Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
aviz85 avatar

Image Generation

  • 3 installs
  • 4 repo stars
  • Updated March 11, 2026
  • aviz85/ai-music-video-maker

image-generation is a Claude Code skill that generates images from a text prompt using Google Gemini or fal.ai FLUX.2 klein 4B.

About

A Claude Code skill that generates images from a text prompt using Google's Gemini model by default or fal.ai FLUX.2 klein 4B in cheap mode. A developer runs its generate_poster.ts script to produce posters, social content, or reference-edited images with configurable aspect ratio and quality. It supports reference assets for image editing and RTL/Hebrew text layouts.

  • Generates images via Google Gemini (default) or fal.ai FLUX.2 klein 4B (--cheap, ~$0.003/image)
  • Aspect-ratio, quality (1K/2K), and reference-image editing flags via a ts-node CLI
  • Handles RTL/Hebrew text layouts and a WOW cinematic-effects prompt mode

Image Generation by the numbers

  • 3 all-time installs (skills.sh)
  • Ranked #1,155 of 1,337 Generative Media skills by installs in the Skillselion catalog
  • Data as of Jul 28, 2026 (Skillselion catalog sync)
At a glance

image-generation capabilities & compatibility

Requires GEMINI_API_KEY and/or FAL_KEY; fal.ai cheap mode ~$0.003/image.

Capabilities
image generation · video generation
Works with
openai
Use cases
image generation
Pricing
Bring your own API key
From the docs

What image-generation says it does

Generate images using Google's Gemini model (default) or fal.ai FLUX.2 klein 4B (cheap mode).
SKILL.md
**Cost**: ~$0.003 per image (vs Gemini's higher cost)
SKILL.md
npx skills add https://github.com/aviz85/ai-music-video-maker --skill image-generation

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs3
repo stars4
Last updatedMarch 11, 2026
Repositoryaviz85/ai-music-video-maker

What it does

Generate poster or social images from a prompt via CLI, choosing Gemini for quality or FLUX.2 klein for fast, low-cost batches.

Who is it for?

Generating poster and social images from prompts, with a cheap batch mode for iterations and previews.

Skip if: Text-heavy or complex final production compositions when using cheap mode, where the docs steer users to Gemini instead.

When should I use this skill?

You need to create an image, generate a visual, or produce a poster from a text prompt.

What you get

A generated image saved to a specified destination path at the chosen aspect ratio and quality.

  • Generated image file at the -d destination path

By the numbers

  • fal.ai cheap mode ~$0.003/image
  • 4-step inference ~2-4 seconds
  • 2 quality levels (1K/2K)

Files

SKILL.mdMarkdownGitHub ↗

Image Generation

Generate images using Google's Gemini model (default) or fal.ai FLUX.2 klein 4B (cheap mode).

Quick Start

MANDATORY: Always use -d (destination) flag to specify output path. This avoids file management issues with poster_0.jpg in the scripts folder.

cd ~/.claude/skills/image-generation/scripts

# ALWAYS specify destination with -d flag
npx ts-node generate_poster.ts -d /tmp/my-image.jpg "A futuristic city at sunset"

# Cheap mode: fal.ai FLUX.2 klein 4B (fast, lower cost)
npx ts-node generate_poster.ts --cheap -d /tmp/city.jpg "A futuristic city at sunset"

# With aspect ratio
npx ts-node generate_poster.ts -d /tmp/landscape.jpg --aspect 3:2 "A wide landscape poster"
npx ts-node generate_poster.ts --cheap -d /tmp/story.jpg -a 9:16 "A vertical story format"

# With reference assets (image editing)
npx ts-node generate_poster.ts -d /tmp/banner.jpg --assets "/path/to/avatar.jpg" "Create banner with character"
npx ts-node generate_poster.ts --cheap -d /tmp/photo.jpg --assets "/path/to/image.jpg" "Turn this into a realistic photo"

Why `-d` is mandatory:

  • Output goes to predictable location (e.g., /tmp/ for temp images)
  • Avoids hunting for poster_0.jpg in scripts folder
  • Enables immediate use without file renaming

Providers

ProviderFlagUse CaseCost
Gemini(default)High quality, best resultsHigher
fal.ai klein 4B--cheapFast, budget-friendly~$0.003/image

Cheap Mode (--cheap)

Uses fal.ai FLUX.2 klein 4B - a distilled FLUX model optimized for speed and cost.

Why use cheap mode?

  • Cost: ~$0.003 per image (vs Gemini's higher cost)
  • Speed: Fast 4-step inference (~2-4 seconds)
  • Quality: Good enough for drafts, social media, iterations
  • Batch friendly: Generate many variations quickly

Endpoints:

  • Text-to-image: fal-ai/flux-2/klein/4b
  • Image editing (with --assets): fal-ai/flux-2/klein/4b/edit

Best for:

  • Quick iterations and previews
  • Social media content
  • Concept exploration
  • Batch generation (10+ images)

Use Gemini instead for:

  • Final production assets
  • Complex compositions
  • Text-heavy images (especially Hebrew)

Quality

Control image resolution with --quality or -q:

QualityResolutionUse Case
1K1024pxDefault - fast, good for web
2K2048pxHigh quality - print, detailed posters
npx ts-node generate_poster.ts -q 2K "High quality poster"

Aspect Ratio

IMPORTANT: Always use the default 3:2 aspect ratio unless the user explicitly requests a different format (like "vertical", "story", "square", etc.). Do NOT change the aspect ratio on your own.

Control image dimensions with --aspect or -a:

RatioUse Case
3:2Horizontal (DEFAULT - use this unless user specifies otherwise)
1:1Square - Instagram, profile pics
2:3Vertical - Pinterest, posters
16:9Wide - YouTube thumbnails, headers
9:16Tall - Stories, reels, TikTok
npx ts-node generate_poster.ts --aspect 3:2 "Your prompt"
npx ts-node generate_poster.ts -a 16:9 "Your prompt"

Adding Assets (Reference Images)

Use --assets with full paths to include reference images:

# Single asset
npx ts-node generate_poster.ts --assets "/full/path/to/image.jpg" "Your prompt"

# Multiple assets (comma-separated)
npx ts-node generate_poster.ts --assets "/path/a.jpg,/path/b.png" "Use both images"

# With cheap mode - uses fal.ai edit endpoint
npx ts-node generate_poster.ts --cheap --assets "/path/to/image.jpg" "Turn this into a painting"

Supported formats: .jpg, .jpeg, .png, .webp, .gif

IMPORTANT: Assets are NOT automatically included. You must explicitly pass them via --assets.

Destination (MANDATORY)

ALWAYS use --destination or -d to specify output path:

# REQUIRED: Always specify destination
npx ts-node generate_poster.ts -d /tmp/poster.jpg "My poster"

# If file exists, auto-adds suffix: poster_1.jpg, poster_2.jpg, etc.

Features:

  • Auto-creates parent directories if needed
  • Collision avoidance: if file exists, adds _1, _2, etc.
  • Use /tmp/ for temporary images that will be uploaded elsewhere

Save to Gallery

Save good results for future style reference:

npx ts-node generate_poster.ts --save-to-gallery "my-style" "prompt"

Creates assets/gallery/my-style.jpg + .meta.json with prompt info.

API Configuration

Create scripts/.env:

GEMINI_API_KEY=your_gemini_api_key
FAL_KEY=your_fal_api_key

Hebrew/RTL Content

IMPORTANT: When the image contains Hebrew text, you MUST add the following sentence to the prompt:

"CRITICAL: Layout is RTL (right-to-left). All text in Hebrew. Visual flow, reading order, and panel sequence go from RIGHT to LEFT."

Copy this exact sentence and paste it at the BEGINNING of your prompt. Without it, the image will render left-to-right which is wrong for Hebrew content.

WOW Mode

When user asks for "wow mode" or wants maximum visual impact, add these epic elements to the prompt:

"EPIC CINEMATIC WOW: Amazed expression, mind-blown reaction, intense VFX - shattered glass particles, explosive energy bursts, volumetric light rays, dramatic lens flares, particle explosions, motion blur streaks, holographic glitches, electric sparks, cinematic color grading, dramatic rim lighting, depth of field bokeh, anamorphic lens effects. Maximum visual spectacle."

This pushes the visual to the edge with:

  • Shattered/particle effects
  • Explosion/energy bursts
  • Lens flares and volumetric lighting
  • Motion blur and dynamic effects
  • Electric/holographic glitches
  • Dramatic cinematic lighting

Output

  • Files saved to path specified by -d flag (MANDATORY)
  • Aspect ratio: Configurable via --aspect (default: 3:2)
  • Quality: 1K (1024px on longest edge)
  • Send via WhatsApp after generation (if whatsapp skill exists)

Related skills

FAQ

Which providers does this skill support?

Google Gemini by default, and fal.ai FLUX.2 klein 4B in cheap mode (--cheap).

How much does cheap mode cost?

About $0.003 per image using fal.ai FLUX.2 klein 4B with 4-step inference.

Generative Mediallmautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.