fal-tryon

A collection of skills for generating, editing, and upscaling images and videos using fal.ai models, with queue-based processing, local file upload to CDN, workflow chaining, and audio text-to-speech/speech-to-text capabilities.

Generates images and videos using fal.ai's AI models with queue support, allowing flexible generation, file upload, and asynchronous processing.

A cinematography skill for designing cinematic image and video prompts, covering shot language, camera movement, lighting, lens choices, color grading, film texture, scene blocking, and production-ready visual direction for generative media.

Agent skills for generating images and videos using fal.ai models with queue-based processing, file uploads, and platform management for pricing and usage estimation.

Agent skills for generating images and videos using fal.ai models with queue-based processing, file uploads, and platform management for pricing and usage estimation.

Agent-first CLI skill for fal.ai providing access to 1,200+ model endpoints for image and video generation, with smart routing that auto-classifies prompts and routes to optimal models by modality.

Manages fal.ai platform operations like retrieving pricing, checking usage, estimating costs, and configuring API keys.

Generates production-ready fal.ai workflow JSON files for creating complex, multi-step AI pipelines that chain together different models and media types.

A Claude Code skill that upgrades coded websites to award-tier design using fal.ai, combining vision model analysis, GPT Image 2 reference generation, and build-spec output to transform local HTML files or dev-server sites into professionally designed pages.

Modality-organized catalog of fal.ai production endpoints for text-to-image, image-to-image, text-to-video, image-to-video, and more, helping users choose the right model for their task.