# Ovis Image

Ovis-Image is a 7B text-to-image model optimized for fast generation and exceptionally clean, high-quality text rendering in images.

## API Information

- **Model Slug:** ovis-image
- **Branded URL:** https://www.eachlabs.ai/openvision/ovis/ovis-image
- **Provider:** OpenVision
- **Category:** Text to Image
- **Output Type:** array
- **Status:** active
- **Base Cost:** $0.012 per megapixel per image
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/ovis-image

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.012 per megapixel per image
- **Pricing Details:** default: $0.012

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text description of the desired image. |
| negative_prompt | string | No | - | - | Text describing what to avoid in the output. |
| image_size | string | No | landscape_4_3 | square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9 | Output image size preset. Default: landscape_4_3. |
| num_inference_steps | integer | No | 28 | 1–50 | Number of denoising steps. Range: 1–50. Default: 28. |
| guidance_scale | number | No | 5 | 0–20 | Classifier-free guidance scale. Range: 0–20. Default: 5. |
| seed | integer | No | - | 1–0 | Random seed for reproducible results. Leave empty for random output. |
| num_images | integer | No | 1 | 1–4 | Number of images to generate. Range: 1–4. Default: 1. |
| enable_safety_checker | boolean | No | true | - | Run safety checker on output. Default: true. |
| output_format | string | No | png | png, jpeg, webp | Output image format. Default: png. |
| acceleration | string | No | regular | regular, none | Acceleration mode. Default: regular. |

## 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": "ovis-image",
  "input": {
    "prompt": "The split-second of digital extraction, a human figure exploding into voxel-like cubes, leaving behind a desaturated collapsing landscape as they surge into a swirling neon data vortex. High-energy motion, glowing particle streams, 3D fragmentation effect, vivid holographic colors."
  }
}'
```

## 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

**ovis-image — Text-to-Image AI Model**

Unlock fast, high-fidelity image generation with ovis-image, a 7B parameter text-to-image AI model from OpenVision's ovis family, designed to deliver exceptionally clean text rendering in visuals while maintaining rapid processing speeds. Developers and creators searching for a **text-to-image AI model** with superior typography integration will find ovis-image stands out by producing legible, artifact-free text overlays in images—solving a common pain point in AI-generated art where prompts like product labels or signage often blur or distort. Optimized for efficiency, this **OpenVision text-to-image** solution generates high-quality outputs in seconds, making it ideal for real-time applications and high-volume workflows on Eachlabs.

## 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.