# Realisitic Vision V3 Inpainting

Realistic Vision V3.0 Inpainting

## API Information

- **Model Slug:** realisitic-vision-v3-inpainting
- **Branded URL:** https://www.eachlabs.ai/stability/realistic-vision/realisitic-vision-v3-inpainting
- **Provider:** Stability AI
- **Category:** Image to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Per-second pricing based on provider predict_time. Rate: $0.00154/sec from GPU tier.
- **Estimated Processing Time:** 75 seconds
- **Last Updated:** 2026-04-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/realisitic-vision-v3-inpainting

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Per-second pricing based on provider predict_time. Rate: $0.00154/sec from GPU tier.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Per-second pricing based on provider predict_time. Rate: $0.00154/sec from GPU tier. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| image | string | Yes | - | - | Input image |
| prompt | string | No | RAW photo, a portrait photo of Katie Read in casual clothes, natural skin, 8k uhd, high quality, film grain, Fujifilm XT3 | - | - |
| mask | string | Yes | - | - | Mask image |
| negative_prompt | string | No | (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck | - | - |
| strength | number | No | 0.8 | 0–1 | strength/weight |
| steps | integer | No | 20 | 0–100 | num_inference_steps |
| num_outputs | integer | No | 1 | 0–5 | Number of images to create |
| guaidance_scale | number | No | 7.5 | 0–20 | Higher guidance scale encourages to generate images that are closely linked to the text prompt |

## 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": "realisitic-vision-v3-inpainting",
  "input": {
    "mask": "https://cdn.eachlabs.ai/ipfs/J6bUrZnQhr3Vt5loDobhRrCxNPPKIc83yOw1KWkLTZtzjCiw/pexels-ali-pazani-2787341.png",
    "image": "https://cdn.eachlabs.ai/ipfs/J6bUrBE3IEtFB3gsEmtuQXoaHmZGGfdrUwHp57SMGiSJuI4h/pexels-ali-pazani-2787341_mask.png"
  }
}'
```

## 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

**realisitic-vision-v3-inpainting — Image-to-Image AI Model**

Developed by Stability as part of the **realistic-vision** family, **realisitic-vision-v3-inpainting** is an advanced image-to-image AI model specializing in precise inpainting for photorealistic edits, enabling users to seamlessly modify specific areas of images while preserving overall realism and detail. This **Stability image-to-image** tool excels at targeted alterations like object removal, background replacement, or detail enhancement, solving common challenges in photo editing workflows where traditional tools fall short on natural integration. Ideal for developers seeking a **realisitic-vision-v3-inpainting API** or creators needing high-fidelity inpainting, it delivers professional-grade results from an input image and text prompt, supporting resolutions up to those of SDXL standards for sharp, detailed outputs.

## 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.