# FLUX.2 [klein] 4B Base LoRA · Edit API

> يحرر ما يصل إلى 4 صور باستخدام klein 4B Base ودعم LoRA وprompt سلبي و4 إلى 50 خطوة

تحرير الصور باستخدام نموذج klein 4B Base عبر موجّه وما يصل إلى 4 صور في `image_urls`. يمكن تطبيق ما يصل إلى 3 من LoRA عبر `loras`. يدعم `negative_prompt` و`guidance_scale` (الافتراضي 5، من 0 إلى 20)، ومن 4 إلى 50 خطوة، وإعداد `acceleration`. يتبع حجم المخرج المدخل ما لم يتم ضبط `image_size`.

- Model id: `flux-2/klein/4b/base/edit/lora`
- Made by: Black Forest Labs
- Category: Image Editing
- Output: image
- Price per megapixel: $0.016 / megapixel (cheapest run $0.016 (16 API credits))
- Run: `POST https://api.doitong.com/v1/run/flux-2/klein/4b/base/edit/lora`
- Quote: `POST https://api.doitong.com/v1/quote/flux-2/klein/4b/base/edit/lora`
- Docs page: https://doitong.com/ar/developers/models/flux-2/klein/4b/base/edit/lora

## Pricing

Price: **$0.016 / megapixel**. Price per megapixel: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $0.032 = 32 API credits (2 MP × $0.016).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/flux-2/klein/4b/base/edit/lora` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  |  | موجّه يصف تعديلات الصورة. |
| `negative_prompt` |  | string | no | `` |  | موجّه سلبي يحدد محتوى الصورة المراد استبعاده عبر التوجيه الخالي من المصنّف. |
| `guidance_scale` |  | number | no | `5` | 0 – 20 | المقياس المطبق على التوجيه الخالي من المصنّف. |
| `seed` |  | integer \| null | no |  |  | تجاوز بذرة التوليد؛ يتيح حذفها للتوليد اختيار بذرة عشوائيًا. |
| `num_inference_steps` |  | integer | no | `28` | 4 – 50 | عدد خطوات الاستدلال المطلوب تنفيذها. |
| `image_size` |  | object {width, height} \| enum (string) \| null | no |  | `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | أبعاد الصورة الناتجة؛ عند حذفها، تطابق الأبعاد صورة المدخل. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 4 | عدد الصور المطلوب توليده. |
| `acceleration` |  | enum (string) | no | `regular` | `none`, `regular`, `high` | مستوى التسريع المطبق أثناء توليد الصورة. |
| `enable_safety_checker` |  | boolean | no | `true` |  | فحص السلامة، الذي يعيد صورًا سوداء بدلًا من أي صور مصنفة على أنها غير آمنة. تُمكّن القيمة true الفحص؛ وتعطله false للحسابات المخولة فقط، بينما تُفحص الطلبات من دون تخويل على أي حال. |
| `output_format` |  | enum (string) | no | `png` | `jpeg`, `png`, `webp` | تنسيق ملف الصورة الناتجة. |
| `image_urls` | `images` | array of image URL | yes |  |  | عناوين URL للصور المراد تحريرها، بحد أقصى 4 صور. |
| `loras` |  | array of object {path, scale} | no | `[]` |  | أوزان LoRA المراد تطبيقها، بحد أقصى 3 إدخالات. |
| `loras[].path` |  | string | yes |  |  | موقع أوزان LoRA، محدد كعنوان URL أو معرّف مستودع HuggingFace بصيغة owner/repo أو مسار محلي. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | عامل القياس المطبق على LoRA، ويتراوح من 0.0 إلى 4.0. |

File parameters (`images`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "images": [
    "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  ]
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "image_urls": [
    "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  ]
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/flux-2/klein/4b/base/edit/lora?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image_urls": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/flux-2/klein/4b/base/edit/lora?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image_urls": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image_urls": [
        "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    ],
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/flux-2/klein/4b/base/edit/lora", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "flux-2/klein/4b/base/edit/lora",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "image_urls": [
          "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
        ]
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "flux-2/klein/4b/base/edit/lora",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 32,
    "usd": "0.032",
    "charged": 32,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image_urls": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  },
  "output": {
    "images": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200,
        "width": 1024,
        "height": 768
      }
    ],
    "timings": {},
    "seed": 42,
    "has_nsfw_concepts": [
      false
    ],
    "prompt": "string"
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `images` | array of object {url, content_type, file_name, file_size, width, height} | الصور الناتجة عن النموذج. |
| `timings` | object |  |
| `seed` | integer | بذرة توليد الصورة، بما في ذلك القيمة المختارة عشوائيًا إذا لم يتضمن المدخل بذرة؛ وإلا تكرر القيمة المقدمة. |
| `has_nsfw_concepts` | array of boolean | يشير إلى ما إذا كانت مفاهيم NSFW تظهر في الصور المُولّدة. |
| `prompt` | string | الموجّه المستخدم أثناء توليد الصورة. |

## Related models

- [FLUX.2 \[klein\] 4B Base LoRA](https://doitong.com/developers/models/flux-2/klein/4b/base/lora.md) (`flux-2/klein/4b/base/lora`): $0.016 / megapixel
- [FLUX.2 \[klein\] 4B LoRA](https://doitong.com/developers/models/flux-2/klein/4b/lora.md) (`flux-2/klein/4b/lora`): $0.01 / megapixel
- [FLUX.2 \[klein\] 9B Base LoRA](https://doitong.com/developers/models/flux-2/klein/9b/base/lora.md) (`flux-2/klein/9b/base/lora`): $0.02 / megapixel
- [FLUX.2 \[klein\] 9B LoRA](https://doitong.com/developers/models/flux-2/klein/9b/lora.md) (`flux-2/klein/9b/lora`): $0.015 / megapixel
- [FLUX.2 \[klein\] 4B LoRA · Edit](https://doitong.com/developers/models/flux-2/klein/4b/edit/lora.md) (`flux-2/klein/4b/edit/lora`): $0.01 / megapixel
- [FLUX.2 \[klein\] 9B Base LoRA · Edit](https://doitong.com/developers/models/flux-2/klein/9b/base/edit/lora.md) (`flux-2/klein/9b/base/edit/lora`): $0.02 / megapixel
- [FLUX.2 \[klein\] 9B LoRA · Edit](https://doitong.com/developers/models/flux-2/klein/9b/edit/lora.md) (`flux-2/klein/9b/edit/lora`): $0.015 / megapixel
- [FLUX.1 Kontext \[pro\]](https://doitong.com/developers/models/flux-pro/kontext.md) (`flux-pro/kontext`): $0.04 / image

## Links

- HTML page: https://doitong.com/developers/models/flux-2/klein/4b/base/edit/lora
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=flux-2/klein/4b/base/edit/lora
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/flux-2/klein/4b/base/edit/lora