Seedream 4.5 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-4.5/image-to-image
Type	Image generation (image-to-image)
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

Seedream 4.5 image editing: unified generation-editing with up to 14 references for edits, scene swaps and composites, consistent subjects and text, flat per-image billing.

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

Multi-reference composition

Up to 14 reference images per request, referenced by order for composites and consistency.

image_urlsprompt

Scene & season edits

Swap backgrounds, seasons and mood while subjects and in-image text stay intact.

prompt

Unified generation-editing

Edited outputs keep the same generation-tier quality — no fidelity loss.

promptresolution

Per-image billing

Flat rate independent of reference count and 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-4.5/image-to-image",
  "input": {
    "prompt": "Change the season to heavy winter snowfall: snow accumulating on the signboard and street, warm lantern glow contrasting the cold blue night, keep the storefront layout and calligraphy text unchanged",
    "image_urls": [
      "https://static.hiapi.ai/gallery/2026/07/220f90f15f629434.jpg"
    ],
    "aspect_ratio": "3:4",
    "resolution": "2K"
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "seedream-4.5/image-to-image",
  "input": {
    "prompt": "Change the season to heavy winter snowfall: snow accumulating on the signboard and street, warm lantern glow contrasting the cold blue night, keep the storefront layout and calligraphy text unchanged",
    "image_urls": [
      "https://static.hiapi.ai/gallery/2026/07/220f90f15f629434.jpg"
    ],
    "aspect_ratio": "3:4",
    "resolution": "2K"
  }
}
''')

# 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-4.5/image-to-image",
  "input": {
    "prompt": "Change the season to heavy winter snowfall: snow accumulating on the signboard and street, warm lantern glow contrasting the cold blue night, keep the storefront layout and calligraphy text unchanged",
    "image_urls": [
      "https://static.hiapi.ai/gallery/2026/07/220f90f15f629434.jpg"
    ],
    "aspect_ratio": "3:4",
    "resolution": "2K"
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value seedream-4.5/image-to-image.

example seedream-4.5/image-to-image

input object required

Business parameters. Put Seedream 4.5 Image to Image-specific configuration here.

prompt string required

Editing instruction describing the desired output. Max 3000 characters.

image_urls string[] required

Input reference images (1-14). Public URLs; jpeg/png/webp (SVG not supported), max 10MB each.

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 image resolution. 2K for standard quality, 4K for ultra HD.

default 2K enum: 2K4K

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

Season change (snowy ramen shop)

Tested: storefront and calligraphy preserved, scene turned into a snowy winter night.

Request body

{
  "model": "seedream-4.5/image-to-image",
  "input": {
    "prompt": "Change the season to heavy winter snowfall: snow accumulating on the signboard and street, warm lantern glow contrasting the cold blue night, keep the storefront layout and calligraphy text unchanged",
    "image_urls": [
      "https://static.hiapi.ai/gallery/2026/07/220f90f15f629434.jpg"
    ],
    "aspect_ratio": "3:4",
    "resolution": "2K"
  }
}

Two-image composite (4K)

Tested: product from image 1 placed into the scene of image 2 with matched lighting.

Request body

{
  "model": "seedream-4.5/image-to-image",
  "input": {
    "prompt": "Place the ice-carved perfume bottle from image 1 onto the rocky ledge beside the snow leopard in image 2, matching the dawn alpine lighting and cold atmosphere, seamless composite, keep both subjects photorealistic",
    "image_urls": [
      "https://static.hiapi.ai/gallery/2026/07/c2a64356e31c2205.jpg",
      "https://static.hiapi.ai/gallery/2026/07/5d186d631d3ba69a.jpg"
    ],
    "aspect_ratio": "16:9",
    "resolution": "4K"
  }
}

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

How many reference images?

1-14 (jpeg/png/webp, up to 10MB each), referenced by order in the prompt.

Does reference count affect price?

No — billing is per output image, 2K/4K at the same rate.

Seedream 4.5 edit vs FLUX.2 edit?

Both are multi-reference editors: Seedream takes up to 14 refs and preserves Chinese text well; FLUX.2 takes up to 8 with strong photoreal consistency.