Welcome to Fawna
Fawna is an AI creative studio for storytellers. Turn a script into a video with Scene Mode, iterate shot by shot in the Editor, and fill in the gaps with specialized tools. This site explains what every model does, how to prompt it well, and how to get the most out of every feature.
Where to start
If you want to ship your first result today, pick one of these tracks. Each takes about five minutes.

The four surfaces
Fawna has four places where you spend time. Pick the one that matches what you are doing today.
- Scene Mode: paste a script, get a finished video. Minimal effort, maximum pacing. See Scene Mode.
- Editor: full multi-track timeline with clips, transitions, audio, markers, and a preview player. For shot-by-shot control. See Editor.
- Image & Video Generation: chat-style generator. Every model, every control, one prompt at a time. See Image & Video Generation.
- Tools: Audio Generation, Background Remover, Background Extender. Fill-in utilities for voice-over, cutouts, and canvas extension. See Tools.
Meet the models
Fawna wraps top-tier video and image models behind branded tiers. You pick by what the output should feel like. Every tier has its own sweet spot.


See the full breakdown in the Models overview.
How this docs site is organized
- Getting started: five-minute walkthroughs to a first result.
- Prompting: the playbook for making models do what you mean.
- Models: one page per tier with capabilities, defaults, and tips.
- Scene Mode: script-to-video flow, narrators, and the scene grid.
- Editor: the multi-track timeline editor. Tools, tracks, transitions, markers, keyboard.
- Tools: Image & Video Generation, Audio Generation, Background Remover, Background Extender.
- Account: credits, privacy, billing, and frequently asked questions.
Search works across every page. Hit ⌘K from any docs page to jump to a
specific topic. Results sort by title match.