Fal

Interact with fal.ai AI model APIs for image, video, speech generation, and LLM text completion

Actions5

Image to Video Actions
- Generate Video
Run LLM Actions
- Generate Text
Text to Image Actions
- Generate
Text to Speech Actions
- Generate Audio
Text to Video Actions
- Generate Video

Text to Image → Generate

AI-generated

Summary

Generate images from text prompts using fal.ai models.

Inputs

prompt (required) — Text prompt describing what you want to see
model — AI model to use for image generation
numImages — Number of images to generate (1-4)
aspectRatio — The aspect ratio of the generated image
resolution — Output resolution quality
additionalOptions — Additional generation options (model-dependent)

Output shape

image data

Generated image(s) from the fal.ai API. Returned data availability depends on syncMode and model selection; when syncMode is true (nano-banana-2 only), media is returned as a data URI and not stored in request history.

Discussion