P-Image
Pruna's P-Image is an ultra-fast text-to-image model with automatic prompt enhancement and 2-stage refinement, combining exceptional speed with high-quality output and flexible aspect ratios.
Quick start
# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/infer \
-H "content-type: application/json" \
-d '{
"model": "pruna/p-image",
"prompt": <string>
}'
# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/infer \
-J '{"model": "pruna/p-image", "prompt": "<string>"}'Examples
Parameters
Aspect ratio for the image. Use "custom" with width/height for exact dimensions.
Disable safety checker for generated images.
Custom height in pixels (256-1440, multiple of 16). Only used when aspect_ratio="custom".
HuggingFace API token for accessing private LoRAs. This credential is forwarded verbatim to Pruna. It is only written to gateway request-body logs when the gateway-level collectLogPayload debug flag is explicitly enabled — it never appears in structured analytics logs.
How strongly the LoRA should be applied (-1 to 3).
Load LoRA weights. Supports HuggingFace URLs in the format huggingface.co/<owner>/<model-name>[/<file.safetensors>].
Text description of the image to generate. The model automatically enhances prompts for better results.
Upsample the prompt with an LLM for enhanced results.
Random seed for reproducible generation.
Custom width in pixels (256-1440, multiple of 16). Only used when aspect_ratio="custom".