Terms: the words animation tools use
Each page explains one term as the tools use it and lists the readings where it turns up. As of 2026-09-25.
Explanations follow how the pages use a term when the makers agree.
Where two makers mean different things by a term, the page says so.
The terms cover the three parts of a series tool: how it draws, how it keeps a cast together, and how its characters speak.
Each term page ends with the readings where the word appears, so the definition can be checked against the makers' own usage.
1In this section
- Canon — A show's canon is what stays true across episodes: characters, places, relationships and events that later episodes must respect.
- Character sheet — A character sheet shows one character from several angles and with several expressions on a single page, so every later shot can refer back to it.
- Lip sync — Lip sync in AI animation tools: lip sync moves a character's mouth in time with a spoken line, so dialogue can be delivered on screen.
- Long form — Long form in AI animation tools: long-form video runs well beyond a short clip, from several minutes to the length of a film.
- Manga and webtoon — Manga, webtoon and manhwa are comic forms, printed pages or vertical scrolling strips, that many animation tools now make as well as moving pictures.
- Native audio — Native audio means a video model generates sound, voices and effects in the same pass as the picture, instead of adding them afterwards.
- Photo to character — Photo to character turns a photograph of a real person into an animated or 3D character that can then be posed, moved and given lines.
- Rigging — Rigging in AI animation tools: rigging gives a 3D character a skeleton and controls so it can be posed and animated, including the face for lip sync.
- Season plan — Season plan in AI animation tools: a season plan lays out a run of episodes before any is made: the arc, the episode outlines and the cast.
- Style preset — Style preset in AI animation tools: a style preset is a saved look, a drawing medium, palette and finish, that a tool applies across a project.
- Text to speech — Text to speech in AI animation tools: text to speech turns written lines into spoken audio with a synthetic voice, without recording anyone.
- Upscaling — Upscaling enlarges a finished video or image to a higher resolution, filling in the extra pixels with a model rather than drawing the picture again.
- Voice cloning — Voice cloning makes a synthetic voice that sounds like a recorded one, so a character can keep one voice throughout a series.
2A series pipeline, animated or not
The series side of “Terms” looks like this in SceneMixer's own guides:
A SceneMixer segment comes out with its sound already in it: each line spoken in that character’s voice, the speaker’s lips moving with the words, and the ambience of the place — rain, traffic, a clock.
SceneMixer, Dialogue and Sound in One Generation (read 2026-10-13)
A script longer than about 10,000 characters (counted as Chinese-equivalent characters) is read in two passes: first the cast, sets and props, then the episode list with a short outline per episode.
SceneMixer, Long Scripts Are Read in Two Passes: What “Preparing Episodes” Means and Why Some Episodes Open Later (read 2026-10-13)