Can I generate videos from existing images?

Yes, the skill supports image-to-video generation using models like Seedance 1.0 Pro and Kling by uploading an image and providing a motion prompt.

Does this skill support text-to-speech?

Yes, it includes support for CSM-1B for conversational speech and provides patterns for integrating ElevenLabs and VideoDB audio generation.

How can I avoid high costs when generating media?

The skill includes an 'estimate_cost' tool that allows you to check the projected price of a generation before you commit to running the model.

Which image generation models are available?

The skill provides access to Nano Banana 2 for fast iterations and Nano Banana Pro for high-fidelity production images and typography.

What is required to use the fal-ai-media skill?

You must have the fal-ai-mcp-server installed via npx and a valid FAL_KEY from fal.ai configured in your ~/.claude.json file.

fal.ai Media Generation

Name: fal.ai Media Generation
Author: affaan-m

byaffaan-m

•

156,033

•

Herramientas de Diseño

Generates high-quality images, videos, and audio directly within Claude Code using fal.ai's state-of-the-art AI models.

The fal-ai-media skill integrates the fal.ai MCP server into Claude Code, providing a unified interface for sophisticated media generation. It empowers developers to create everything from fast image drafts and production-grade visuals to cinematic videos and natural conversational speech. By supporting industry-leading models like Nano Banana, Kling, and Seedance, this skill enables seamless asset creation, model discovery, and cost estimation without leaving the terminal, making it an essential tool for building media-rich applications and content workflows.

Características Principales

01156,033 GitHub stars

02Integrated file upload system for using local assets as model inputs.

03Built-in cost estimation and model discovery via the fal.ai MCP server.

04Support for high-fidelity models including Nano Banana Pro, Kling Video, and Veo 3.

05Advanced image-to-video and video-to-audio conversion capabilities.

06Multi-modal generation covering text-to-image, video, and audio synthesis.

Casos de Uso

01Creating natural-sounding voiceovers and ambient sound effects for multimedia projects.

02Generating AI-powered video content and cinematic clips for marketing or applications.

03Rapidly prototyping UI/UX mockups and product photography during frontend development.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add affaan-m/everything-claude-code fal-ai-media

For use in Claude.ai and ChatGPT

Características Principales

01156,033 GitHub stars

02Integrated file upload system for using local assets as model inputs.

03Built-in cost estimation and model discovery via the fal.ai MCP server.

04Support for high-fidelity models including Nano Banana Pro, Kling Video, and Veo 3.

05Advanced image-to-video and video-to-audio conversion capabilities.

06Multi-modal generation covering text-to-image, video, and audio synthesis.

Casos de Uso

01Creating natural-sounding voiceovers and ambient sound effects for multimedia projects.

02Generating AI-powered video content and cinematic clips for marketing or applications.

03Rapidly prototyping UI/UX mockups and product photography during frontend development.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add affaan-m/everything-claude-code fal-ai-media

For use in Claude.ai and ChatGPT