# Kling O3 Image Text to Image - Core.Today AI API

> Kuaishou's Kling Omni 3 (O3) text-to-image via Fal.AI. High-consistency image generation at 1K/2K/4K, single images or a related series of 2-9, with optional character elements (@Element1) for face/identity control.

- **Provider**: Kuaishou
- **Model ID**: fal-ai/kling-image/o3/text-to-image
- **Category**: Image Generation
- **Credits**: 66 per image (1K/2K 65, 4K 130 credits/image; series billed per image)
- **Speed**: Medium
- **Quality**: Ultra

## Features
- 1K, 2K and 4K output
- Series mode: 2-9 related images with consistent characters and style
- Character elements (@Element1) for face/identity control
- Up to 9 independent images per request

## Use Cases
- Editorial and fashion imagery with typography
- Storyboards and comic panels as a consistent series
- Character sheets that keep the same face across shots
- Print-ready 4K key visuals

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - Text prompt for image generation (max 2,500 characters). Reference character elements as @Element1, @Element2, ...

### Optional
- **elements**: array - Characters or objects for face/identity control, referenced in the prompt as @Element1, @Element2, ... Each element takes a frontal_image_url and optional reference_image_urls.
- **resolution**: string (default: 1K) - Output resolution. 1K and 2K cost the same; 4K costs double per image.
  Options: 1K, 2K, 4K
- **result_type**: string (default: single) - 'single' generates num_images independent images; 'series' generates series_amount related images.
  Options: single, series
- **num_images**: integer (default: 1) - Number of images to generate when result_type is 'single' (1-9). Charged per image.
- **series_amount**: integer - Number of images in the series (2-9). Required when result_type is 'series'. Charged per image.
- **aspect_ratio**: string (default: 16:9) - Aspect ratio of the generated images.
  Options: 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9
- **output_format**: string (default: png) - The format of the generated image.
  Options: jpeg, png, webp

## Examples

### Editorial moss dress
A single 1K editorial image in 16:9.
```json
{
  "model": "fal-ai/kling-image/o3/text-to-image",
  "input": {
    "prompt": "High fashion model wearing a dress made entirely of living moss and small white flowers, standing in an abandoned greenhouse, shafts of light, editorial photography.",
    "resolution": "1K",
    "aspect_ratio": "16:9",
    "output_format": "png",
    "num_images": 1
  }
}
```

### Four-panel story series
A consistent series of four related images at 2K.
```json
{
  "model": "fal-ai/kling-image/o3/text-to-image",
  "input": {
    "prompt": "A small robot explores a rainy neon city: waking up, finding an umbrella, meeting a cat, watching the sunrise.",
    "resolution": "2K",
    "aspect_ratio": "3:4",
    "result_type": "series",
    "series_amount": 4
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- 1K and 2K are the same price — use 2K unless you need smaller files.
- 4K doubles the per-image price; reserve it for final, print-size output.
- In series mode you are charged for series_amount images (num_images is ignored).
- Define characters with elements and refer to them as @Element1 to keep faces consistent.

## Documentation
https://fal.ai/models/fal-ai/kling-image/o3/text-to-image