AI video and storyboard glossary
The terms behind making video with Fawna, in plain English. New to storyboards or text to video? Start here.
Storyboard
A shot-by-shot visual plan of a video. Each frame shows what one shot looks like before anything is produced, so a team can see and agree on the sequence first.
AI Storyboard Maker →Animatic
A storyboard with timing and motion: the still frames play in order with rough audio, giving a sense of pacing before final footage exists.
Shot list
The ordered list of every shot in a scene, with its framing and direction. A storyboard and a shot list describe the same plan in pictures and in words.
Text to video
Generating a video clip from a written prompt. You describe the shot and an AI model renders it.
AI Video Generator →Image to video
Animating an existing still image into a moving clip, optionally guided by a prompt and a character reference.
AI Video Generator →Script to video
Turning a full script into a finished video by breaking it into scenes and shots, generating each one, and adding narration.
AI Storyboard Maker →AI voiceover
Narration generated from text in a chosen voice, also called text to speech. A voice can be cast per character and synced to the video.
AI Voiceover →Character consistency
Keeping the same character looking like the same character across every shot, by locking a reference and a description rather than re-rolling a new face each time.
Asset Library →Background removal
Lifting a subject out of an image onto a transparent background, also called a cutout. The background can then be replaced or extended.
Background Remover →Outpainting
Extending an image past its original edges so it fills a wider or taller frame, instead of cropping the subject out to fit a new aspect ratio.
B-roll
Supplementary footage that illustrates what a narrator is describing, cut over the voiceover instead of showing a talking head.
Presenter mode
A video style where an on-camera host is the spine of the piece, cutting away to b-roll and back. In Fawna a host cue puts the presenter on screen.
Explainer Maker →Faceless video
A video made without showing a person on camera, driven by a voiceover over generated or stock visuals. Common for narration and documentary channels.
Faceless YouTube →Aspect ratio
The shape of the frame, written as width to height. 16:9 is widescreen, 9:16 is vertical for Shorts and Reels, and 1:1 is square.
Ken Burns effect
A slow pan and zoom applied to a still image to give it gentle motion, named after the documentary filmmaker who popularized it.
Video Editor →Establishing shot
A wide shot at the start of a scene that shows where the action takes place, orienting the viewer before cutting in closer.
Scene vs shot
A scene is a continuous unit of the story in one place; a shot is a single camera take. A scene is built from one or more shots.
Style master
A reference plate that defines a consistent look. In Fawna a style is three master plates (treatment, environment, and character) that anchor every generation.
Asset Library →Thumbnail
The still image that represents a video in a feed. A strong thumbnail uses a clear subject, bold text, and high contrast to earn the click.
Thumbnail Creator →Credit
The unit Fawna uses to price AI work. Each generation, like an image, a second of video, or a block of voiceover, costs a set number of credits.
Pricing →See the terms in action
Reading about it only gets you so far. Make a storyboard and watch the words become a video.