FLUX.2 [klein] 9B 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	flux-2-klein-9b/image-to-image
Type	Image generation (image-to-image)
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

FLUX.2 [klein] 9B image-to-image API for fast four-step single-reference editing with stronger detail preservation, text rendering, and commercial finish.

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

Premium commercial retouching

Prioritizes material detail, lighting, and preservation for hero advertising images.

image_urlsprompt

Text and fine-detail edits

The 9B route is a better fit when in-image text, marks, and complex local detail need stronger rendering.

prompt

Fast four-step generation

Defaults to four inference steps for a practical speed-quality balance.

num_inference_steps

Common marketing ratios

Supports 1:1, 4:3, 3:4, 16:9, and 9:16 for product cards, banners, and vertical ads.

aspect_ratio

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": "flux-2-klein-9b/image-to-image",
  "input": {
    "prompt": "Keep the subject and camera angle. Refine the image into a premium commercial advertisement with richer material detail and natural lighting.",
    "image_urls": [
      "https://static.hiapi.ai/gallery/2026/07/f35f947e46888163.png"
    ],
    "aspect_ratio": "16:9",
    "seed": 20260727,
    "num_inference_steps": 4,
    "output_format": "webp"
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "flux-2-klein-9b/image-to-image",
  "input": {
    "prompt": "Keep the subject and camera angle. Refine the image into a premium commercial advertisement with richer material detail and natural lighting.",
    "image_urls": [
      "https://static.hiapi.ai/gallery/2026/07/f35f947e46888163.png"
    ],
    "aspect_ratio": "16:9",
    "seed": 20260727,
    "num_inference_steps": 4,
    "output_format": "webp"
  }
}
''')

# 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": "flux-2-klein-9b/image-to-image",
  "input": {
    "prompt": "Keep the subject and camera angle. Refine the image into a premium commercial advertisement with richer material detail and natural lighting.",
    "image_urls": [
      "https://static.hiapi.ai/gallery/2026/07/f35f947e46888163.png"
    ],
    "aspect_ratio": "16:9",
    "seed": 20260727,
    "num_inference_steps": 4,
    "output_format": "webp"
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value flux-2-klein-9b/image-to-image.

example flux-2-klein-9b/image-to-image

input object required

Business parameters. Put FLUX.2 [klein] 9B Image to Image-specific configuration here.

prompt string required

Describe the edits to apply to the reference image.

image_urls string[] required

One reference image. Supports jpeg, png, or webp; svg is not supported. Input images are processed at about 1 MP.

aspect_ratio enum optional

Aspect ratio for the generated image.

default 1:1 enum: 1:14:33:416:99:16

seed integer optional

Random seed for reproducible generation.

num_inference_steps integer optional

Number of inference steps. Must be an integer from 4 to 8; defaults to 4.

default 4

output_format enum optional

Format of the generated image.

default png enum: jpegpngwebp

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

Premium commercial refinement (16:9)

Uses one public reference image, keeps the subject and angle, and enhances materials, natural lighting, and commercial polish.

Request body

{
  "model": "flux-2-klein-9b/image-to-image",
  "input": {
    "prompt": "Keep the subject and camera angle. Refine the image into a premium commercial advertisement with richer material detail and natural lighting.",
    "image_urls": [
      "https://static.hiapi.ai/gallery/2026/07/f35f947e46888163.png"
    ],
    "aspect_ratio": "16:9",
    "seed": 20260727,
    "num_inference_steps": 4,
    "output_format": "webp"
  }
}

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 does 9B image-to-image support?

HiAPI currently exposes one reference image. image_urls must be an array containing one public image URL.

How is 9B image-to-image billed?

It is currently billed at a fixed per-output-image price, independent of aspect_ratio, output_format, or inference steps. See the live HiAPI pricing page for current rates. View live pricing

Why does 9B cost more than 4B?

9B targets stronger final-image quality, detail preservation, text rendering, and complex edits. 4B is better for cost-sensitive, high-volume iteration.

What are the input-image limits?

jpeg, png, and webp are supported; svg is not supported. Input images are processed at about 1 MP. Use a stable, publicly accessible HTTPS URL.