VIDEO ROOM · TOOL 11
Diorama.
Enter one idea. Get a cinematic miniature/tilt-shift video prompt — timed to the second, and adapted for Gemini Veo, Seedance, Omni, Kling, Runway and Luma.
Sets the aspect ratio and resolution noted in every generated prompt.
Universal promptalways on
Gemini (Veo)
Seedance
Omni
Kling
Runway
Luma
No prompts yet
Enter an idea on the left and hit Generate.
Each scene renders as its own frame, timed to the second.
Each scene renders as its own frame, timed to the second.
CUTTING ROOM · DIORAMA GUIDE
How to use Diorama
Seven steps from a one-line idea to a finished AI video prompt, sized and timed for wherever you're publishing.
01
Type your idea
Enter one plain-language idea —
a rainy night market in Bangkok is enough. No need to write a full prompt yourself; that's what the tool is for. Stuck? Tap 🎲 Surprise me for a random example.02
Choose your duration mode
Single Shot makes one continuous clip (5–30s). Multi-Scene breaks your idea into 2–6 timed shots that add up to a full sequence (15–60s total), each with its own start and end timecode.
03
Pick your video size
Select the platform you're publishing to — YouTube, Instagram Reels, Facebook, TikTok, and more. The correct aspect ratio and resolution are added to every generated prompt automatically.
04
Select which AI tools to generate for
Tick Gemini, Seedance, Omni, Kling, Runway, or Luma. Each gets its own version of the prompt, written in that tool's typical style — you don't need to reformat anything by hand.
05
Generate prompts
Hit Generate prompts. Each scene appears as its own frame, typed out in real time, with its exact duration and timecode marked on a ruler underneath.
06
Copy or Share directly
Use Copy prompt to grab the text, or Share to send it straight to an app via your phone's native share sheet. On desktop, Share copies the prompt and opens the platform's site for you to paste.
07
Generate your video and edit
Paste the prompt into your chosen AI tool and generate the clip. Bring the result into CapCut (or your usual editor) to finish and publish.
Frequently asked questions
If your question isn't here, the same logic applies to most edge cases: Diorama writes prompts, your chosen AI tool generates the video.
No — Diorama only writes the prompt text. You paste that prompt into an AI video tool (Gemini, Kling, Runway, and so on), and that tool generates the actual clip.
No. Diorama runs entirely in your browser and needs no login, key, or server. You'll need your own account on whichever AI video platform you use to actually generate the clip.
No. Everything runs locally in your browser — nothing is sent to a server, stored, or logged.
Browser security stops any website from typing into another website. On phones, Share uses your device's native share sheet, which can hand text straight to an installed app. Desktop browsers have no equivalent, so Share copies the prompt and opens the site for you to paste.
Seedance doesn't have one single official public web app — most "Seedance" sites you'll find are third-party wrappers. The Seedance button copies the prompt instead of guessing a link, so you can paste it into whichever Seedance-access app you already use and trust.
Yes — copy it into your AI tool's input box and adjust the wording however you like before generating.
Match wherever you're publishing: 9:16 for Reels, Shorts, TikTok, and Stories; 1:1 or 4:5 for feed posts; 16:9 for YouTube landscape.
It states your intended duration in the prompt, but the final length depends on the AI platform — some cap clips at a fixed length (e.g. 5–10s) regardless of what's requested, so check that tool's current limits.
Yes — camera angle, lighting, motion, and texture are reshuffled each time, so hitting Generate again on the same idea gives you a fresh variation to try.