generate-image
# Generate Image
What this skill does
# Generate Image
Generate images using OpenRouter's image generation API.
## Usage
When the user asks you to generate an image, create a picture, or make visual content, use this command.
## Instructions
1. Extract the image prompt from the user's request
2. Determine any optional parameters:
- **Reference images**: One or more images to use as style/content guidance
- **Aspect ratio**: 1:1, 16:9, 9:16, 4:3, 3:4, etc.
- **Image size**: 1K, 2K, or 4K (Gemini models only)
- **Output filename**: Custom name or auto-generated
- **Model**: Override the default model
3. Run the generation script:
```bash
${CLAUDE_PLUGIN_ROOT}/generate-image.py [OPTIONS] "prompt"
```
The script uses uv for dependency management - dependencies install automatically on first run.
## Options
- `-l, --list-models` - List all available image generation models with pricing
- `-o, --output FILE` - Custom output filename
- `-a, --aspect-ratio RATIO` - Aspect ratio (1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9)
- `-s, --size SIZE` - Image resolution: 1K, 2K, or 4K (Gemini models only)
- `-m, --model MODEL` - Override the model (default: google/gemini-2.0-flash-exp:free)
- `-r, --reference IMAGE` - Reference image for style/content guidance (can be used multiple times)
- `--session NAME` - Create or continue a named session for iterative refinement
- `--continue` - Continue the most recent session
- `--list-sessions` - List all available sessions
- `--delete-session NAME` - Delete a session and all its files
## Examples
```bash
# Simple generation
${CLAUDE_PLUGIN_ROOT}/generate-image.py "A serene mountain landscape at sunset"
# With aspect ratio and filename
${CLAUDE_PLUGIN_ROOT}/generate-image.py -a 16:9 -o sunset.png "Golden sunset over calm ocean"
# High resolution square image
${CLAUDE_PLUGIN_ROOT}/generate-image.py -a 1:1 -s 4K "Detailed portrait of a robot"
# Using a different model
${CLAUDE_PLUGIN_ROOT}/generate-image.py -m "black-forest-labs/flux-1.1-pro" "Abstract art"
# With reference image(s) for style guidance
${CLAUDE_PLUGIN_ROOT}/generate-image.py -r style_reference.png "A castle in this artistic style"
# Multiple reference images
${CLAUDE_PLUGIN_ROOT}/generate-image.py -r style1.png -r style2.png "Combine these styles into a landscape"
# List all available image generation models
${CLAUDE_PLUGIN_ROOT}/generate-image.py --list-models
# Start a session for iterative refinement
${CLAUDE_PLUGIN_ROOT}/generate-image.py --session my-cover -a 2:3 "VHS cover for a horror game"
# Continue refining in the same session (automatically includes previous image)
${CLAUDE_PLUGIN_ROOT}/generate-image.py --session my-cover "Make the title text larger and move it to the bottom"
# Continue the most recent session without specifying the name
${CLAUDE_PLUGIN_ROOT}/generate-image.py --continue "Add more film grain texture"
# List all sessions
${CLAUDE_PLUGIN_ROOT}/generate-image.py --list-sessions
# Delete a session when done
${CLAUDE_PLUGIN_ROOT}/generate-image.py --delete-session my-cover
```
## Sessions
Sessions allow you to have a conversation with the image generation model to iteratively refine your images. When you use `--session NAME`:
1. A new session is created (or continued if it exists)
2. Your prompt and the generated image are saved
3. On subsequent calls, the previous image is automatically uploaded so the model can see and refine it
4. All generated images are copied to the session folder for reference
Session state is stored in `$XDG_STATE_HOME/openrouter-image-gen/sessions/` (defaults to `~/.local/state/openrouter-image-gen/sessions/`).
## Discovering Models
Use `--list-models` to see all available image generation models with their pricing. This queries the OpenRouter API for models with image output capability.
## Output
Images are saved to `$XDG_STATE_HOME/openrouter-image-gen/output/` (defaults to `~/.local/state/openrouter-image-gen/output/`). The script outputs the full paths to generated images. Use the Read tool to view them, then copy to the appropriate location when finalized.
## Setup Required
The script needs an OpenRouter API key. Configure it using one of these methods (checked in order):
1. **Environment variable** (recommended):
```bash
export OPENROUTER_API_KEY=your-key-here
```
2. **Config file** at one of these locations (checked in order):
- `./.openrouter-config` (current directory)
- `~/.config/openrouter/config`
- `~/.openrouter-config`
Config file format:
```
OPENROUTER_API_KEY=your-key-here
```
Get your API key at: https://openrouter.ai/keys
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.