# SDXL Ad Inpaint

Product advertising image generator using SDXL

## API Information

- **Model Slug:** sdxl-ad-inpaint
- **Branded URL:** https://www.eachlabs.ai/stability/sdxl/sdxl-ad-inpaint
- **Provider:** Stability
- **Category:** Image to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Per-second pricing based on provider predict_time. Rate: $0.00108/sec from GPU tier.
- **Estimated Processing Time:** 20 seconds
- **Last Updated:** 2026-04-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/sdxl-ad-inpaint

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Per-second pricing based on provider predict_time. Rate: $0.00108/sec from GPU tier.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Per-second pricing based on provider predict_time. Rate: $0.00108/sec from GPU tier. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| image | string | Yes | - | image/jpeg, image/png, image/jpg, image/webp | An image can be used as input to influence or guide the model's output alongside text descriptions. |
| product_fill | string | No | Original | Original,80,70,60,50,40,30,20 | Product fill is about populating a product with relevant information or features based on AI input. |
| prompt | string | Yes | - | - | A prompt is the initial text or instruction given to the model to start generating a response. |
| negative_prompt | string | No | low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement | - | Negative prompts are used to specify what the AI should avoid including when generating text or images. |
| img_size | string | No | 1024, 1024 | [,',5,1,2,,, ,2,0,4,8,',,, ,',5,1,2,,, ,1,9,8,4,',,, ,',5,1,2,,, ,1,9,2,0,',,, ,',5,1,2,,, ,1,8,5,6,',,, ,',5,7,6,,, ,1,7,9,2,',,, ,',5,7,6,,, ,1,7,2,8,',,, ,',5,7,6,,, ,1,6,6,4,',,, ,',6,4,0,,, ,1,6,0,0,',,, ,',6,4,0,,, ,1,5,3,6,',,, ,',7,0,4,,, ,1,4,7,2,',,, ,',7,0,4,,, ,1,4,0,8,',,, ,',7,0,4,,, ,1,3,4,4,',,, ,',7,6,8,,, ,1,3,4,4,',,, ,',7,6,8,,, ,1,2,8,0,',,, ,',8,3,2,,, ,1,2,1,6,',,, ,',8,3,2,,, ,1,1,5,2,',,, ,',8,9,6,,, ,1,1,5,2,',,, ,',8,9,6,,, ,1,0,8,8,',,, ,',9,6,0,,, ,1,0,8,8,',,, ,',9,6,0,,, ,1,0,2,4,',,, ,',1,0,2,4,,, ,1,0,2,4,',,, ,',1,0,2,4,,, ,9,6,0,',,, ,',1,0,8,8,,, ,9,6,0,',,, ,',1,0,8,8,,, ,8,9,6,',,, ,',1,1,5,2,,, ,8,9,6,',,, ,',1,1,5,2,,, ,8,3,2,',,, ,',1,2,1,6,,, ,8,3,2,',,, ,',1,2,8,0,,, ,7,6,8,',,, ,',1,3,4,4,,, ,7,6,8,',,, ,',1,4,0,8,,, ,7,0,4,',,, ,',1,4,7,2,,, ,7,0,4,',,, ,',1,5,3,6,,, ,6,4,0,',,, ,',1,6,0,0,,, ,6,4,0,',,, ,',1,6,6,4,,, ,5,7,6,',,, ,',1,7,2,8,,, ,5,7,6,',,, ,',1,7,9,2,,, ,5,7,6,',,, ,',1,8,5,6,,, ,5,1,2,',,, ,',1,9,2,0,,, ,5,1,2,',,, ,',1,9,8,4,,, ,5,1,2,',,, ,',2,0,4,8,,, ,5,1,2,',] | Image size determines the dimensions of the resulting generated images. |
| scheduler | string | No | K_EULER | DDIM,DPMSolverMultistep,HeunDiscrete,KarrasDPM,K_EULER_ANCESTRAL,K_EULER,PNDM | A scheduler manages the sequence and timing of tasks or steps in the model's processing. |
| num_inference_steps | integer | No | 40 | - | The number of inference steps refers to how many steps the model takes to generate a result, affecting quality and computation time. |
| guidance_scale | number | No | 7.5 | - | Guidance scale sets the influence of guidance on the AI's generation process to steer the output towards desired criteria. |
| condition_scale | number | No | 0.9 | 0–1 | Condition scale adjusts the strength of conditions applied to the model's output to better match specific requirements. |
| num_refine_steps | integer | No | 10 | 0–40 | The number of refine steps represents additional passes the model makes to improve the result. |
| apply_img | boolean | No | true | - | Apply img refers to the process of using an image as part of the input to guide or influence the model's output. |
| seed | integer | No | - | - | A seed is a starting point for random number generation, ensuring repeatability of the AI's output if the same seed is used. |

## 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-ad-inpaint",
  "input": {
    "image": "https://storage.googleapis.com/magicpoint/inputs/image-background-editing-input.webp",
    "prompt": "perfume bottle on the table"
  }
}'
```

## 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-ad-inpaint — Image-to-Image AI Model**

sdxl-ad-inpaint, a specialized variant in Stability's SDXL family, excels as a **product advertising image generator** using image-to-image techniques, transforming existing product photos into compelling ad visuals with precise inpainting.

Developed by Stability, this **image-to-image AI model** leverages SDXL's advanced latent diffusion architecture to edit and enhance images for marketing, enabling e-commerce teams to quickly generate professional-grade advertising composites without costly photoshoots.

Ideal for **AI photo editing for e-commerce**, sdxl-ad-inpaint takes an input image and text prompt to inpaint or modify specific areas, producing high-detail outputs optimized for promotional use.

## 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.