# Kling O3 Image Text to Image

> 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**: fal
- **Model ID**: fal-ai/kling-image/o3/text-to-image
- **Category**: image_generation
- **Credits**: 66 per request
- **Pricing Type**: input_based

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `result_type` (string, optional): 'single' generates num_images independent images; 'series' generates series_amount related images (a consistent set). (Default: `single`; Options: `single`, `series`)
- `aspect_ratio` (string, optional): Aspect ratio of the generated images. (Default: `16:9`; Options: `16:9`, `9:16`, `1:1`, `4:3`, `3:4`, `3:2`, `2:3`, `21:9`)
- `output_format` (string, optional): The format of the generated image. (Default: `png`; Options: `jpeg`, `png`, `webp`)
- `elements` (array, optional): Characters or objects for face/identity control, referenced in the prompt as @Element1, @Element2, ...
- `series_amount` (integer, optional): Number of images in the series (2-9). Required and used only when result_type is 'series'. Charged per image. (Range: min: 2, max: 9)
- `prompt` (string, **required**): Text prompt for image generation. Reference character elements as @Element1, @Element2, ... Max 2500 characters.
- `resolution` (string, optional): Output resolution. 1K is standard and 2K high-res (same price); 4K is ultra high-res and costs double per image. (Default: `1K`; Options: `1K`, `2K`, `4K`)
- `num_images` (integer, optional): Number of images to generate when result_type is 'single'. Charged per image. (Default: `1`; Range: min: 1, max: 9)

## Example Request

```json
{
  "model": "fal-ai/kling-image/o3/text-to-image",
  "input": {
    "aspect_ratio": "16:9",
    "output_format": "png",
    "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",
    "num_images": 1
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

json

## Tags

text-to-image, kling

## Documentation

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