AI filmmaking glossary
Text-to-image (t2i)
Last updated: September 24, 2026
Definition
Text-to-image, or t2i, is AI generation that produces a still image from a written prompt alone, with no input picture. You describe a subject, setting, lighting, and lens in words, and the model renders a frame. It is the fastest way to explore a look before committing to motion.
How it works in FXI Studio
In FXI Studio, text-to-image is the default way to create a concept frame, a mood board still, or an establishing shot you will later animate. You write the shot the way a director would brief it, and the frame comes back ready to iterate.
Because a still is cheap to regenerate, t2i is where you lock the look of a scene before spending a video render on it. That frame can then seed an image-to-video shot so motion inherits the composition you already approved.
Where to go next
Put the term to work
Start free with 65 credits, no card required.