Each demo runs on the same API and compute you build with. Open one, then read the docs.
Built by the GMI Cloud community and GMI DevRel. 49 demos, each one a small app that calls GMI inference and returns a result.
A storybook studio for little dreamers: type an idea, get a kid-safe picture book with a painted illustration and narration on every page.
Type a topic, get a produced podcast: DeepSeek-V4-Flash writes a two-voice script, Inworld TTS-2 voices every line in parallel, transcript synced per word.
A life becomes a cinema: 15 years of one person's Facebook turned into a walk-in 3D theatre and a film, with an AI director on GMI Cloud, by Hans Lin
Create age-tailored bedtime stories with illustrations and narration.
Kiosk app: take a webcam photo, pick one of the 48 World Cup 2026 nations, get an AI team photo of you in that jersey (GMI image queue).
Drop a long recording, ask a question: a vision agent searches it coarse-to-fine, cuts the clip, subtitles it in three languages, optional Omni remix.
24 IT tickets handled by 24 parallel Nemotron agents with 21 mock tools, a thinking-mode dial and comparison runs.
Footage in, physics out: Gemini 4 Argon tracks a moving object across 48 frames, writes and runs the fit, and puts its g next to 9.81 with an error bar.
A security camera wall: six-second clips go to Nemotron 3.5 Super VL, which returns events, positions and rule-breaking alerts.