stability-ai

Generate high-quality images via Stability AI API (SDXL, SD3, Stable Image Core). Use when user asks to "generate image", "make a picture", or "draw this".

3,891 stars
Complexity: easy

About this skill

The Stability AI Skill empowers AI agents to generate diverse and high-quality images directly through the Stability AI API. It provides a robust interface to popular models like SDXL, SD3, and Stable Image Core, allowing users to create visuals ranging from realistic photographs to fantastical art. The skill is designed for programmatic image creation, enabling agents to interpret user prompts and execute sophisticated generation commands. This skill is highly versatile, supporting various parameters such as specific aspect ratios (e.g., 16:9, 1:1), numerous style presets (e.g., anime, cinematic, pixel-art), and advanced controls like negative prompts, seed values for reproducibility, and custom steps/CFG scales. It streamlines the process of integrating powerful image generation capabilities into AI workflows, making it ideal for content creation, digital art projects, and visual prototyping. Users would leverage this skill to quickly produce visual assets, explore creative concepts, or integrate dynamic image generation into larger automated tasks. The output includes a local image file in various formats (PNG, JPG, WebP) along with comprehensive JSON metadata, ensuring transparency and reproducibility of generated content.

Best use case

This skill's primary use case is for AI agents or users who need to generate custom images based on text prompts, controlling various artistic and technical parameters. It benefits digital artists, content creators, marketers, and developers looking to automate visual content creation or integrate powerful image generation into their applications and workflows.

Generate high-quality images via Stability AI API (SDXL, SD3, Stable Image Core). Use when user asks to "generate image", "make a picture", or "draw this".

A high-quality image file (PNG, JPG, or WebP) saved to a local path, accompanied by a JSON file containing all generation metadata.

Practical example

Example input

Generate a cyberpunk street at night with neon lights, in a 16:9 aspect ratio and a neon-punk style.

Example output

Image generated: `/path/to/generated_image_123.jpg`. Metadata saved: `/path/to/generated_image_123.json`

When to use this skill

  • When a user asks to "generate image", "make a picture", or "draw this".
  • To create visual content for websites, social media, or presentations from text descriptions.
  • When specific artistic styles, aspect ratios, or advanced generation parameters are required.
  • For rapid prototyping of visual concepts or generating diverse image variations.

When not to use this skill

  • When an existing image needs editing, modification, or upscaling (this skill is for generation).
  • If offline image generation is required, as it relies on an active API key and internet connection.
  • For tasks requiring real-time video generation or 3D model creation.
  • If the generated image quality or specific style presets do not meet highly niche, specialized requirements.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/stability-ai/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/1999azzar/stability-ai/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/stability-ai/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How stability-ai Compares

Feature / Agentstability-aiStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityeasyN/A

Frequently Asked Questions

What does this skill do?

Generate high-quality images via Stability AI API (SDXL, SD3, Stable Image Core). Use when user asks to "generate image", "make a picture", or "draw this".

How difficult is it to install?

The installation complexity is rated as easy. You can find the installation instructions above.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Stability AI Skill

## Setup
1. Copy `.env.example` to `.env`.
2. Set `STABILITY_API_KEY` in `.env`.
3. Optional: Set `API_HOST` if using a custom endpoint.

## Usage
- **Role**: Digital Artist.
- **Trigger**: "Draw a cat", "Generate cyberpunk city", "Create an image".
- **Output**: Local file path to the generated image and JSON metadata.

## Commands
(The script automatically handles dependencies on first run)

```bash
# Basic generation
scripts/generate "A futuristic city with neon lights"

# Aspect ratio (1:1, 16:9, 9:16, 21:9, 4:3, 3:4)
scripts/generate "Landscape painting" --ratio 16:9

# Style preset
scripts/generate "Portrait of a warrior" --style photographic

# Seed for reproducibility
scripts/generate "Abstract art" --seed 42

# Negative prompt
scripts/generate "Beautiful sunset" --negative "blurry, low quality"

# Output format (png, jpg, webp)
scripts/generate "Nature scene" --format webp

# Advanced: Custom model, steps, CFG scale
scripts/generate "Fantasy landscape" \
  --model stable-diffusion-3-medium \
  --steps 50 \
  --cfg 7.0 \
  --ratio 21:9

# V2 API (experimental)
scripts/generate "Modern architecture" --v2

# Combined options
scripts/generate "Cyberpunk street at night" \
  --ratio 16:9 \
  --style neon-punk \
  --seed 123 \
  --format jpg \
  --steps 45 \
  --cfg 6.5
```

## Features

### Style Presets
Available styles: enhance, anime, photographic, digital-art, comic-book, fantasy-art, line-art, analog-film, neon-punk, isometric, low-poly, origami, modeling-compound, cinematic, 3d-model, pixel-art, tile-texture

### Aspect Ratios
Supported: 1:1 (default), 16:9, 9:16, 21:9, 4:3, 3:4

### Output Formats
- PNG (default, lossless)
- JPEG/JPG (lossy, smaller size)
- WebP (modern, efficient)

### Metadata
Each generated image includes a JSON metadata file with:
- Prompt and negative prompt
- Model, parameters, and settings
- Generation timestamp
- API version used

## Models
- Default: SDXL 1.0 (`stable-diffusion-xl-1024-v1-0`)
- See `references/models.md` for complete model list, API versions, and credit costs.

## Auto-Cleanup
Automatically keeps the last 20 generated images. Older files and their metadata are removed to save disk space.

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation

openclaw-youtube

3891
from openclaw/skills

YouTube SERP Scout for agents. Search top-ranking videos, channels, and trends for content research and competitor tracking.

Content & Documentation

openclaw-media-gen

3891
from openclaw/skills

Generate images & videos with AIsa. Gemini 3 Pro Image (image) + Qwen Wan 2.6 (video) via one API key.

Content & Documentation

Cold Email Writer

3891
from openclaw/skills

Writes personalized cold emails that actually get replies

Content & Documentation

Presentation Mastery — Complete Slide Design & Delivery System

3891
from openclaw/skills

You are a Presentation Architect. You help build presentations that persuade, inform, and move people to action. You cover the full lifecycle: audience analysis → narrative structure → slide design → delivery coaching → post-presentation follow-up.

Content & Documentation

ai-humanizer

3891
from openclaw/skills

Rewrites AI-generated content to sound natural, human, and undetectable. Removes robotic patterns, adds voice variety, and preserves meaning.

Content & Documentation

Employee Handbook Generator

3891
from openclaw/skills

Build a complete, customized employee handbook for your company. Covers policies, benefits, conduct, leave, remote work, DEI, and compliance — ready for legal review.

Content & Documentation

afrexai-copywriting-mastery

3891
from openclaw/skills

Write high-converting copy for any medium — landing pages, emails, ads, UX, sales pages, video scripts, and brand voice. Complete methodology with frameworks, templates, scoring rubrics, and swipe files. Use when writing or reviewing any user-facing text.

Content & Documentation

afrexai-conversion-copywriting

3891
from openclaw/skills

Write high-converting copy for any surface — landing pages, emails, ads, sales pages, product descriptions, CTAs, video scripts, and more. Complete conversion copywriting system with research methodology, 12 proven frameworks, swipe-file templates, scoring rubrics, and A/B testing protocols. Use when you need to write or review any copy meant to drive action.

Content & Documentation