Seedream 5.0 Pro Image to Image API

POST /v1/tasks

All models are called through the Unified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name	seedream-5.0-pro/image-to-image
Type	Image generation (image-to-image)
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

HiAPI flagship image editing model: up to 10 reference images for consistent edits and composites, with 1K/2K resolution tiers.

Production guidance

For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Consistency-preserving edits

Restyle scenes while keeping layout, subjects and in-image text — state what must stay unchanged in the instruction (verified: rainy-to-sunny street edit kept signage text and people intact).

promptimage_urls

Multi-reference composites

Up to 10 reference images to merge people, products and scenes with strong subject consistency; state each image's role explicitly.

image_urls

Tiered cost control

1K outputs 1K images at $0.06/image; 2K outputs 2K images at $0.10/image. Billing is tiered by resolution.

resolution

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": "seedream-5.0-pro/image-to-image",
  "input": {
    "prompt": "Turn this rainy cyberpunk night market into a bright sunny morning scene, keep the same street layout and glowing storefront sign text unchanged",
    "image_urls": [
      "https://static.hiapi.ai/previews/seedream-5.0-pro/2026/07/09/1783562443968-9f2774efdd1a6516-example-i2i-in.webp"
    ],
    "aspect_ratio": "16:9",
    "resolution": "2K",
    "output_format": "png"
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "seedream-5.0-pro/image-to-image",
  "input": {
    "prompt": "Turn this rainy cyberpunk night market into a bright sunny morning scene, keep the same street layout and glowing storefront sign text unchanged",
    "image_urls": [
      "https://static.hiapi.ai/previews/seedream-5.0-pro/2026/07/09/1783562443968-9f2774efdd1a6516-example-i2i-in.webp"
    ],
    "aspect_ratio": "16:9",
    "resolution": "2K",
    "output_format": "png"
  }
}
''')

# 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": "seedream-5.0-pro/image-to-image",
  "input": {
    "prompt": "Turn this rainy cyberpunk night market into a bright sunny morning scene, keep the same street layout and glowing storefront sign text unchanged",
    "image_urls": [
      "https://static.hiapi.ai/previews/seedream-5.0-pro/2026/07/09/1783562443968-9f2774efdd1a6516-example-i2i-in.webp"
    ],
    "aspect_ratio": "16:9",
    "resolution": "2K",
    "output_format": "png"
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value seedream-5.0-pro/image-to-image.

example seedream-5.0-pro/image-to-image

input object required

Business parameters. Put Seedream 5.0 Pro Image to Image-specific configuration here.

prompt string required

Editing or generation instruction describing the desired output, 3-4000 characters.

image_urls string[] required

Reference image URLs (1-10) for single-image edits or multi-reference composites. JPG/PNG/WebP up to 10MB each; SVG is not supported.

aspect_ratio enum required

Width-height ratio of the generated image.

default 1:1 enum: 1:14:33:416:99:162:33:221:9

resolution enum required

Output resolution tier. 1K outputs a 1K image at $0.06/image; 2K outputs a 2K image at $0.10/image.

default 2K enum: 1K2K

output_format enum optional

Output image format.

default png enum: pngjpeg

callback object optional

Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.

url string required

Required when callback is set; 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

Rainy night to sunny morning (layout and text preserved)

16:9 / high — restyles the scene while keeping street layout and signage text.

Request body

{
  "model": "seedream-5.0-pro/image-to-image",
  "input": {
    "prompt": "Turn this rainy cyberpunk night market into a bright sunny morning scene, keep the same street layout and the glowing storefront sign text unchanged",
    "image_urls": [
      "https://static.hiapi.ai/previews/seedream-5.0-pro/2026/07/09/1783562443968-9f2774efdd1a6516-example-i2i-in.webp"
    ],
    "aspect_ratio": "16:9",
    "resolution": "2K"
  }
}

Multi-reference composite (person + scene)

Two reference images merged into one; state each image's role in the instruction.

Request body

{
  "model": "seedream-5.0-pro/image-to-image",
  "input": {
    "prompt": "Place the person from image 1 into the scene from image 2, keeping the person's face and outfit consistent with image 2's lighting",
    "image_urls": [
      "https://example.com/person.jpg",
      "https://example.com/scene.jpg"
    ],
    "aspect_ratio": "16:9",
    "resolution": "2K"
  }
}

Getting the result

The response returns a taskId immediately without waiting for generation to finish.
In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
When status=success, download the generated image from output[].url.
When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

What are the reference image requirements? How many can I pass?

1-10 image URLs in JPG/PNG/WebP, up to 10MB each; SVG is not supported. For multi-reference composites, state each image's role in the instruction for more stable results.

Can edits preserve the original text and layout?

Yes. Spell out what must stay unchanged in the instruction, e.g. "keep the street layout and the storefront sign text unchanged" — in our tests a rainy-to-sunny edit kept signage text and people intact.

Do basic and high cost the same?

1K outputs a 1K image at $0.06/image; 2K outputs a 2K image at $0.10/image. Billing is tiered by resolution, so iterate with 1K and switch to 2K for final delivery. View pricing