# Imagen 4 Fast - Core.Today AI API

> A fast version of Imagen 4 for when speed and cost are more important than maximum quality.

- **Provider**: Google
- **Model ID**: google/imagen-4-fast
- **Category**: Image Generation
- **Credits**: 46 per image
- **Speed**: Fast
- **Quality**: Standard

## Features
- Lowest-cost tier in the Imagen 4 family
- Fast generation optimized for iteration speed
- Configurable safety filter strictness
- Common aspect ratio presets for social and marketing use

## Use Cases
- High-volume, budget-conscious image generation
- Rapid prototyping before committing to google/imagen-4
- Social media content at speed
- Draft visuals for internal review

## 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

### Optional
- **aspect_ratio**: string (default: 1:1) - Aspect ratio of the generated image
  Options: 1:1, 9:16, 16:9, 3:4, 4:3
- **safety_filter_level**: string (default: block_only_high) - block_low_and_above is strictest; block_only_high is most permissive
  Options: block_low_and_above, block_medium_and_above, block_only_high
- **output_format**: string (default: jpg) - Format of the output image
  Options: jpg, png

## Examples

### Action Film Style
A dynamic, high-energy action-film-style shot
```json
{
  "model": "google/imagen-4-fast",
  "input": {
    "prompt": "The photo: Create a cinematic, photorealistic medium shot capturing the dynamic energy of a high-octane action film.",
    "aspect_ratio": "4:3",
    "output_format": "jpg"
  }
}
```

## 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
- Use this model for iteration and drafts, then switch to google/imagen-4 for final, higher-quality output
- The half-price rate compared to Imagen 4 makes this well-suited for high-volume batch generation
- Loosen safety_filter_level to block_only_high (default) only when content is not sensitive
- Same aspect_ratio options as Imagen 4 for consistent framing across both tiers

## Documentation
https://replicate.com/google/imagen-4-fast