$npx skillfedfor your agent

P Image

P Image lets you create and edit images using Pruna's speed-optimized models through the inference.sh CLI. Choose from four variants: standard text-to-image generation, LoRA-based styling, image editing with multi-image support, or stylized editing. Supports multiple aspect ratios and includes preset styles like cinematic, pixel art, and anime.

P Image generates images via Pruna's optimized models, supporting text-to-image, editing, LoRA styles, and multi-image compositing.

AI-generated summary based on this skill's SKILL.md

★ 660  94 unlicensed, metadata onlyupdated by inference-sh

Decision gist · record as of 2026-07-26

P Image generates images via Pruna's optimized models, supporting text-to-image, editing, LoRA styles, and multi-image compositing. P Image lets you create and edit images using Pruna's speed-optimized models through the inference.sh CLI. Choose from four variants: standard text-to-image generation, LoRA-based styling, image editing with multi-image support, or stylized editing. Supports multiple aspect ratios and includes preset styles like cinematic, pixel art, and anime.

manual: git clone https://github.com/inference-sh/skills → cp -r skills ~/.claude/skills/p-image

Use it when

  • P Image integrates with the inference.sh CLI to streamline image workflows.
  • P Image capabilities include text-to-image generation, LoRA styling for personalized looks, multi-image editing support.
Same gist for agents: .md · .json

Install

inference-sh/skills/p-image · repository language: Shell

generated, unverified - the skill's exact subdirectory could not be determined; check the repository on GitHub

Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

What is P Image and what can it do?

P Image lets you create and edit images using Pruna's speed-optimized models through the inference.sh CLI. The skill offers four variants: standard text-to-image generation, LoRA-based styling, image editing with multi-image support, or stylized editing. P Image supports multiple aspect ratios and includes preset styles like cinematic, pixel art, and anime.

How to use P Image for image generation and editing?

P Image integrates with the inference.sh CLI to streamline image workflows. You can generate images from text prompts, apply LoRA-based styling for custom aesthetics, edit existing images with multi-image support, or create stylized variations. The skill's speed-optimized models ensure fast processing across all four generation and editing variants.

What are the key features and capabilities of P Image?

P Image capabilities include text-to-image generation, LoRA styling for personalized looks, multi-image editing support, and stylized editing options. The skill supports various aspect ratios to match your design needs and provides preset styles—cinematic, pixel art, and anime—ready to apply immediately to your image projects.

How do I integrate P Image into my workflow?

P Image integrates through the inference.sh CLI, making it straightforward to add to existing pipelines. Select your variant based on your need—standard generation, LoRA styling, multi-image editing, or stylized editing—then configure your aspect ratio and style preferences. The speed-optimized models ensure efficient processing within your workflow.

What documentation or setup instructions exist for P Image?

P Image documentation and setup guidance are available through the inference.sh platform. Start by accessing the P Image skill through the CLI, then choose your desired variant and configure parameters like aspect ratio and preset styles. Detailed tutorials and configuration options help you get started quickly with image creation and editing tasks.

Let your AI agent find skills like this

Example. Real query, live index.

You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.

wish › “Understand what P Image skill does and its core functionality”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

Flux Image
by inference-sh · inference-sh/skills

Flux Image taps FLUX models through the inference.sh CLI to create images from text prompts, image inputs, or custom-styled variations. Choose between high-quality Dev LoRA for production work or the faster Klein variant for rapid iteration.

no license declared → metadata onlyupdated Jul 2026
★ 660repo stars
Image Upscaling
by inference-sh · inference-sh/skills

Image Upscaling enlarges low-resolution photos, AI-generated art, and old pictures to higher resolution while maintaining clarity. It offers multiple upscaling models including Topaz Image Upscaler, Real-ESRGAN, and FLUX Dev Upscaler, each suited for different enhancement needs from professional prints to web displays.

no license declared → metadata onlyupdated Jul 2026
★ 660repo stars
Happyhorse
by inference-sh · inference-sh/skills

HappyHorse 1.0 is a video generation and editing skill powered by Alibaba's models, accessible via the inference.sh CLI. Create physically realistic videos from text prompts, animate still images, preserve characters across multiple reference photos, or edit existing footage with natural language instructions—all at 720P or 1080P up to 15 seconds.

no license declared → metadata onlyupdated Jul 2026
★ 660repo stars
Og Image Design
by inference-sh · inference-sh/skills

OG Image Design helps you create social sharing images optimized for Facebook, Twitter, LinkedIn, and other platforms. It provides platform-specific dimensions, design rules for text and safe zones, and ready-to-use templates for blog posts, product launches, and tutorials.

no license declared → metadata onlyupdated Jul 2026
★ 660repo stars
Agent Tools
by inference-sh · inference-sh/skills

Agent Tools equips your AI agent with a unified CLI to invoke hundreds of cloud-hosted AI models and services. Generate images and videos, call LLMs like Claude and Gemini, perform web searches, automate Twitter, and create 3D models—all without managing GPUs or infrastructure.

no license declared → metadata onlyupdated Jul 2026
★ 660repo stars
Seedance
by inference-sh · inference-sh/skills

Seedance creates videos from text, images, or reference material with built-in audio generation via ByteDance's Seedance 2.0 model. Choose from standard, fast, or studio variants supporting up to 1080p resolution and 4-15 second durations for social media, product demos, and animated content.

no license declared → metadata onlyupdated Jul 2026
★ 660repo stars
Tags
image-processingvisual-analysismedia-handlinginference-engineautomation-tool