p-image-edit

Use when the user wants to edit an existing image, change wardrobe or background, compose from reference photos, inpaint-style adjustments, or multi-image edits from a prompt.

Pruna AI@pruna-ai

Install

openclaw skills install @pruna-ai/p-image-edit

p-image-edit (Pruna)

Premium edit and multi-image composition. Full parameters: p-image-edit model docs.

Shared HTTP patterns: pruna-api.md (upload, poll, download)

HTTP (curl)

Upload references

bash

curl -X POST "https://api.pruna.ai/v1/files" \
  -H "apikey: ${PRUNA_API_KEY}" \
  -F "content=@/path/to/reference.png"

Use each response urls.get in input.images.

Create (async — recommended)

bash

curl -X POST 'https://api.pruna.ai/v1/predictions' \
  -H 'Content-Type: application/json' \
  -H "apikey: ${PRUNA_API_KEY}" \
  -H 'Model: p-image-edit' \
  -d '{
    "input": {
      "prompt": "Change background to soft gradient, keep subject identical",
      "images": ["https://api.pruna.ai/v1/files/FILE_ID"],
      "aspect_ratio": "9:16"
    }
  }'

Poll and download: pruna-api.md.

Before generating

Generation diversity — ritual seed + axis rotation when the job accepts seed or you need a logged run_id.
Confirm prompt, which reference files to upload (1–5), aspect_ratio, and turbo on/off with the user. Run p-image-edit-quality-checklist.md on outputs.

Avatar pipelines: edit from the locked upscaled hero URL. Chain: p-image-edit → p-image-upscale → slop gate → p-video-avatar. Never pass raw edit URLs to video models. See multi-scene-avatar-video.

Multi-scene narrated films: generate start still (edit_prompt) and end still (last_frame_edit_prompt) per scene for the scene anchor triple. Run all scene edits in parallel after the hero anchor exists (parallel-execution.md). See multi-scene-ai-video.

Visual transition reels: same start/end still pattern for the scene anchor pair — see scene-transition-video.

Prerequisites

Upload each reference to POST https://api.pruna.ai/v1/files (multipart content=@file). Use each file’s urls.get value in input.images.

Required input

prompt (string)
images (array of 1–5 URLs, typically https://api.pruna.ai/v1/files/{id})

Common optional fields

aspect_ratio: match_input_image, 1:1, 16:9, 9:16, etc.
turbo (boolean, default true; turn off for harder edits)
seed, disable_safety_checker

Example: synchronous single-image edit

bash

curl -X POST 'https://api.pruna.ai/v1/predictions' \
  -H 'Content-Type: application/json' \
  -H "apikey: ${PRUNA_API_KEY}" \
  -H 'Model: p-image-edit' \
  -H 'Try-Sync: true' \
  -d '{
    "input": {
      "prompt": "Change background to soft gradient, keep subject identical",
      "images": ["https://api.pruna.ai/v1/files/FILE_ID"],
      "aspect_ratio": "9:16"
    }
  }'

Typical next steps

Upscale for delivery: p-image-upscale
Motion: p-video with scene anchor pair, scene anchor triple, or p-video-avatar
Pipeline: pruna-generative-pipeline

Related workflow

Multi-scene avatar + animate reels: multi-scene-avatar-video — phased curl or local slider script (not in this tool skill).