# Realistic Vision

Realistic Vision generates lifelike images, ideal for creative and professional projects.

## API Information

- **Model Slug:** realistic-vision-v6-0-b1
- **Branded URL:** https://www.eachlabs.ai/stability/realistic-vision/realistic-vision-v6-0-b1
- **Provider:** Stability AI
- **Category:** Text to Image
- **Output Type:** array
- **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:** 10 seconds
- **Last Updated:** 2026-04-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/realistic-vision-v6-0-b1

## 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 |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | No | photo of offroad car, forest, sunset, clouds | - | Prompt is the text input describing what you want the image to look like. |
| negative_prompt | string | No | (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime), text, 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 | - | Negative_prompt involves specifying what should not be included in the generated image. |
| image | string | No | - | image/jpeg, image/png, image/jpg, image/webp | Image is the visual output generated by the model based on the prompt. |
| mask | string | No | - | - | Mask is used to specify which parts of the image to keep or alter during generation. |
| width | integer | No | 512 | 0–1920 | Width determines the horizontal size of the generated image. |
| height | integer | No | 728 | 0–1920 | Height determines the vertical size of the generated image. |
| strength | number | No | 1 | 0–1 | Strength determines the extent to which the original image is altered if a starting image is provided. |
| num_inference_steps | integer | No | 20 | 0–100 | Num_inference_steps defines how many steps the model should take to generate the image, affecting quality and speed. |
| guidance_scale | number | No | 7.5 | 0–10 | Guidance_scale adjusts how much the model should follow the prompt versus being creative. |
| scheduler | string | No | K_EULER_ANCESTRAL | DDIM,DPMSolverMultistep,HeunDiscrete,K_EULER_ANCESTRAL,K_EULER,PNDM | Scheduler controls the method and order in which the image generation process is carried out. |
| use_karras_sigmas | boolean | No | false | - | Use_karras_sigmas is an option to improve image quality by using a specialized technique. |
| seed | integer | No | - | - | Seed is a number used to initialize the random number generator, helping to reproduce the same output. |

## 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": "realistic-vision-v6-0-b1",
  "input": {}
}'
```

## Output Schema

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

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "array",
  "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

**realistic-vision-v6.0-b1 — Text-to-Image AI Model**

Developed by Stability as part of the **realistic-vision** family, **realistic-vision-v6.0-b1** is a cutting-edge text-to-image AI model that generates photorealistic images from text prompts, solving the challenge of creating lifelike visuals without expensive photography or rendering setups. This **Stability text-to-image** powerhouse excels in producing highly detailed, human-like portraits and scenes with natural lighting, skin textures, and proportions that rival professional photography. Ideal for creators seeking a **text-to-image AI model** for realistic outputs, **realistic-vision-v6.0-b1** supports high-resolution generations up to 1024x1024 pixels, making it perfect for **AI image generator for realistic photos** workflows.

## 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.