# SDXL ControlNet Union · Image to Image API

> SDXL kipo-tele-kipo, poza, depth, edge, normal vaj segmentacija kontrolne kipenca andar multipe ControlNet lidžaripeha

Transformirin ek startno kipo, SDXL base modelesa, promptosa thaj opcionalne kontrolne kipenca vaś openpose, depth, teed, canny, normal thaj segmentacija. Sako kontrolno inputo si lesko preprocess toggle. `strength` džal 0.05 katar 1, `num_inference_steps` 1 katar 70, thaj per call šaj te avena zural 8 kipi. LoRAs thaj embeddings šaj te aven, a rezultato si jpeg vaj png.

- Model id: `sdxl-controlnet-union/image-to-image`
- Made by: Stability AI
- Category: Image Editing
- Output: image
- Estimated price per run: $0.048 / image (cheapest run $0.048 (48 API credits))
- Run: `POST https://api.doitong.ru/v1/run/sdxl-controlnet-union/image-to-image`
- Quote: `POST https://api.doitong.ru/v1/quote/sdxl-controlnet-union/image-to-image`
- Docs page: https://doitong.com/rom/developers/models/sdxl-controlnet-union/image-to-image

## Pricing

Price: **$0.048 / image**. Estimated from the typical cost of one run, per output (`num_images`). The quote is exactly what the run charges.

The full example input below costs $0.048 = 48 API credits (1 image × 48 API credits).

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/sdxl-controlnet-union/image-to-image` 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 |  |  | Phen o kipo savo kames te kerel pes, use but detail sar šaj te avel maj lačho rezultato. |
| `controlnet_conditioning_scale` |  | number | no | `0.5` | 0 – 1 | Zor e conditioning-oski savi si aplicarime ControlNet-osa. |
| `image_url` | `image` | string (image URL) | yes |  |  | Startuno kipo pala keripe, dino URL-osa. |
| `negative_prompt` |  | string | no | `` |  | Negativno prompto savo phenel save detajura na kamen pe o kipo. Šaj te isključil boje, objektura, pejzažo vaj maj cikne detajura thaj kvalitetura, sar mustaći, mutno dikhimos vaj teluni rezolucija. |
| `image_size` |  | object {height, width} \| enum (string) \| null | no |  | `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Rezultatoskere dimenzije, automatikane prindžarde andar o kontrolno kipo kana nane dino size. |
| `num_inference_steps` |  | integer | no | `35` | 1 – 70 | Gin inference steps pala te kerel. |
| `guidance_scale` |  | number | no | `7.5` | 0 – 20 | Zor e promptoske pačajipaski vaś izbor e kiposko, sikavdi sar CFG (Classifier Free Guidance). |
| `strength` |  | number | no | `0.95` | 0.05 – 1 | Količina e podobnipnaski maškar o generirime kipo thaj o angluno kipo. |
| `seed` |  | integer \| null | no |  |  | Seed vaš reprodukcia e kipengo ande Stable Diffusion. O kipo šaj te reprodukčarel pes ekzaktno pe sa keripena te mukhes isto o modelesko version, prompto thaj seed. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 8 | Manglo kipoqo gin vaš generiripe. |
| `loras` |  | array of object {force, path, scale} | no | `[]` |  | LoRA weights kidle vaš o vakeripen, delde sar jekh lista. |
| `loras[].force` |  | boolean | no | `false` |  | Whether embedding use is mandatory: true makes it compulsory. |
| `loras[].path` |  | string | yes |  |  | LoRA weightsko sasto: deldo sar HF modelosko identifikator savo arakhel safetensors weights, vaj sar safetensors fajlo arakhlo URL-esa vaj pathesa. |
| `loras[].scale` |  | number | no | `1` | 0 – 1 | Multiplikator dino e LoRA vazipnaske anglal mergipen ande o bazno modelo. |
| `embeddings` |  | array of object {path, tokens} | no | `[]` |  | Embeddings kidle vaš o vakeripen, delde sar jekh lista. |
| `embeddings[].path` |  | string | yes |  |  | Embedding weights specifičime URL-esa vaj fajloske pathesa. |
| `embeddings[].tokens` |  | array of string \| null | no |  |  | Embedding tokenonge lista, avtomatikano navipen si dostupno kana na deldo: sajekh vector ande embeddingosko fajlo lel tokeno andar sekvenca <s0>, <s1>, ... . |
| `enable_safety_checker` |  | boolean | no | `true` |  | Safety-checker aktivacia; true aktivarel checking. |
| `safety_checker_version` |  | enum (string) | no | `v1` | `v1`, `v2` | Kid maškar custom ViT safety checker (`v2`) thaj CompVis checker (`v1`, standardno). |
| `expand_prompt` |  | boolean | no | `false` |  | Promptosko bararipen avere promptosa, aktivno kana si true. |
| `format` |  | enum (string) | no | `jpeg` | `jpeg`, `png` | Fajlo-formato e rezultato kipoqo. |
| `request_id` |  | string | no | `` |  | Mangipnasko identifikator vaš jekh response-sa jekh mangipnasa savo les kerda. |
| `preserve_aspect_ratio` |  | boolean | no | `false` |  | Čhiv ko true te ačhavel o generirime kiposkoro aspect ratio vi kana leskoro baripen si upral o limit. Pala te lel čače proporcije crop-osa palal e keripe, čhiv crop_output ko True. Width vaj height vrednostura save nane delime ko 32 si palem zaokruglarde ko majpašalno multiple e 32-koro, thaj ada resizing standardno na ačhavel o aspect ratio. |
| `crop_output` |  | boolean | no | `false` |  | Crop-ker o generirime rezultato ko čačo aspect ratio kana true. |
| `openpose_image_url` |  | string (image URL) \| null | no |  |  | URL savo džal ko kontrolno kipo. |
| `openpose_preprocess` |  | boolean | no | `true` |  | Kontroluil preprocessing e openpose kipesko. |
| `depth_image_url` |  | string (image URL) \| null | no |  |  | URL savo džal ko kontrolno kipo. |
| `depth_preprocess` |  | boolean | no | `true` |  | Kontroluil preprocessing e depth kipesko. |
| `teed_image_url` |  | string (image URL) \| null | no |  |  | URL savo džal ko kontrolno kipo. |
| `teed_preprocess` |  | boolean | no | `true` |  | Kontroluil preprocessing e teed kipesko. |
| `canny_image_url` |  | string (image URL) \| null | no |  |  | URL savo džal ko kontrolno kipo. |
| `canny_preprocess` |  | boolean | no | `true` |  | Kontroluil preprocessing e canny kipesko. |
| `normal_image_url` |  | string (image URL) \| null | no |  |  | URL savo džal ko kontrolno kipo. |
| `normal_preprocess` |  | boolean | no | `true` |  | Kontroluil preprocessing e normal kipesko. |
| `segmentation_image_url` |  | string (image URL) \| null | no |  |  | URL savo džal ko kontrolno kipo. |
| `segmentation_preprocess` |  | boolean | no | `true` |  | Kontroluil preprocessing e segmentacijake kipesko. |

File parameters (`image`, `openpose_image_url`, `depth_image_url`, `teed_image_url`, `canny_image_url`, `normal_image_url`, `segmentation_image_url`) 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
{
  "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

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

## 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/sdxl-controlnet-union/image-to-image?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# 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/sdxl-controlnet-union/image-to-image?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
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 = {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/sdxl-controlnet-union/image-to-image", 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": "sdxl-controlnet-union/image-to-image",
      "input": {
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "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": "sdxl-controlnet-union/image-to-image",
  "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": 48,
    "usd": "0.048",
    "charged": 48,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "images": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "width": 1024,
        "height": 768,
        "content_type": "image/jpeg"
      }
    ],
    "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `images` | array of object {url, width, height, content_type} | Fajloskere informacie vaš e kerde kipura. |
| `timings` | object |  |
| `seed` | integer | Kipo-generiripeqo seed, inkludirindoj o randomno kidlo valoro kana o inputo na sas seed; averčes, repetirisar o dindo valoro. |
| `has_nsfw_concepts` | array of boolean | Sikavel te si NSFW koncepto ande generirime kipo. |
| `prompt` | string | Prompto utilizuime ko kipoqo generiripe. |

## Related models

- [SDXL ControlNet Union](https://doitong.com/developers/models/sdxl-controlnet-union.md) (`sdxl-controlnet-union`): $0.014 / image
- [SDXL ControlNet Union · Inpainting](https://doitong.com/developers/models/sdxl-controlnet-union/inpainting.md) (`sdxl-controlnet-union/inpainting`): $0.012 / image
- [FLUX.1 Kontext \[pro\]](https://doitong.com/developers/models/flux-pro/kontext.md) (`flux-pro/kontext`): $0.04 / image
- [GPT Image 2.5 Edit](https://doitong.com/developers/models/openai/gpt-image-2.5/flare/edit.md) (`openai/gpt-image-2.5/flare/edit`): from $0.12 / image
- [Nano Banana 2 Edit](https://doitong.com/developers/models/nano-banana-2/edit.md) (`nano-banana-2/edit`): from $0.06 / image
- [Nano Banana Pro Edit](https://doitong.com/developers/models/nano-banana-pro/edit.md) (`nano-banana-pro/edit`): from $0.15 / image
- [Qwen Image 3 Edit](https://doitong.com/developers/models/alibaba/qwen-image-3/edit.md) (`alibaba/qwen-image-3/edit`): from $0.04 / image
- [Seedream 5.0 Pro Edit](https://doitong.com/developers/models/bytedance/seedream/v5/pro/edit.md) (`bytedance/seedream/v5/pro/edit`): from $0.0675 / run of output image

## Links

- HTML page: https://doitong.com/developers/models/sdxl-controlnet-union/image-to-image
- 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=sdxl-controlnet-union/image-to-image
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/sdxl-controlnet-union/image-to-image