# Z-Image Turbo ControlNet

> Generate images that follow a control image's edges, depth, or pose while matching your text prompt.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/tongyi-mai/z-image/turbo/controlnet`
- **Model ID**: `tongyi-mai/z-image/turbo/controlnet`
- **Category**: image-to-image
- **Kind**: inference
- **Tags**: z-image, controlnet, structural-conditioning, canny, depth, pose, image-to-image, turbo

## Pricing

- **Price**: $0.0065 per megapixel

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/tongyi-mai/z-image/turbo/controlnet` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/tongyi-mai/z-image/turbo/controlnet/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/tongyi-mai/z-image/turbo/controlnet/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/tongyi-mai/z-image/turbo/controlnet/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`seed`** (`integer | null`, _optional_):
  The same seed and the same prompt given to the same version of the model will output the same image every time.

- **`prompt`** (`string`, _required_):
  The prompt describing the image to generate.

- **`image_url`** (`string`, _required_):
  URL of the control/reference image that guides structural conditioning. Its aspect ratio also drives the output size.

- **`image_size`** (`ImageSize | ImageSizeEnum`, _optional_):
  Output size. Use a preset string (e.g. 'landscape_16_9') or a custom {width, height} object. 'auto' derives the size from the control image's aspect ratio.
  - Default: `"auto"`
  - Options: `"square_hd"`, `"square"`, `"portrait_4_3"`, `"portrait_16_9"`, `"landscape_4_3"`, `"landscape_16_9"`, `"auto"`

- **`num_images`** (`integer`, _optional_):
  The number of images to generate. Each generated image is billed.
  - Default: `1`
  - Range: `1` to `4`

- **`preprocess`** (`PreprocessEnum | null`, _optional_):
  How to preprocess the control image before conditioning. 'none' uses the image directly; 'canny' extracts edges; 'depth' estimates a depth map; 'pose' extracts body pose.
  - Default: `"none"`
  - Options: `"none"`, `"canny"`, `"depth"`, `"pose"`

- **`control_end`** (`number`, _optional_):
  Fraction of the denoising process at which ControlNet conditioning ends.
  - Default: `0.8`
  - Range: `0` to `1`

- **`acceleration`** (`AccelerationEnum`, _optional_):
  The acceleration level to use. Higher acceleration is faster but may reduce quality.
  - Default: `"regular"`
  - Options: `"none"`, `"regular"`, `"high"`

- **`control_scale`** (`number`, _optional_):
  How strongly the control image conditions the result (0 = ignore control, 1 = strongest conditioning).
  - Default: `0.75`
  - Range: `0` to `1`

- **`control_start`** (`number`, _optional_):
  Fraction of the denoising process at which ControlNet conditioning begins.
  - Default: `0`
  - Range: `0` to `1`

- **`output_format`** (`OutputFormatEnum`, _optional_):
  The format of the generated image.
  - Default: `"png"`
  - Options: `"jpeg"`, `"png"`, `"webp"`

- **`num_inference_steps`** (`integer`, _optional_):
  The number of inference steps to perform.
  - Default: `8`
  - Range: `1` to `8`

- **`enable_safety_checker`** (`boolean`, _optional_):
  If set to true, the safety checker will be enabled.
  - Default: `true`

- **`enable_prompt_expansion`** (`boolean`, _optional_):
  If true, the prompt is automatically expanded/enriched before generation. Enabling this increases the price by a small per-request surcharge.
  - Default: `false`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "prompt": "A vivid watercolor painting of a white lighthouse with a red lantern room standing on a rocky cliff above crashing turquoise waves at golden-hour sunset, soft washes of orange and pink sky",
  "image_url": "https://media.modelrunner.ai/9syrS9NnVrVQDHybkC4AX.png",
  "image_size": "auto",
  "num_images": 1,
  "preprocess": "none",
  "control_end": 0.8,
  "acceleration": "regular",
  "control_scale": 0.75,
  "control_start": 0,
  "output_format": "png",
  "num_inference_steps": 8,
  "enable_safety_checker": true,
  "enable_prompt_expansion": false
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/WTaGOfHRpAm8Uk5BYCRCx.png"
]
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/tongyi-mai/z-image/turbo/controlnet \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "A vivid watercolor painting of a white lighthouse with a red lantern room standing on a rocky cliff above crashing turquoise waves at golden-hour sunset, soft washes of orange and pink sky",
  "image_url": "https://media.modelrunner.ai/9syrS9NnVrVQDHybkC4AX.png",
  "image_size": "auto",
  "num_images": 1,
  "preprocess": "none",
  "control_end": 0.8,
  "acceleration": "regular",
  "control_scale": 0.75,
  "control_start": 0,
  "output_format": "png",
  "num_inference_steps": 8,
  "enable_safety_checker": true,
  "enable_prompt_expansion": false
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("tongyi-mai/z-image/turbo/controlnet", {
  input: {
  "prompt": "A vivid watercolor painting of a white lighthouse with a red lantern room standing on a rocky cliff above crashing turquoise waves at golden-hour sunset, soft washes of orange and pink sky",
  "image_url": "https://media.modelrunner.ai/9syrS9NnVrVQDHybkC4AX.png",
  "image_size": "auto",
  "num_images": 1,
  "preprocess": "none",
  "control_end": 0.8,
  "acceleration": "regular",
  "control_scale": 0.75,
  "control_start": 0,
  "output_format": "png",
  "num_inference_steps": 8,
  "enable_safety_checker": true,
  "enable_prompt_expansion": false
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "tongyi-mai/z-image/turbo/controlnet",
        arguments={
  "prompt": "A vivid watercolor painting of a white lighthouse with a red lantern room standing on a rocky cliff above crashing turquoise waves at golden-hour sunset, soft washes of orange and pink sky",
  "image_url": "https://media.modelrunner.ai/9syrS9NnVrVQDHybkC4AX.png",
  "image_size": "auto",
  "num_images": 1,
  "preprocess": "none",
  "control_end": 0.8,
  "acceleration": "regular",
  "control_scale": 0.75,
  "control_start": 0,
  "output_format": "png",
  "num_inference_steps": 8,
  "enable_safety_checker": true,
  "enable_prompt_expansion": false
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/tongyi-mai/z-image/turbo/controlnet)
- [OpenAPI Schema](https://modelrunner.ai/models/tongyi-mai/z-image/turbo/controlnet/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/tongyi-mai/z-image/turbo/controlnet/llms.txt)