# SDXL Controlnet

SDXL Controlnet enhances image generation by providing precise control over structure and details.

## API Information

- **Model Slug:** sdxl-controlnet
- **Branded URL:** https://www.eachlabs.ai/stability/sdxl/sdxl-controlnet
- **Provider:** Stability
- **Category:** Image to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** $0.00108 per processing second
- **Estimated Processing Time:** 18 seconds
- **Last Updated:** 2026-04-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/sdxl-controlnet

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.00108 per processing second
- **Pricing Details:** default: $0.00108

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| image | string | Yes | - | image/jpeg, image/png, image/jpg, image/webp | Input image for img2img or inpaint mode |
| prompt | string | Yes | aerial view, a futuristic research complex in a bright foggy jungle, hard lighting | - | Input prompt |
| negative_prompt | string | No | low quality, bad quality, sketches | - | Input Negative Prompt |
| num_inference_steps | integer | No | 50 | 1–500 | Number of denoising steps |
| condition_scale | number | No | 0.5 | 0–1 | controlnet conditioning scale for generalization |
| seed | integer | No | 0 | - | Random seed. Set to 0 to randomize the seed |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "sdxl-controlnet",
  "input": {
    "image": "https://cdn-us.eachlabs.ai/defaults/6a1e7645fdb5cce2f370b1fdf6747925d4792eb76925e9b88715624ddec7907e.webp",
    "prompt": "a couple watching a romantic sunset, 4k photo"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated image)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**sdxl-controlnet — Image-to-Image AI Model**

sdxl-controlnet, developed by Stability as part of the sdxl family, empowers developers and creators with precise structural control in image-to-image AI generation, transforming reference images into detailed outputs while preserving poses, edges, and layouts. This Stability image-to-image model excels in workflows requiring exact adherence to input structures, such as pose-guided edits or depth-based refinements, making it ideal for AI image editor API integrations. Unlike standard diffusion models, sdxl-controlnet leverages ControlNet architecture to condition SDXL generations on control maps like canny edges or depth, delivering high-fidelity results at resolutions up to 1024x1024.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.