All models

P-Image-Edit

pruna/p-image-edit
Pruna Image EditingImage-to-ImageComposition

Pruna's P-Image-Edit edits and composes 1-5 reference images with text instructions. It supports complex compositions, style transfers, and targeted edits with flexible output 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-edit",
    "prompt": "<your prompt>",
    "images": ["https://example.com/input.jpg"]
  }'

# 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-edit", "prompt": "<your prompt>", "images": ["https://example.com/input.jpg"]}'

Examples

example

Parameters

Input
images array required

Array of 1-5 reference images. Each entry is an HTTP(S) URL or a base64 data URI (data:image/...;base64,...).

prompt string required

Text instruction describing the desired edit or composition.

aspect_ratio string optional default: "match_input_image"

Output aspect ratio.

disable_safety_checker boolean optional default: false

Disable safety checker for generated images.

seed integer optional

Random seed for reproducible generation.

turbo boolean optional default: true

Run faster with additional optimizations. For complicated tasks, it is recommended to turn this off.

Output
image: model output URL