p-image-lora

P-Image LoRA combines ultra-fast image generation with customizable style adaptation through LoRA weights. Apply community-trained or custom LoRA models from HuggingFace to achieve specific artistic styles, characters, or visual themes while maintaining sub-second generation speed.

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

api_example.sh

curl -X POST "https://platform.qubrid.com/v1/images/generations" \
  -H "Authorization: Bearer $QUBRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "p-image-lora",
  "positive_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"
}'

Technical Specifications

Model Architecture & Performance

Variant Optimized with LoRA support
Model Size Not publicly disclosed
Quantization Proprietary optimization
Architecture Optimized diffusion model with LoRA adapter support
Precision Mixed precision
License Proprietary
Release Date 2026
Developers Pruna AI

Pricing

Pay-per-use, no commitments

Per Image $0.005/Image

API Reference

Complete parameter documentation

Parameter Type Default Description
lora_weights string null HuggingFace URL to LoRA weights for style adaptation (e.g., 'username/model-name').
lora_scale number 1 Strength of LoRA application. Range: -1.0 to 3.0. Higher values = stronger style influence.
hf_api_token string null HuggingFace API token required for accessing private LoRA weights.
aspect_ratio string 16:9 Aspect ratio for the output image. Options: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, custom.
width number 1024 Custom width in pixels (256-1440), used only when aspect_ratio is 'custom'. Must be multiple of 16.
height number 1024 Custom height in pixels (256-1440), used only when aspect_ratio is 'custom'. Must be multiple of 16.
seed number 0 Random seed for reproducible generation.
prompt_upsampling boolean false Use LLM to enhance and expand the prompt for better results.
disable_safety_checker boolean false Optional flag to disable built-in safety check for generated images.
response_format string url Format of the generated image response. Options: url (default), b64_json (base64).

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

Performance

Strengths & considerations

Strengths Considerations
Ultra-fast generation (~<1 second per image)
Flexible LoRA integration from HuggingFace
Adjustable style strength with lora_scale
Support for private LoRA models
Optional prompt enhancement
LoRA quality depends on training data
Requires valid HuggingFace LoRA weights
Private LoRAs need API token

Use cases

Recommended applications for this model

Custom style generation
Character consistency
Brand-specific imagery
Fine-tuned creative workflows
Rapid style prototyping

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 scaled our personalized outreach from hundreds to tens of thousands of prospects. AI-driven research and content generation doubled our campaign velocity without sacrificing quality."

Demand Generation Team

Marketing & Sales Operations