Skip to main content

​
About the Provider

Pruna AI is an AI optimization company focused on making state-of-the-art image generation fast, affordable, and accessible. Their P-Image model family is designed to deliver professional-quality image generation with sub-second inference speeds, strong prompt adherence, and support for fine-tuning and LoRA-based customization.

​
Model Quickstart

This section helps you quickly get started with the p-image model on the Qubrid AI inferencing platform. To use this model, you need:
  • A valid Qubrid API key
  • Access to the Qubrid inference API
  • Basic knowledge of making API requests in your preferred language
Once authenticated with your API key, you can send inference requests to the p-image model and receive responses based on your input prompts. Below are example placeholders showing how the model can be accessed using different programming environments.
You can choose the one that best fits your workflow. 
import requests
import json
 
url = "https://platform.qubrid.com/v1/images/generations"
headers = {
    "Authorization": "Bearer QUBRID_API_KEY",
    "Content-Type": "application/json"
}
 
data = {
  "model": "p-image",
  "prompt": "cinematic shot of a lone astronaut standing on a desolate alien planet, glowing orange sunset sky, dust storms swirling, dramatic lighting, ultra-wide lens composition, movie still aesthetic, realistic space suit details, volumetric atmosphere, 8k sci-fi film scene",
  "aspect_ratio": "16:9",
  "width": 1440,
  "height": 1440,
  "seed": 0,
  "disable_safety_checker": False,
  "response_format": "url"
}
 
response = requests.post(url, headers=headers, json=data)
 
if response.status_code == 200:
    with open("generated_image.png", "wb") as f:
        f.write(response.content)
        print("Image saved to generated_image.png")
else:
    print(f"Error: {response.status_code}")
    print(response.text)

​
Model Overview

P-Image is a text-to-image generation model developed by Pruna AI, designed for high-quality image synthesis at sub-second inference speeds.
  • It is optimized for cost efficiency and speed without sacrificing visual quality or prompt adherence.
  • The model supports fine-tuning and LoRA-based customization, enabling domain-specific style adaptation.
  • P-Image is suitable for production workflows requiring fast, scalable, and high-fidelity image generation.

​
Model at a Glance

FeatureDetails
Model IDp-image
ProviderPruna AI
Model TypeText-to-Image Generation
ArchitectureOptimized latent diffusion model with sub-second inference
Default Resolution1440 × 1440
Output TypeImages generated from text prompts

​
When to use?

You should consider using P-Image if:
  • You need high-quality text-to-image generation at sub-second speeds
  • Your application requires cost-efficient, scalable image generation
  • You want strong prompt adherence with support for diverse visual styles
  • You need fine-tuning or LoRA-based customization for domain-specific outputs

​
Inference Parameters

Parameter NameTypeDefaultDescription
Aspect Ratiostring16:9Output image aspect ratio.
Widthnumber1440Image width in pixels.
Heightnumber1440Image height in pixels.
Seednumber0Random seed for reproducibility.
Disable Safety CheckerbooleanfalseDisables the built-in safety filter if enabled.
Response FormatstringurlFormat of the response — url or b64_json.

​
Key Features

  • Sub-Second Inference: Generates high-quality images in under one second, optimized for production speed and cost efficiency.
  • Strong Prompt Adherence: Delivers accurate visual outputs across a wide range of text prompts and styles.
  • Fine-Tuning Support: Supports model fine-tuning and LoRA-based style customization for domain-specific use cases.
  • Flexible Resolution Control: Configurable width, height, and aspect ratio for diverse output requirements.
  • Safety Controls: Built-in safety checker with optional override for appropriate use cases.

​
Summary

P-Image is a fast, affordable, and high-quality text-to-image model built by Pruna AI for production-scale image generation.
  • It delivers sub-second inference speeds while maintaining strong visual quality and prompt adherence.
  • The model supports fine-tuning and LoRA customization for style-specific applications.
  • It is suitable for developers and enterprises requiring scalable, cost-efficient image generation workflows.