Black Forest Labs

FLUX.2 Klein 4B

flux-2-klein-4b/image-to-image

A 4-billion-parameter distilled small model that unifies text-to-image generation and image editing, with end-to-end inference as fast as under 1 second and runs on about 13GB of VRAM

flux-2-klein-4b/image-to-image flux-2-klein-4b/text-to-image

Try flux-2-klein-4b/image-to-image

Input

Showcases

View all showcases

Output

image

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

Pricing

flux-2-klein-4b/image-to-image per image

Specifications	Unit Price
0.25 MP	$0.00608
0.5 MP	$0.00643
1 MP	$0.00715
2 MP	$0.00858
4 MP	$0.01143

Overview

FLUX.2 klein 4B is a 4-billion-parameter image editing model released by Black Forest Labs. It accepts a single reference image as input and performs controlled modifications to the original image via instructions. Developers can specify the output resolution (0.25–4 MP), aspect ratio, format, and compression quality, and fix the random seed to reproduce results. It is suitable for developers who need to quickly validate image editing workflows, and for teams integrating reference-image redrawing into application prototypes.

Key Highlights

Single-reference-image instruction editing — Just provide one reference image and an editing prompt to complete targeted modifications to the original image, with no need to build an additional editing pipeline.
Fine-grained control over output parameters — Supports specifying resolution (0.25–4 MP), aspect ratio, output format, and compression quality, and a seed can be used to reproduce identical results.
Compact distilled model — With 4B parameters distilled from a larger FLUX.2 base, it lowers the deployment barrier while retaining understanding of lighting and materials.

Capabilities

Instruction-based image editing: Input a reference image and a prompt, and the model modifies the reference image as described, outputting edited results that can be used directly in downstream workflows.

Output resolution and ratio control: Resolution can be selected between 0.25 MP and 4 MP, and the aspect ratio can match the original image or be set to common specified ratios to meet the requirements of different display placements.

Adjustable format and quality: Supports webp, jpg, and png output, and compression quality (0–100) can be set, making it easy to trade off between image quality and file size.

Reproducible results: By setting the seed parameter, the same editing result can be reproduced under identical inputs, facilitating debugging and consistency verification of batch tasks.

Use Cases

Quick validation of image editing workflows by developers — Test editing effects with a single reference image plus a prompt, and produce reproducible sample images to evaluate whether to integrate into a production pipeline.
Style-consistent redrawing of product images — Based on a product reference image, adjust style or details according to instructions and output images with uniform specifications for display or asset libraries.
Real-time interactive editing prototypes — Integrate reference-image redrawing capabilities into interactive tools and output preview images as low as 0.25 MP for instant feedback.

Limitations and Model Selection Advice

Only a single reference image is accepted; multiple images cannot be constrained simultaneously. Input images exceeding 4 MP will be compressed to 4 MP, and the SVG format is not supported. As a small 4B distilled model, its capability ceiling is constrained by scale; for complex edits or scenarios requiring high-fidelity detail restoration, evaluating larger models is recommended. Independent horizontal benchmark data is currently lacking, so the full license and usage terms should be verified before commercial use.

Frequently asked questions

View all FAQs →

What is FLUX.2 [klein] 4B best for?

It fits batch drafts, product concepts, social assets, and cost-sensitive iteration. Move to 9B when realism, typography, and fine detail matter more.
How should I choose between 0.25 and 4 MP?

Start with 0.25 or 0.5 MP for drafts, use 1 MP for typical web assets, and select 2 or 4 MP for larger output. Price changes by megapixel tier.
Which aspect ratios are supported?

1:1, 16:9, 9:16, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 21:9, and 9:21.
How can I reproduce a composition direction?

Keep seed, prompt, ratio, megapixel tier, and output settings fixed while changing one variable at a time.

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: flux-2-klein-4b/image-to-image

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for flux-2-klein-4b/image-to-image and route default — see the parameter table below.

seedintegerOptional

Random seed used to control the reproducibility of generation results; takes an integer. With the same input, the same seed produces consistent results.

promptstringRequired

Prompt describing the edit to perform on the reference image; takes a string.

image_urlsarrayRequiredminItems 1maxItems 1

Array of reference images, where each element is the URL of a single reference image; supports jpeg, png, and webp formats, does not support svg; images larger than 4 MP will be compressed to 4 MP.

Array [ string ]

resolutionstringOptionalDefault: "1 MP"

Output image resolution, specifying the output size in megapixels; defaults to 1 MP.

Options:0.25 MP0.5 MP1 MP2 MP4 MP

aspect_ratiostringOptionalDefault: "match_input_image"

Aspect ratio of the output image; when set to match_input_image, the original aspect ratio of the reference image is preserved; defaults to match_input_image.

Options:match_input_image1:116:99:163:22:34:33:4

Show all (4)

5:44:521:99:21

output_formatstringOptionalDefault: "jpg"

Output format of the generated image; defaults to jpg.

Options:webpjpgpng

output_qualityintegerOptionalDefault: 95min 0max 100

Compression quality of the output image, applies only to jpg and webp formats; takes an integer, defaults to 95.

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": "flux-2-klein-4b/image-to-image",
  "input": {
    "prompt": "…",
    "image_urls": "…",
    "resolution": "1 MP",
    "aspect_ratio": "match_input_image",
    "output_format": "jpg",
    "output_quality": 95
  }
}'

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: "flux-2-klein-4b/image-to-image",
    input: {
      "prompt": "…",
      "image_urls": "…",
      "resolution": "1 MP",
      "aspect_ratio": "match_input_image",
      "output_format": "jpg",
      "output_quality": 95
    }
  }),
});
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": "flux-2-klein-4b/image-to-image",
        "input": {
          "prompt": "…",
          "image_urls": "…",
          "resolution": "1 MP",
          "aspect_ratio": "match_input_image",
          "output_format": "jpg",
          "output_quality": 95
        }
    },
)
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"
    }
  }
}