Name: ControlNet Depth API: Depth-Guided Image Generation
Brand: magicapi
SKU: api-magicapi-image-modification-depth-maps-jagilley-controlnet-depth2img
Availability: InStock
Author: API Market

Shashank Agarwal

# 🧊 Depth-Guided Image Generation API (jagilley ControlNet Depth)

## Overview
ControlNet Depth by jagilley modifies images using depth maps. Send an `image` and a text `prompt`: the model estimates a depth map of the image, then generates a new picture that follows that depth layout while matching your prompt. The scene's shapes and perspective stay in place; the content and style change.

Each request returns a list of image URLs: the detected depth map followed by the generated images (1 or 4, set by `num_samples`).

## Features
- **Depth-guided generation**: keeps the spatial layout of your image while repainting it from a prompt.
- **Depth map included**: the response also contains the depth map the model detected.
- **Output sizes**: `image_resolution` of `256`, `512` (default) or `768`.
- **1 or 4 samples per request** with `num_samples`.
- **Prompt helpers**: `a_prompt` adds quality words to every prompt, `n_prompt` lists things to avoid; both have sensible defaults.
- **Sampler controls**: `ddim_steps`, `scale` (guidance), `eta` and `seed`.

## Use Cases
1. **Restyle a scene**: keep the room, street or pose from a photo and change what is in it.
2. **Concept variations**: produce several versions of the same composition with different subjects.
3. **Depth maps**: get a depth estimate of a photo as a by-product of each request.
4. **Creative edits**: put new characters or materials into an existing layout, as in the example.

## Visual Examples
### Example Input
Prompt: "a stormtrooper giving a lecture at a university"

Input image:

![ControlNet Depth example input: the source image](https://blog.api.market/wp-content/uploads/2026/10/controlnet-depth2img-input-api-market.png)

Settings: `scale` `9`, `ddim_steps` `20`, `num_samples` `1`, `image_resolution` `512`, `detect_resolution` `512`, `a_prompt` and `n_prompt` at their default values.

### Example Output
The request returned two images: the detected depth map and the generated image.

![ControlNet Depth example output 1: the depth map detected from the input image](https://blog.api.market/wp-content/uploads/2026/10/controlnet-depth2img-output-1-kgy1xcw8-api-market.png)

![ControlNet Depth example output 2: a stormtrooper giving a lecture at a university, following the depth of the input](https://blog.api.market/wp-content/uploads/2026/10/controlnet-depth2img-output-2-kgy1xcw8-api-market.png)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `image` | string (URL) | Yes |  |  | Input image |
| `prompt` | string | Yes |  |  | Prompt for the model |
| `num_samples` | string | No | `1` | `1`, `4` | Number of samples to generate. Higher values may run out of memory |
| `image_resolution` | string | No | `512` | `256`, `512`, `768` | Resolution of the generated image |
| `ddim_steps` | integer | No | `20` |  | Number of DDIM sampling steps |
| `scale` | number | No | `9` | 0.1 to 30 | Guidance scale |
| `seed` | integer | No | none |  | Random seed |
| `eta` | number | No | `0` |  | eta value of the DDIM sampler |
| `a_prompt` | string | No | `best quality, extremely detailed` |  | Text added to the prompt |
| `n_prompt` | string | No | `longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality` |  | Negative prompt |
| `detect_resolution` | integer | No | `512` | 128 to 1024 | Resolution used for depth detection |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.016 per API unit.
- **1 API unit = 1 request with up to 10 seconds of processing.** A request that takes longer is billed one more unit for each started 10-second block of processing time.
- **Example cost**: the example request above took 4.7 seconds of processing, so it used 1 unit = $0.016.
- `num_samples` `4`, a higher `image_resolution` or more `ddim_steps` take longer and can use more units.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/image-modification-depth-maps-jagilley-controlnet-depth2img`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well. The first request after a quiet period can take more than a minute to start.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/image-modification-depth-maps-jagilley-controlnet-depth2img/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "922c7bb67b87ec32cbc2fd11b1d5f94f0ba4f5519c4dbd02856376444127cc60",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/10/controlnet-depth2img-input-api-market.png",
      "scale": 9,
      "prompt": "a stormtrooper giving a lecture at a university",
      "a_prompt": "best quality, extremely detailed",
      "n_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "ddim_steps": 20,
      "num_samples": "1",
      "image_resolution": "512",
      "detect_resolution": 512
    }
  }'
```

Response (201 Created):
```json
{
  "id": "kgy1xcw8j1rna0d1ccrbbjnj4w",
  "version": "922c7bb67b87ec32cbc2fd11b1d5f94f0ba4f5519c4dbd02856376444127cc60",
  "status": "starting",
  "created_at": "2026-10-22T10:38:07.673Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/image-modification-depth-maps-jagilley-controlnet-depth2img/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "kgy1xcw8j1rna0d1ccrbbjnj4w",
  "status": "succeeded",
  "output": [
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-depth2img-output-1-kgy1xcw8-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-depth2img-output-2-kgy1xcw8-api-market.png"
  ],
  "error": null,
  "created_at": "2026-10-22T10:38:07.673Z",
  "started_at": "2026-10-22T10:39:50.907Z",
  "completed_at": "2026-10-22T10:39:55.569Z"
}
```

`output` is a list of PNG image URLs: the detected depth map first, then one generated image per sample.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `image` or `prompt`, or a `num_samples` other than `"1"` or `"4"`.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/image-modification-depth-maps-jagilley-controlnet-depth2img";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "922c7bb67b87ec32cbc2fd11b1d5f94f0ba4f5519c4dbd02856376444127cc60", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  image: "https://blog.api.market/wp-content/uploads/2026/10/controlnet-depth2img-input-api-market.png",
  scale: 9,
  prompt: "a stormtrooper giving a lecture at a university",
  a_prompt: "best quality, extremely detailed",
  n_prompt: "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  ddim_steps: 20,
  num_samples: "1",
  image_resolution: "512",
  detect_resolution: 512
}).then((output) => {
  const [depthMap, ...images] = output;
  console.log({ depthMap, images });
});
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/image-modification-depth-maps-jagilley-controlnet-depth2img"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "922c7bb67b87ec32cbc2fd11b1d5f94f0ba4f5519c4dbd02856376444127cc60", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


output = create_and_wait_for_prediction({
    "image": "https://blog.api.market/wp-content/uploads/2026/10/controlnet-depth2img-input-api-market.png",
    "scale": 9,
    "prompt": "a stormtrooper giving a lecture at a university",
    "a_prompt": "best quality, extremely detailed",
    "n_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
    "ddim_steps": 20,
    "num_samples": "1",
    "image_resolution": "512",
    "detect_resolution": 512
})
depth_map, images = output[0], output[1:]
print(depth_map, images)
```

## FAQ
- **Why do I get two images when `num_samples` is 1?**
  - The first URL is the depth map the model detected from your image. The generated images follow it, one per sample.
- **Are `num_samples` and `image_resolution` numbers or strings?**
  - Strings. Send `"1"` or `"4"` and `"256"`, `"512"` or `"768"`. `detect_resolution` is an integer.
- **How do I change how closely the result follows my prompt?**
  - Adjust `scale` (guidance, 0.1 to 30, default 9). Higher values follow the prompt more strictly.
- **Do I need to send `a_prompt` and `n_prompt`?**
  - No. Both have default values that are applied when you leave them out.
- **How is a request billed?**
  - $0.016 for each started 10-second block of processing. The example took 4.7 seconds and cost $0.016.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page. You can also email our support team at hello@magicapi.com.


Generate new images that follow the depth layout of your photo with jagilley ControlNet Depth; each response includes the detected depth map.