Skip to content
remotion-thumbnail logo

Remotion Thumbnail Generator

remotion-thumbnail

Generate professional YouTube thumbnails with AI-powered expression cutouts and Remotion rendering. Perfect for content creators who want consistent, high-quality thumbnails at scale.

SKILL.md

Full skill instructions

Remotion Thumbnail Generator

Generate professional YouTube thumbnails using your own expression cutouts and Remotion's powerful rendering engine.

What This Skill Does

This skill helps you create consistent, high-quality YouTube thumbnails by:

  1. Capturing your expressions - Guide you through 25 preset expressions
  2. Creating cutouts - Automatically remove backgrounds using AI
  3. Generating thumbnails - Render professional thumbnails with custom text, backgrounds, and styles

Quick Start

Prerequisites

  • Node.js 18 or higher
  • Replicate API key (for background removal) - Get one at https://replicate.com
  • A webcam or camera for capturing expressions

Installation

The skill files should be in your agent's skills directory. The renderer is a self-contained Remotion project.

# Install renderer dependencies
cd <skill-dir>/​renderer
npm install

Set Up Your Environment

# Set your Replicate API key
export REPLICATE_API_TOKEN="your-api-key-here"

Workflow

Phase 1: Capture Expressions

Run the interactive capture script to photograph yourself in 25 different expressions:

node <skill-dir>/​scripts/​capture.js

What it does:

  • Shows you each expression to capture (e.g., "Happy/​Smiling", "Shocked", "Pointing Up")
  • Tells you where to save each photo
  • Tracks which expressions you've captured
  • Saves metadata to storage/​expressions_db.json

Tips:

  • Use good lighting (natural light from a window works great)
  • Keep the same framing/​distance for all shots
  • Wear solid colors (avoid busy patterns)
  • Plain background makes cutout processing easier

Phase 2: Generate Cutouts

Process all your raw photos to create transparent-background cutouts:

node <skill-dir>/​scripts/​process_cutouts.js

What it does:

  • Reads all captured expressions from the database
  • Sends each photo to Replicate's background removal AI
  • Downloads and saves the cutout PNGs
  • Updates the database with cutout URLs

Time: ~30-60 seconds per expression

Phase 3: Generate Thumbnails

Once you have cutouts, generate thumbnails on demand:

npx remotion still Thumbnail <skill-dir>/​renderer/​out/​thumbnail.png \
  --props='{
    "headline": "This Changed Everything",
    "emotionId": 5,
    "stylePreset": "bold",
    "cutoutUrl": "<skill-dir>/​storage/​cutouts/​5_cutout.png",
    "bgUrl": "https://example.com/​background.jpg"
  }'

Parameters:

  • headline (string): The main text to display
  • emotionId (number): Which expression to use (1-25)
  • stylePreset (string): Visual style - "bold", "dramatic", or "clean"
  • cutoutUrl (string): Path to your expression cutout
  • bgUrl (string): URL or path to background image

Output: High-res PNG thumbnail ready for YouTube

Expression Reference

See EXPRESSIONS.md for the full list of 25 expressions and usage tips.

Style Presets

"bold"

  • Vibrant colors
  • Strong contrast
  • Dynamic composition
  • Best for: Entertainment, gaming, reaction content

"dramatic"

  • Moody lighting
  • Cinematic feel
  • Subdued colors
  • Best for: Documentaries, serious topics, storytelling

"clean"

  • Minimal design
  • Soft colors
  • Professional look
  • Best for: Educational, business, tutorials

Advanced Usage

Custom Backgrounds

You can use:

  • Image URLs: Direct link to any image
  • Local files: File path to an image on disk
  • AI-generated: Use DALL-E, Midjourney, etc. and pass the URL
  • Solid colors: Pass a color code (implementation detail in renderer)

Batch Generation

Generate multiple thumbnails programmatically:

# See references/​BATCH_GENERATION.md for examples

Customizing the Renderer

The Remotion renderer is a standard React/​Remotion project. You can:

  • Modify styles in renderer/​src/​Thumbnail.tsx
  • Add new style presets
  • Adjust layout/​composition
  • Add animations (for video thumbnails)

See Remotion docs for details.

Troubleshooting

"Expression not found"

  • Make sure you've run Phase 1 (capture) and Phase 2 (cutouts)
  • Check storage/​expressions_db.json to see which expressions are ready

"Replicate API error"

  • Verify your REPLICATE_API_TOKEN is set correctly
  • Check your Replicate account has credits
  • See TROUBLESHOOTING.md for more

"Renderer not found"

  • Ensure you've run npm install in the renderer directory
  • Check that Node.js 18+ is installed

For more issues, see references/​TROUBLESHOOTING.md

File Structure

remotion-thumbnail/
├── SKILL.md                    # This file
├── scripts/
│   ├── capture.js              # Interactive expression capture
│   └── process_cutouts.js      # Background removal pipeline
├── references/
│   ├── SETUP.md                # Detailed setup guide
│   ├── EXPRESSIONS.md          # Expression reference
│   ├── BATCH_GENERATION.md     # Batch processing examples
│   └── TROUBLESHOOTING.md      # Common issues & solutions
├── assets/
│   └── expressions.json        # Expression definitions
├── renderer/                   # Remotion project
│   ├── src/
│   │   └── Thumbnail.tsx       # Main thumbnail component
│   └── package.json
└── storage/                    # Generated at runtime
    ├── raw/                    # Your captured photos
    ├── cutouts/                # AI-processed cutouts
    └── expressions_db.json     # Expression metadata

Performance Tips

  • First run: Cutout generation takes time (~30-60s per expression)
  • Subsequent thumbnails: Instant once cutouts are ready
  • Caching: Cutouts are reusable forever - generate once, use unlimited times

License

MIT - See LICENSE file for details.

Credits

Created by Alternative Design
Powered by Remotion and Replicate

Support


Pro tip: Once you have your expression library set up, you can generate unlimited thumbnail variations in seconds. Perfect for A/​B testing or maintaining consistent branding across your channel!

More skills from diegosouzapw

accessibility logo
diegosouzapw/awesome-omni-skill

accessibility

Accessibility guidelines for VS Code features — covers accessibility help dialogs, accessible views, verbosity settings, accessibility signals, ARIA alerts/status announcements, keyboard navigation, and ARIA labels/roles. Applies to both new interactive UI surfaces and updates to existing feature...

62 1
View
mermaid-diagrams logo
diegosouzapw/awesome-omni-skill

mermaid-diagrams

Mermaid diagram creation for flowcharts, sequences, ERDs, and more. Generate diagrams from text in markdown files. Use for documentation, architecture diagrams, and visual representations. Triggers on mermaid, flowchart, sequence diagram, ERD, entity relationship, gantt chart, pie chart, class di...

62 1
View
tauri2-react-rust logo
diegosouzapw/awesome-omni-skill

tauri2-react-rust

Guides development of cross-platform desktop apps with Tauri 2, TypeScript, React, and Rust. Use when building Tauri apps, implementing IPC, designing Rust backend or TypeScript/React frontend, when researching or cloning a website (open site, snapshot elements), when verifying local dev or built...

62 1
View
fp-ts-errors logo
diegosouzapw/awesome-omni-skill

fp-ts-errors

Handle errors as values using fp-ts Either and TaskEither for cleaner, more predictable TypeScript code. Use when implementing error handling patterns with fp-ts.

62 0
View
ring:pre-dev-research logo
diegosouzapw/awesome-omni-skill

ring:pre-dev-research

Gate 0 research phase for pre-dev workflow. Dispatches 3 parallel research agents to gather codebase patterns, external best practices, and framework documentation BEFORE creating PRD/TRD. Outputs research.md with file:line references.

62 0
View
create-assistant logo
diegosouzapw/awesome-omni-skill

create-assistant

Create and configure Vapi voice AI assistants with models, voices, transcribers, tools, hooks, and advanced settings. Use when building voice agents, phone bots, customer support assistants, or any conversational AI that handles phone or web calls.

62 0
View
codex-headless logo
diegosouzapw/awesome-omni-skill

codex-headless

Delegiere Aufgaben an OpenAI Codex CLI im Headless-Mode. Nutzt ChatGPT Subscription (KEIN API Key). Nur Workspace-Zugriff, KEIN System-Zugriff. Auto-Accept mit --full-auto. Web-Recherche mit --search.

62 0
View
social-media-scheduler logo
diegosouzapw/awesome-omni-skill

social-media-scheduler

Generate a full week of social media content for any topic. Outputs platform-optimized posts for Twitter/X, LinkedIn, and Instagram with hashtags and posting times.

62 0
View
Data Privacy Compliance logo
diegosouzapw/awesome-omni-skill

Data Privacy Compliance

Data privacy and regulatory compliance specialist for GDPR, CCPA, HIPAA, and international data protection laws. Use when implementing privacy controls, conducting data protection impact assessments, ensuring regulatory compliance, or managing data subject rights. Expert in consent management, da...

62 0
View
triple-review logo
diegosouzapw/awesome-omni-skill

triple-review

Reviews a task using the TRIPLE protocol, as the review agent.

62 0
View
Tech Stack & Architecture Decision logo
diegosouzapw/awesome-omni-skill

Tech Stack & Architecture Decision

Define and document the technology stack and architecture decisions for a project. Use when the user needs to choose a tech stack, make architecture decisions, define infrastructure choices, or document technology selections. Triggers on requests like "define the tech stack", "choose technologies...

62 0
View

Popular AI tools

Kaiber logo
Video

Kaiber

Generate, edit, and beat-sync AI video with leading models in one workspace.

Paid
View
Vimcal logo
Productivity

Vimcal

The world's fastest calendar for remote work

Free
View

Transform Your Design with AI Designer by ImgCreator.ai

Freemium
View
Akool AI logo
Content & writing

Akool AI

Revolutionizing Video Production with AI-Powered Creativity

Paid
View

Extend an image past the frame and let AI fill the new aspect ratio.

Freemium
View
StarByFace logo
Security

StarByFace

Discover your celebrity doppelgänger with StarByFace!

Free
View
C

ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.

Freemium
View
Opus Clip logo
Coding & apps

Opus Clip

Opus.ai: Revolutionize Your Web Experience

Free
View