Best for
Users comparing AI video tools or features before picking one
Resource
AI video glossary: the terms behind the app
This AI video glossary explains the core terms used across Visionary and the wider AI video space, from generation modes to editing operations. Use it to understand what a feature actually does before choosing it.
AI answer
Core terms
An AI video glossary maps the vocabulary of AI video tools to what each term does in practice: text-to-video generates a clip from a written prompt, image-to-video animates a still photo, frame-to-video interpolates motion between two frames, and upscaling increases resolution without re-generating content. Knowing these terms helps a user pick the right Visionary feature for a given source and goal.
Expected result
Clear match between a term, a technique, and the right app feature
Known limit
Terminology varies slightly between vendors and models
Example
Confirming that 'upscaling' will not add new motion, only resolution
Generation and motion terms
Diffusion models are the underlying technology behind most modern AI video and image generators, including the models available in Visionary. A prompt is the text description that steers what the model creates, and style transfer applies the visual look of one reference (like anime or claymation) onto new footage. These terms describe the generation stage, before any export or enhancement step.
| Term | Definition |
|---|---|
| Text-to-video | Generates a video clip directly from a written prompt, no source image required |
| Image-to-video | Animates a single uploaded photo based on a motion description |
| Frame-to-video | Generates the motion between two provided frames (start and end) |
| Diffusion model | The AI architecture that generates images or video by refining noise into a coherent result |
| Prompt | The text instructions that describe subject, motion, and style to the model |
| Style transfer | Applying a visual style, such as anime or claymation, onto existing footage |
Editing and output terms
Upscaling increases a video's resolution, commonly up to 4K, using an AI model rather than simple pixel stretching. Colorization adds realistic color to black-and-white footage, and a watermark is the visible logo overlay that free-tier tools often add, which Visionary removes on paid exports. These terms describe what happens after a clip is generated, during refinement and export.
| Term | Definition |
|---|---|
| Video upscaler | Increases resolution and sharpness of an existing clip, e.g. to 4K |
| Colorization | Adds plausible color to black-and-white photos or footage |
| Watermark-free export | An export with no overlay logo, available on Visionary paid plans |
| Commercial rights | License terms allowing generated video to be used in paid or business work |
Workflow
How to use this page in practice
- 01
Open Visionary on iPhone or iPad
- 02
Pick the feature that matches the term you need, such as image-to-video or upscaler
- 03
Upload a source image or clip and enter a prompt if needed
- 04
Generate, then export or upscale the result
FAQ
Questions this page should answer
What is the difference between text-to-video and image-to-video?
Text-to-video generates a clip purely from a written prompt with no source image, while image-to-video starts from an uploaded photo and adds motion described in the prompt, keeping the original visual.
What does upscaling mean in AI video?
Upscaling increases a video's resolution and sharpness, for example from standard definition up to 4K, using an AI model rather than simply stretching existing pixels.
What is a diffusion model?
A diffusion model is the AI architecture behind most modern video and image generators; it creates a result by gradually refining random noise into a coherent image or clip based on a prompt.
Where can I find these terms applied in Visionary?
Each term in this glossary corresponds to a specific Visionary feature, such as image-to-video, video upscaler, or ai-photo-colorizer, all accessible from the main app on iPhone and iPad.
More in Resource
Explore related Visionary tools
Visionary
Create with Visionary on iPhone and iPad
Visionary is an AI photo-to-video and video creation app for iPhone and iPad.