# Pruna P-Image

> Pruna AI's distilled text-to-image model optimized for extremely low-cost, high-throughput generation. One of the most-run community models on Replicate (15.6M+ runs) thanks to its speed and price.

- **Provider**: replicate
- **Model ID**: prunaai/p-image
- **Category**: image_generation
- **Credits**: 12 per request
- **Pricing Type**: fixed

## 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

- `aspect_ratio` (string, optional): Aspect ratio for the generated image. (Default: `16:9`; Options: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `custom`)
- `disable_safety_checker` (boolean, optional): Disable safety checker for generated images. (Default: `False`)
- `seed` (integer, optional): Random seed. Set for reproducible generation.
- `lora_scale` (number, optional): Determines how strongly the main LoRA should be applied. 0.5 usually works well for most LoRAs. (Default: `0.5`; Range: min: -1, max: 3)
- `prompt_upsampling` (boolean, optional): Upsample the prompt with an LLM. (Default: `False`)
- `width` (integer, optional): Width of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16. (Range: min: 256, max: 1440)
- `lora_weights` (string, optional): Load LoRA weights. Supports HuggingFace URLs in the format huggingface.co/<owner>/<model-name>[/<lora-weights-file.safetensors>]. HuggingFace LoRAs may require an API token to access, which you can provide in the `hf_api_token` input.
- `prompt` (string, **required**): Text prompt for image generation.
- `hf_api_token` (string, optional): HuggingFace API token. If you're using a HuggingFace LoRAs that needs authentication, you'll need to provide an API token.
- `height` (integer, optional): Height of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16. (Range: min: 256, max: 1440)

## Example Request

```json
{
  "model": "prunaai/p-image",
  "input": {
    "prompt": "your prompt here"
  }
}
```

## 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

url

## Tags

prunaai, text-to-image, image-generation, fast-generation

## Documentation

https://replicate.com/prunaai/p-image