How do I control the dimensions of the output?

You can use the --aspect or -a flag to specify ratios like 16:9 for wide screens, 9:16 for vertical stories, or 1:1 for square posts.

Which models are used for image and video generation?

The skill uses Google Gemini or fal.ai FLUX.2 for images, and xAI Grok Imagine or fal.ai LTX-2 for videos.

Is there a lower-cost option for quick drafts?

Yes, using the --cheap flag triggers fal.ai's optimized models (FLUX.2 klein or LTX-2) for faster, budget-friendly generation at approximately $0.003 per image.

Does it support right-to-left languages like Hebrew?

Yes, the skill includes specialized logic to ensure correct RTL layout and visual flow when generating images containing Hebrew text.

Can I edit existing images with this skill?

Yes, you can use the --assets flag to provide reference images for AI-driven editing and transformations.

Image & Video Generation

Name: Image & Video Generation
Author: aviz85

byaviz85

•

디자인 도구

Generates high-quality AI images and cinematic videos using Gemini, FLUX, and Grok models directly from Claude Code.

This skill empowers Claude to act as a creative director and visual asset producer by integrating leading AI models for image and video synthesis. Users can generate everything from social media posters and high-resolution 2K prints to 15-second cinematic drone shots and animated videos. It supports advanced features like reference image editing, specific aspect ratios (3:2, 16:9, etc.), and localized RTL support for Hebrew content, making it a versatile tool for prototyping visuals, creating marketing materials, or adding cinematic flair to projects without leaving the terminal.

주요 기능

0120 GitHub stars

02Specialized 'WOW mode' for maximum visual impact and RTL support for Hebrew layouts.

03Multi-model support including Google Gemini, fal.ai FLUX.2, and xAI Grok Imagine.

04High-resolution output up to 2K and cinematic video generation up to 720p.

05Advanced controls for aspect ratios, image-to-video animation, and reference asset integration.

06Cost-optimized 'Cheap Mode' using distilled models for fast iterations and low-cost drafts.

사용 사례

01Generating high-fidelity visual concepts and storyboards during the development process.

02Rapidly prototyping social media assets and marketing posters with custom branding.

03Converting static images into short cinematic video loops for web or presentations.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add aviz85/claude-skills-library image-generation

For use in Claude.ai and ChatGPT

Download Skill