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 and editing 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-edit-lora 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-edit-lora 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/edits"
headers = {
    "Authorization": "Bearer QUBRID_API_KEY"
}

# ─────────────────────────────────────────
# Option 1: File Upload (Multipart)
# ─────────────────────────────────────────
files = [
    ('files', ('input.png', open('<YOUR-IMAGE-COMPLETE-PATH>', 'rb'), 'image/png'))
]
data = {
  "model": "p-image-edit-lora",
  "prompt": "Add a rainbow over the mountains",
  "lora_weights": None,
  "lora_scale": 1,
  "hf_api_token": None,
  "turbo": True,
  "aspect_ratio": "16:9",
  "seed": 1,
  "disable_safety_checker": False,
  "response_format": "url"
}

response = requests.post(url, headers=headers, data=data, files=files)
print(response.json())

# ─────────────────────────────────────────
# Option 2: JSON with Image URLs
# ─────────────────────────────────────────
headers_json = {
    "Authorization": "Bearer QUBRID_API_KEY",
    "Content-Type": "application/json"
}
payload = {
  "model": "p-image-edit-lora",
  "prompt": "Add a rainbow over the mountains",
  "lora_weights": None,
  "lora_scale": 1,
  "hf_api_token": None,
  "turbo": True,
  "aspect_ratio": "16:9",
  "seed": 1,
  "disable_safety_checker": False,
  "response_format": "url"
}
payload["images"] = ["<YOUR-IMAGE-URL-1>", "<YOUR-IMAGE-URL-2>"]

response = requests.post(url, headers=headers_json, json=payload)
print(response.json())

​
Model Overview

P-Image Edit LoRA is an image editing variant of the P-Image model developed by Pruna AI, combining text-guided image editing with LoRA (Low-Rank Adaptation) support for fine-tuned style control.
  • It extends P-Image Edit with the ability to apply custom LoRA weights at inference time, enabling domain-specific visual style adaptation during the editing process.
  • The model supports an optional turbo mode for faster inference while maintaining editing quality.
  • P-Image Edit LoRA is suitable for production workflows requiring both precise image editing and lightweight style customization through LoRA adapters.

​
Model at a Glance

FeatureDetails
Model IDp-image-edit-lora
ProviderPruna AI
Model TypeText-Guided Image Editing with LoRA Support
ArchitectureOptimized latent diffusion model with image conditioning and LoRA adapter support
Input TypeImage file upload or image URL
Output TypeEdited image based on text prompt with optional LoRA style control

​
When to use?

You should consider using P-Image Edit LoRA if:
  • You need text-guided image editing with custom LoRA style control
  • Your application requires domain-specific visual adaptation during the editing process without full model retraining
  • You want optional turbo mode for faster inference without significantly compromising editing quality
  • You need flexible input support via file upload or image URLs with Hugging Face LoRA integration

​
Inference Parameters

Parameter NameTypeDefaultDescription
Promptstring—Text instruction describing the desired edit.
LoRA WeightsstringnullPath or identifier of the LoRA weights to apply at inference.
LoRA Scalenumber1Strength of the LoRA adapter effect on the output image.
HF API TokenstringnullHugging Face API token required for accessing private LoRA weights.
TurbobooleantrueEnables turbo mode for faster inference.
Aspect Ratiostring16:9Output image aspect ratio.
Seednumber1Random seed for reproducibility.
Disable Safety CheckerbooleanfalseDisables the built-in safety filter if enabled.
Response FormatstringurlFormat of the response — url or b64_json.

​
Key Features

  • LoRA Style Control: Supports custom LoRA weights at inference time for domain-specific visual style adaptation during image editing without full model retraining.
  • Text-Guided Image Editing: Performs precise modifications to existing images based on natural language instructions while preserving visual fidelity.
  • Turbo Mode: Optional accelerated inference mode for faster editing results in production-scale workflows.
  • Hugging Face Integration: Accepts Hugging Face API tokens for seamless access to private or community LoRA weights.
  • Flexible Input Support: Accepts both multipart file uploads and JSON-based image URLs for seamless integration into diverse workflows.

​
Summary

P-Image Edit LoRA is a fast, customizable text-guided image editing model built by Pruna AI for production-scale workflows.
  • It extends P-Image Edit with LoRA adapter support for lightweight style customization at inference time.
  • The model supports turbo mode for accelerated inference and Hugging Face integration for LoRA weight access.
  • It is suitable for developers and enterprises requiring scalable image editing with domain-specific visual style control.