Glossary

Motion & video, defined

A plain-language reference for the terms you'll meet while making animated video.

Aspect Ratio

The proportional relationship between a video's width and height, such as 16:9 or 9:16.

Audio Ducking

Automatically lowering background music's volume while speech is present, then restoring it after.

ControlNet

A technique for conditioning a diffusion model's output on structure — like pose, depth, or edges — instead of a prompt alone.

Diffusion Model

A generative model that creates images or video by learning to reverse a process of adding random noise.

Easing

A curve that controls the rate of change of an animation, making motion feel natural rather than mechanical.

Frame

A single still image in a sequence; the smallest unit of time in a video.

Frame Rate (FPS)

The number of individual frames shown per second of video, measured in frames per second.

Generative Music

Music composed by an AI model from a text or mood prompt, rather than recorded or licensed from a catalog.

Image-to-Video

Animating a single still image into a short video clip, typically by predicting plausible motion around it.

Inpainting

Regenerating a masked region of an image or video while leaving the rest of the frame untouched.

Interpolation

Calculating intermediate values between two known points to create smooth transitions.

Keyframe

A defined point that sets a property's value at a specific time, between which the software interpolates.

Latent Space

The compressed, abstract representation a generative model works in before decoding its output into pixels.

Lip Sync

Matching a video's mouth movement to a spoken audio track.

LoRA

A small, efficient fine-tune layered on top of a base generative model to teach it a specific style or subject.

Loudness Normalization (LUFS)

Adjusting an audio track's perceived loudness to a standard target, measured in LUFS.

Prompt

The text instruction given to a generative AI model to steer what it creates.

Render

The process of turning a composition into final output frames and encoding them into a video file.

Seed

The number that initializes a generative model's randomness, making an otherwise random output reproducible.

Spring

A physics-based animation model that produces natural, bouncy motion based on stiffness and damping.

Temporal Consistency

How stable a subject's appearance stays from frame to frame in AI-generated video.

Text-to-Speech (TTS)

Synthesizing spoken audio from written text using an AI voice model.

Text-to-Video

Generating a video clip directly from a written prompt, with no footage or manual animation involved.

Timecode

A standardized way of labeling a precise position in a video, usually as hours:minutes:seconds:frames.

Transcription

Converting spoken audio into timestamped text, the basis for captions and subtitles.

Upscaling

Using AI to increase a video or image's resolution while inferring plausible new detail.

Video Diffusion

A diffusion model extended to generate motion across a sequence of frames rather than a single image.

Voice Cloning

Generating speech in a specific person's voice from a short sample of their real voice.

Waveform

A visual representation of an audio track's amplitude over time.

Frequently asked questions

A plain-language reference defining the motion and video terms you'll meet while making animated video — from frame rate and easing to timecode and aspect ratio.

Anyone learning motion design or video production, whether you're brand new or just want a quick, jargon-free refresher.

Not at all — you can describe a video in plain language and let the agent handle the details. The glossary is here for when you want to understand what's happening under the hood.