# Train Flux LoRA API

> 이미지 zip에서 사람, 주제 또는 스타일을 학습하는 Flux LoRA 학습

이미지 zip 아카이브(`images_data_url`)에서 LoRA를 파인튜닝하며 일치하는 캡션 텍스트 파일을 포함할 수 있습니다. 개념 이름에는 `trigger_word`를 사용하고, 스타일 학습에는 `is_style`을 사용하면 세그먼테이션과 캡셔닝이 비활성화됩니다. `create_masks`는 주제에 대한 손실 가중치를 높이며 `steps`는 1~10000을 지원합니다. diffusers LoRA 가중치와 config 파일을 반환합니다.

- Model id: `flux-lora-fast-training`
- Made by: Black Forest Labs
- Category: Training
- Output: file
- Price per run: from $0.002 / run (cheapest run $0.002 (2 API credits))
- Run: `POST https://api.doitong.ru/v1/run/flux-lora-fast-training`
- Quote: `POST https://api.doitong.ru/v1/quote/flux-lora-fast-training`
- Docs page: https://doitong.com/ko/developers/models/flux-lora-fast-training

## Pricing

Price: **from $0.002 / run** (the lowest tier; the quote prices your exact input). Price per run: 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 $2.00 = 2000 API credits (1 run × $2.00).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.ru/v1/quote/flux-lora-fast-training` 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

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `images_data_url` |  | string | yes |  |  | ZIP 아카이브 URL을 통해 이미지를 제공합니다. 선택적으로 각 이미지와 같은 이름의 캡션 텍스트 파일을 연결할 수 있습니다. 최소 4개 이상의 이미지를 권장하며, 일반적으로 이미지 세트가 클수록 좋습니다. |
| `trigger_word` |  | string \| null | no |  |  | 캡션이 없을 때 캡션 대신 사용할 트리거 단어입니다. 기존 캡션이 있으면 trigger_word는 사용되지 않습니다. 트리거 단어를 사용하지 않으려면 None으로 설정합니다. |
| `create_masks` |  | boolean | no | `true` |  | True로 설정하면 마스크 기반 학습 손실 가중치를 활성화합니다. 사람 이미지에서는 가능한 경우 얼굴 마스크를 사용합니다. |
| `steps` |  | integer \| null | no |  | 1 – 10,000 | LoRA의 학습 단계 수입니다. |
| `is_style` |  | boolean | no | `false` |  | True로 설정하면 스타일 학습을 활성화하고, 트리거 단어로 스타일을 지정합니다. 이 모드에서는 트리거 단어가 캡션을 대체하며 세그멘테이션이 비활성화됩니다. |
| `is_input_format_already_preprocessed` |  | boolean | no | `false` |  | 제공된 데이터의 전처리 상태입니다. True는 이미 전처리된 데이터 세트임을 나타냅니다. 기본값인 False는 'photo.jpg'와 'photo.txt'처럼 기본 이름이 일치하는 원시 이미지/캡션 쌍을 요구합니다. |
| `data_archive_format` |  | string \| null | no |  |  | 아카이브 형식입니다. 생략하면 URL에서 추론합니다. |

## Example input

Required parameters only:

```json
{
  "images_data_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

A fuller example:

```json
{
  "images_data_url": "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.ru/v1/run/flux-lora-fast-training?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "images_data_url": "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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.ru/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-lora-fast-training?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "images_data_url": "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.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "images_data_url": "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-lora-fast-training", 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.ru/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-lora-fast-training",
      "input": {
        "images_data_url": "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-lora-fast-training",
  "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": 2000,
    "usd": "2.00",
    "charged": 2000,
    "refunded": 0
  },
  "input": {
    "images_data_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "output": {
    "diffusers_lora_file": {
      "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
    },
    "config_file": {
      "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
    },
    "debug_preprocessed_output": {
      "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
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `diffusers_lora_file` | object {url, content_type, file_name, file_size} | diffusers 형식의 학습된 LoRA 가중치를 가리키는 URL입니다. |
| `config_file` | object {url, content_type, file_name, file_size} | 학습 구성 파일 URL입니다. |
| `debug_preprocessed_output` | object {url, content_type, file_name, file_size} \| null | 전처리 후 이미지 위치를 가리키는 URL입니다. |

## Related models

- [FLUX 2 \[klein\] 9b Base Trainer](https://doitong.com/developers/models/flux-2-klein-9b-base-trainer.md) (`flux-2-klein-9b-base-trainer`): $0.0043 / step
- [Flux 2 Klein 9B Base Trainer](https://doitong.com/developers/models/flux-2-klein-9b-base-trainer/edit.md) (`flux-2-klein-9b-base-trainer/edit`): $0.0139 / step
- [FLUX 2 Trainer](https://doitong.com/developers/models/flux-2-trainer.md) (`flux-2-trainer`): $0.0064 / step
- [FLUX 2 Trainer Edit](https://doitong.com/developers/models/flux-2-trainer/edit.md) (`flux-2-trainer/edit`): $0.0389 / step
- [FLUX 2 Trainer V2](https://doitong.com/developers/models/flux-2-trainer-v2.md) (`flux-2-trainer-v2`): $0.0064 / step
- [FLUX 2 Trainer V2 Edit](https://doitong.com/developers/models/flux-2-trainer-v2/edit.md) (`flux-2-trainer-v2/edit`): $0.0389 / step
- [Flux Kontext Trainer](https://doitong.com/developers/models/flux-kontext-trainer.md) (`flux-kontext-trainer`): from $1.25 / run
- [Train Flux LoRAs For Portraits](https://doitong.com/developers/models/flux-lora-portrait-trainer.md) (`flux-lora-portrait-trainer`): from $2.40 / run

## Links

- HTML page: https://doitong.com/developers/models/flux-lora-fast-training
- 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-lora-fast-training
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/flux-lora-fast-training