 35mm photograph, high detail",
    "aspect_ratio": "16:9",
    "resolution": "1K",
    "seed": 20261019
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "wan2.7-image-standard",
  "input": {
    "prompt": "A quiet Shanghai lane at blue hour after rain, a small ceramic studio with warm paper lanterns, glazed teapots in the window, wet stone reflections, a bicycle leaning against the wall, cinematic 35mm photograph, high detail",
    "aspect_ratio": "16:9",
    "resolution": "1K",
    "seed": 20261019
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "wan2.7-image-standard",
  "input": {
    "prompt": "A quiet Shanghai lane at blue hour after rain, a small ceramic studio with warm paper lanterns, glazed teapots in the window, wet stone reflections, a bicycle leaning against the wall, cinematic 35mm photograph, high detail",
    "aspect_ratio": "16:9",
    "resolution": "1K",
    "seed": 20261019
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value wan2.7-image-standard.

example wan2.7-image-standard

input object required

Model-specific parameter object.

prompt string required

Describe the image to generate, or the changes to apply to the references. Chinese and English are both supported; 1–5,000 characters.

image_urls string[] optional

Public URLs of reference or source images, up to nine; omit them for text-to-image. Supports JPEG, PNG, BMP, and WebP up to 20 MB each, 240–8,000 px per side, aspect ratio 1:8–8:1. With images, the output ratio follows the last reference.

aspect_ratio enum optional

Output aspect ratio for prompt-only generation. When references are supplied, the ratio follows the last image and this field is not needed.

default 1:1 enum: 1:116:94:321:93:49:168:11:8

resolution enum optional

Output resolution tier: roughly 1024² total pixels for 1K and 2048² for 2K.

default 2K enum: 1K2K

seed integer optional

Random seed, 0–2147483647. A fixed seed keeps results relatively stable, but identical output is not guaranteed.

callback object optional

Optional callback configuration. In production, pass callback.url to receive terminal task notifications.

url string required

HTTPS URL that receives terminal task notifications.

example https://your-domain.com/hiapi/callback

when enum optional

Callback trigger timing. Use final.

default final enum: final

Example requests

Golden text-to-image example (1K, 16:9)

Same source as the DEV golden task: a rain-washed lane at blue hour with warm paper lanterns, glazed teapots, wet stone reflections, and a bicycle.

Request body

{
  "model": "wan2.7-image-standard",
  "input": {
    "prompt": "A quiet Shanghai lane at blue hour after rain, a small ceramic studio with warm paper lanterns, glazed teapots in the window, wet stone reflections, a bicycle leaning against the wall, cinematic 35mm photograph, high detail",
    "aspect_ratio": "16:9",
    "resolution": "1K",
    "seed": 20261019
  }
}

Reference editing (single reference)

Use the same golden output as the source and ask for a morning scene while keeping the facade, bicycle, and lane structure.

Request body

{
  "model": "wan2.7-image-standard",
  "input": {
    "prompt": "Turn the reference into a clear morning scene: keep the studio facade, the bicycle, and the lane structure; replace the paper lanterns with open shutters and add soft morning sunlight and long shadows",
    "image_urls": [
      "https://dev-static.hiapi.ai/admin-assets/2026/10/19/1792422144916-ff0acf94218f32b6-golden.webp"
    ],
    "resolution": "1K"
  }
}

Getting the result

A successful submission returns a taskId immediately.
In production, prefer callback.url; for local debugging, poll GET /v1/tasks/:id.
When status=success, download the image from output[].url.
If status=fail, correct the request from the error message instead of retrying the same invalid input.

FAQ

How is Wan 2.7 Image different from Pro?

The standard tier supports 1K and 2K for text-to-image and reference editing. Use Wan 2.7 Image Pro when you need 4K text-to-image.

Does it support reference-based editing?

Yes. Pass up to nine public image URLs and describe the changes in the prompt; omit the images for prompt-only generation.

Can I set an aspect ratio when references are attached?

The output follows the last reference image, so aspect_ratio is not needed. For prompt-only generation, choose one of eight ratios.

How many images does one request return?

The current HiAPI contract returns one image per request, billed per successfully generated image. View live pricing

Which reference formats and sizes are supported?

JPEG, PNG, BMP, and WebP up to 20 MB each; each side must be 240–8,000 px and the aspect ratio within 1:8–8:1.

How do I reproduce a result?

Keep the seed, prompt, reference order, ratio, and resolution fixed. The same settings make results relatively stable, not guaranteed identical.