Setup & Installation
What This Skill Does
Generates images and videos from text prompts using fal.ai's hosted AI models. Supports text-to-image, image-to-video, and text-to-video workflows with a queue system that handles long-running jobs without timing out. You can also search available models, upload local files, and check on async requests.
It connects you to dozens of hosted generation models through a single interface, so you skip the setup of local GPUs or juggling multiple provider APIs.
When to use it
- Turning a text description into a product mockup image
- Creating short video clips from a still photo
- Batch generating multiple image variations for a design concept
- Searching fal.ai's model library to find the right generator for a task
- Converting a landscape photo into a slow-zoom video