skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

p-image

Generate and edit images with Pruna P-Image models via the inference.sh CLI.

Updated Jul 28, 2026
Search Tags:#image generation#image editing#text-to-image#lora#inference.sh#pruna#p-image
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill p-image-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: p-image
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/p-image
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill p-image-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating AI-generated images often requires managing model hosting, GPU infrastructure, and complex SDKs. This Skill lets you generate, edit, and composite images directly from the command line using Pruna's speed-optimized P-Image models through the inference.sh platform. ## Core Features & Use Cases - Text-to-Image Generation: Create images from text prompts with multiple aspect ratios (1:1, 16:9, 9:16, and custom dimensions) using the pruna/p-image app. - LoRA Style Presets: Apply built-in styles like photos-realism, pixel-art, anime-2-5d, and cinematic-movie-style with pruna/p-image-lora. - Image Editing & Compositing: Edit existing images or combine multiple images into collages with pruna/p-image-edit. - Use Case: A content creator needs a stylized hero image for a blog post. They run a single belt command with a prompt and the cinematic-movie-style LoRA preset to get a finished image in seconds. ## Quick Start Ask the AI to generate an image of a futuristic cityscape at sunset using the Pruna P-Image model via the belt CLI.

Frequently Asked Questions about p-image

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate an image with Pruna P-Image?▼

Run belt app run pruna/p-image with a JSON input containing your prompt, for example {"prompt": "a futuristic cityscape at sunset"}. You must first install the inference.sh belt CLI and authenticate with belt login.

What LoRA presets are available in P-Image-LoRA?▼

P-Image-LoRA includes built-in presets: photos-realism, pixel-art, japanese-modern-look, cinematic-movie-style, graffiti-splash, neon-punk, anime-2-5d, ethereal-portrait, retro-90s-style, ink-sketchbook, and paper-cut. Pass the preset name in the lora_preset input field.

Can P-Image-Edit combine multiple images?▼

Yes, pruna/p-image-edit accepts an array of image URLs in the images input field. Provide two or more URLs with a prompt like "combine these images into a collage" to perform multi-image compositing.

What aspect ratios does P-Image support?▼

P-Image supports 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3 aspect ratios via the aspect_ratio input parameter. You can also select custom and specify exact width and height values.

What other Pruna models are available on inference.sh?▼

Pruna offers optimized versions of FLUX Dev, FLUX Klein 4B, Qwen Image, Z-Image Turbo, and WAN Image Small. List all available Pruna apps by running belt app list --namespace pruna.

Related Skills

Explore More Design & Creative Skills→
inference-shinference-sh
723

gpt-image

Generate and edit images with OpenAI GPT-Image-2 via the inference.sh CLI.

Official
Basic
AugustEmnaAugustEmna

media-generation

Generate AI images, videos, and stock images from text prompts.

Community
Intermediate
inference-shinference-sh
688

p-video

Generate videos from text or images using Pruna models via inference.sh CLI.

Official
Intermediate
inference-shinference-sh
688

flux-image

Generate images with FLUX models via the inference.sh CLI.

Official
Intermediate