image-outpainting
Extend and expand images beyond their original boundaries using each::sense AI. Create panoramic views, convert aspect ratios, add backgrounds, and uncrop photos intelligently.
What this skill does
# Image Outpainting / Extension
Extend images beyond their original boundaries using each::sense. This skill uses AI to intelligently generate new content that seamlessly blends with the original image, enabling aspect ratio conversions, background expansion, and creative image extensions.
## Features
- **Horizontal Extension**: Expand images left and right for wider compositions
- **Vertical Extension**: Add content above and below for taller images
- **Aspect Ratio Conversion**: Transform portrait to landscape or vice versa
- **Background Expansion**: Add more context and environment to photos
- **Uncropping**: Recover or imagine content outside the original frame
- **Panoramic Creation**: Turn single images into wide panoramic views
- **Product Photo Enhancement**: Extend product shots for banners and ads
- **Artwork Extension**: Expand illustrations and digital art
## Quick Start
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Extend this image horizontally to create a wider 16:9 composition, maintaining the same style and lighting"}],
"model": "eachsense/beta",
"stream": true,
"image_urls": ["https://example.com/original-photo.jpg"],
"mode": "max"
}'
```
## Common Outpainting Scenarios
| Use Case | Target Ratio | Description |
|----------|--------------|-------------|
| Portrait to Landscape | 16:9 | Convert vertical photos for video/desktop |
| Square to Widescreen | 21:9 | Create cinematic compositions |
| Product Banner | 3:1 or 4:1 | Extend product shots for web banners |
| Social Media | 4:5 or 1:1 | Optimize for Instagram feed |
| Panoramic | 2:1 or 3:1 | Create wide scenic views |
| Full Bleed | Custom | Add margins for printing |
## Use Case Examples
### 1. Extend Image Horizontally
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Extend this image horizontally on both sides. Add more of the natural environment while keeping the subject centered. Maintain consistent lighting, color grading, and style throughout the extension."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": ["https://example.com/landscape-photo.jpg"],
"mode": "max"
}'
```
### 2. Extend Image Vertically
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Extend this image vertically - add more sky above and more ground/foreground below. Keep the horizon line natural and maintain the same atmosphere and time of day."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": ["https://example.com/landscape.jpg"],
"mode": "max"
}'
```
### 3. Convert Portrait to Landscape
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Convert this vertical portrait photo to a horizontal 16:9 landscape format. Extend the background on both sides to create a wider scene. Keep the person as the main subject and ensure the extended areas match the original environment perfectly."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": ["https://example.com/portrait-photo.jpg"],
"mode": "max"
}'
```
### 4. Convert Square to Widescreen
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Transform this square 1:1 image into a cinematic 21:9 widescreen format. Extend the scene horizontally while preserving the central composition. Match the lighting, textures, and visual style seamlessly."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": ["https://example.com/square-image.jpg"],
"mode": "max"
}'
```
### 5. Extend Product Photo for Banner
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Extend this product photo into a wide banner format (approximately 4:1 ratio). Keep the product on the left third of the image and extend the clean background to the right to create space for text overlay. Maintain the same studio lighting and surface texture."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": ["https://example.com/product-shot.jpg"],
"mode": "max"
}'
```
### 6. Add More Background/Context
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Expand this image in all directions to add more environmental context. The subject is too tightly cropped - extend the scene to show more of the surroundings, making it feel less cramped. Keep the original subject size and add approximately 50% more space around it."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": ["https://example.com/tight-crop.jpg"],
"mode": "max"
}'
```
### 7. Uncrop a Cropped Photo
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "This photo has been tightly cropped - uncrop it to reveal more of the scene. Extend downward to show the full body (currently cut off at the waist) and extend the sides to show more of the room interior. Generate realistic content that matches the existing style."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": ["https://example.com/cropped-photo.jpg"],
"mode": "max"
}'
```
### 8. Create Panoramic from Single Image
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Transform this landscape photo into a wide panoramic image with a 3:1 aspect ratio. Extend the scenic view on both left and right sides, continuing the mountain range, sky, and terrain naturally. Create a sweeping vista that feels like a real panoramic photograph."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": ["https://example.com/mountain-view.jpg"],
"mode": "max"
}'
```
### 9. Extend Artwork/Illustration
```bash
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"messages": [{"role": "user", "content": "Extend this digital illustration horizontally to double its width. Continue the artistic style, color palette, and visual elements seamlessly. This is a fantasy landscape illustration - extend the magical forest and atmospheric elements on both sides while maintaining the same painting technique and mood."}],
"model": "eachsense/beta",
"stream": true,
"image_urls": ["https://example.com/fantasy-illustration.jpg"],
"mode": "max"
}'
```
### 10. 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.