p-image-edit-lora

P-Image Edit LoRA combines the speed and quality of P-Image Edit with the flexibility of Low-Rank Adaptation (LoRA) fine-tuning. This enables custom style transfer, character consistency, brand-specific aesthetics, and domain-specific edits using pre-trained LoRA weights from HuggingFace. The model maintains sub-second inference while applying custom adaptations, making it ideal for production workflows requiring consistent styling or specialized editing capabilities.

PrunaAI Image Context N/A
Get API Key
Try in Playground
Free Trial Credit No Credit Card Required
$1.00

api_example.sh

# Option 1: File upload (multipart)
curl -X POST "https://platform.qubrid.com/v1/images/edits" \
  -H "Authorization: Bearer $QUBRID_API_KEY" \
  -F "model=p-image-edit-lora" \
  -F "prompt=Add a rainbow over the mountains" \
  -F "files=@<YOUR-IMAGE-COMPLETE-PATH>"

# Option 2: JSON with image URLs
curl -X POST "https://platform.qubrid.com/v1/images/edits" \
  -H "Authorization: Bearer $QUBRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "p-image-edit-lora",
  "prompt": "Add a rainbow over the mountains",
  "images": [
    "<YOUR-IMAGE-URL-1>",
    "<YOUR-IMAGE-URL-2>"
  ]
}'

Technical Specifications

Model Architecture & Performance

Variant p-image-edit-lora
Model Size Base + LoRA adapters
Quantization Pruna Optimized with LoRA support
Architecture Diffusion-based image editing model with LoRA adapter support
Precision Optimized
License Pruna AI License
Release Date 2026
Developers Pruna AI

Pricing

Pay-per-use, no commitments

Per Image $0.01/Image

API Reference

Complete parameter documentation

Parameter Type Default Description
lora_weights string null HuggingFace URL to LoRA weights. Supports public and private repositories (requires hf_api_token for private).
lora_scale number 1 Controls the strength of LoRA application. Values: -1.0 to 3.0. Higher values apply stronger LoRA effects. Default: 1.0
hf_api_token string null HuggingFace API token for accessing private LoRA weights. Required only for private repositories.
turbo boolean true Enable faster optimizations for quicker inference. Recommended to keep enabled for production use.
aspect_ratio string 16:9 Output aspect ratio. Options: match_input_image, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3.
seed number 1 Random seed for reproducible image edits. Leave empty for random generation. Use same seed for consistent results.
disable_safety_checker boolean false Disable the built-in safety checker for generated images. Use with caution in production environments.
response_format string url Format of the generated image response. Options: url (default), b64_json.

Explore the full request and response schema in our external API documentation

Performance

Strengths & considerations

Strengths Considerations
Supports custom LoRA weights from HuggingFace
Adjustable LoRA strength (-1.0 to 3.0 scale)
Compatible with public and private HuggingFace repositories
Maintains sub-second inference with LoRA applied
Supports 1-5 reference images simultaneously
Strong instruction and prompt adherence
Turbo mode for optimized performance
Reproducible results with seed parameter
Requires LoRA weights to be hosted on HuggingFace
Private LoRA access requires HuggingFace API token
LoRA quality depends on the training quality of the weights
Maximum of 5 images per request
Requires at least one input image (not text-only)
LoRA loading adds slight overhead to first request

Use cases

Recommended applications for this model

Custom style transfer with pre-trained LoRA weights
Character-consistent image editing across multiple images
Brand-specific image transformations and retouching
Domain-specific edits (e.g., architectural, fashion, product photography)
Artistic style application from community LoRA models
Fine-tuned compositing with custom aesthetics
Consistent visual identity across marketing materials

Enterprise
Platform Integration

Docker

Docker Support

Official Docker images for containerized deployments

Kubernetes

Kubernetes Ready

Production-grade KBS manifests and Helm charts

SDK

SDK Libraries

Official SDKs for Python, Javascript, Go, and Java

Don't let your AI control you. Control your AI the Qubrid way!

Have questions? Want to Partner with us? Looking for larger deployments or custom fine-tuning? Let's collaborate on the right setup for your workloads.

"Qubrid enabled us to deploy production AI agents with reliable tool-calling and step tracing. We now ship agents faster with full visibility into every decision and API call."

AI Agents Team

Agent Systems & Orchestration