# Krea 2 Trainer API

> Trèanaichidh e Krea 2 LoRA gnàthaichte bho zip de dh’ìomhaighean, le caipsean fèin-obrachail roghainneil

Dèan gleus mionaideach air LoRA air .zip de dh’ìomhaighean aig `images_data_url`, le captionan .txt den aon ainm agus `trigger_phrase` roghainneil. Is iad na modhan `auto_captioning` Off, Object/Character, Style agus Custom. Tha `steps` eadar 50 agus 10000 (bunaiteach 100), agus `resolution` 768 no 1024. Cuiridh e cuideaman LoRA agus faidhle rèiteachaidh a-mach.

- Model id: `krea-2-trainer`
- Made by: Krea
- Category: Training
- Output: file
- Price per run: from $0.30 / run (cheapest run $0.30 (300 API credits))
- Run: `POST https://api.doitong.com/v1/run/krea-2-trainer`
- Quote: `POST https://api.doitong.com/v1/quote/krea-2-trainer`
- Docs page: https://doitong.com/gd/developers/models/krea-2-trainer

## Pricing

Price: **from $0.30 / 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 $0.30 = 300 API credits (1 run × $0.30).

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/krea-2-trainer` 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 |  |  | URL airson .zip ìomhaighean trèanaidh anns a bheil faidhlichean PNG/JPG/JPEG/WebP; fàilligidh iarrtas le 422 ma tha ìomhaigh sam bith gun fhaidhle caption agus gun `trigger_phrase` neo-fhalamh. Tha captions roghainneil nuair a bheir `trigger_phrase` an roghainn thuiteamach seachad; air neo cleachd gasan ainmean-faidhle co-ionnan: bidh ROOT.EXT a’ paidhreachadh le ROOT.txt, mar eisimpleir 001.jpg le 001.txt. |
| `trigger_phrase` |  | string | no | `` |  | Abairt eisimpleir ann an stoidhle DreamBooth a tha riatanach ma tha `auto_captioning` Off agus ìomhaigh sam bith gun fhaidhle caption. Bidh e a’ toirt captions seachad far a bheil faidhlichean .txt a dhìth agus a’ solar an teacsa tòiseachaidh airson promptan dearbhaidh bun-roghainn. |
| `auto_captioning` |  | enum (string) | no | `Off` | `Off`, `Object/Character`, `Style`, `Custom` | Mod captionachaidh roghainneil: bidh Object/Character, Style agus Custom a’ gairm dataset-captioner le google/gemma-4-31B-it, agus bidh Off a’ cumail an riatanais làithrich gum bi caption .txt le stem co-ionann aig gach ìomhaigh, no gun tèid trigger_phrase a chleachdadh mar thuiteam air ais. Airson captionan a chaidh a ghineadh, thèid trigger_phrase a chur a-steach don prompt captionachaidh agus a dhèanamh àbhaisteach anns na sidecars a thig às a rèir gnàthas captionachaidh LoRA a chaidh a thaghadh. |
| `steps` |  | integer | no | `100` | 50 – 10,000 | Cunntas cheumannan airson trèanadh LoRA. |
| `learning_rate` |  | number | no | `0.0005` | 0.000001 – 0.01 | Ìre ionnsachaidh factar-B LoRA, air a cur an sàs ann an A cuideachd nuair a tha `lora_a_lr_multiplier=1`; fo muon, tha i a’ riochdachadh na h-ìre co-ionann ri AdamW, air a sgèileadh le match_rms_adamw. Airson clàr-ama seasmhach, tha Krea a’ moladh an raoin 3e-4–7e-4. |
| `resolution` |  | enum (integer) | no | `768` | `768`, `1024` | Dùmhlachd-bhreacaidh trèanaidh, far a bheil 1024 a’ fàbharachadh mion-fhiosrachadh as àirde agus 768 a’ tabhann trèanadh mu 1.7x nas luaithe, nas lugha de chleachdadh VRAM agus càileachd stoidhle cha mhòr co-ionann. Tha ìomhaighean air an sgèileadh gus an ceàrnag thargaid a chòmhdach, agus an uair sin air an bhuain sa mheadhan. |
| `debug_dataset` |  | boolean | no | `false` |  | Roghainn luchdachadh a-nuas an t-seata-dàta a nochdas dìreach na chaidh a chleachdadh ann an trèanadh, air a phacaigeadh mar thasglann às dèidh lìonadh nan captionan no gineadh captionan fèin-obrachail. |

## 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.com/v1/run/krea-2-trainer?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.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/krea-2-trainer?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.com/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/krea-2-trainer", 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": "krea-2-trainer",
      "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": "krea-2-trainer",
  "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": 300,
    "usd": "0.30",
    "charged": 300,
    "refunded": 0
  },
  "input": {
    "images_data_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "output": {
    "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
    },
    "prompt_enhancement_system_prompt": "string",
    "debug_dataset": {
      "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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `lora_file` | object {url, content_type, file_name, file_size} | URL luchdachadh a-nuas airson cuideaman LoRA Krea-2 trèanaichte ann an cruth safetensors. |
| `config_file` | object {url, content_type, file_name, file_size} | Ceangal gu faidhle JSON anns a bheil rèiteachadh an trèanaidh/LoRA. |
| `prompt_enhancement_system_prompt` | string \| null | Prompt an t-siostaim air a thilleadh le `auto_captioning` air a chur an comas, gus cuideachadh le sgrìobhadh no leasachadh promptan inference a’ cleachdadh an aon ghnàthas captionachaidh ris an dàta trèanaidh le captionan fèin-obrachail. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Luchdachadh a-nuas dàta trèanaidh a gheibhear nuair a tha `debug_dataset` air a chur an comas: tasglann anns a bheil an seata-dàta ullaichte agus na captionan a chaidh a ghineadh gu fèin-obrachail. |

## Related models

- [Krea 2 Text to Image Turbo LoRA](https://doitong.com/developers/models/krea-2/turbo/lora.md) (`krea-2/turbo/lora`): $0.01 / megapixel
- [Krea 2 Turbo](https://doitong.com/developers/models/krea-2/turbo.md) (`krea-2/turbo`): $0.008 / megapixel
- [ERNIE-Image Trainer](https://doitong.com/developers/models/ernie-image-trainer.md) (`ernie-image-trainer`): $0.0012 / step
- [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

## Links

- HTML page: https://doitong.com/developers/models/krea-2-trainer
- 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=krea-2-trainer
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/krea-2-trainer