A video scene with two characters
Share two characters and pick one of the Scene Builder app’s nine presets (boxing match, wedding, dinner date, dance battle, and more) or write your own. Cherry 2 Pro films them together, with dialogue.
Requires the Mage connector ↓Prefer clicking? Open the Scene Builder app →Examples
Two characters, one scene
The preset writes the shots and the lines; both characters stay themselves.
How it works
How to use the Scene Builder skill
Share two characters
Two images or saved characters, in the order the scene uses them.
Pick the scene
Boxing Match, Wedding, Dinner Date, Dance Battle, Kissing, Mafia Meeting, Late Night Drive, Beach Episode, Morning Together, or your own.
Approve and render
Cherry 2 Pro at 480p and 16:9, 4 seconds by default, with longer lengths offered with their price.
Runs on
Setup
Set up Mage in your agent
Connect Mage
Add the Mage connector to Claude, ChatGPT, Claude Code, Grok, or Cursor, and sign in with your Mage account.
Open MCP setup →Add the skills
In Claude Code, Codex, Cursor, and other agents, add every Mage skill with one command, or install the Claude Code plugin.
npx skills add mage-space/skills/plugin marketplace add mage-space/skills/plugin install mage@mageAsk for it
Describe the job, or run /mage-scene-builder.
Use Mage to put these two in the Dinner Date scene: https://www.mage.space/skills/app-inputs/scene.jpg https://www.mage.space/skills/app-inputs/character.jpg
FAQ
Frequently asked questions
Is it the same as the Scene Builder app?
Yes. The skill sends the Scene Builder app’s own prompt with the same models and defaults, so your agent gets the app’s results from a chat, and can run it on many images in one go.
Can I write my own scene?
Yes. Describe it in your own words; the skill makes sure it says which character is which.
Can I add a third character?
No. Scene Builder takes exactly two. Physical interaction between two generated people is already the hardest case in video, so expect the odd retry.
Can I use a real person’s face?
Only with that person’s permission, and never to deceive, harass, or sexualize anyone. Harmful deepfakes are forbidden on Mage, and the skill states the rule with the price before it runs.
Why does it ask before rendering?
Video is priced by resolution and length, so the skill quotes the model, resolution, length, and Gems and waits for your yes. It starts at 480p, the cheapest, and offers 720p or 1080p for a final.
Try Scene Builder in Claude
Two characters in a ready-made video scene, from a dinner date to a boxing match, each one kept recognizable.
More skills
Explore other skills
Video Edits
Video Editor
Change what a video shows with one instruction, keeping its motion, camera, and timing.
Video Edits
Video Face Swap
Swap a face into every frame of a clip, keeping the motion, expressions, and lip movements.
Video Edits
Video Character Swap
Replace the whole person in a clip with your character, body and outfit included.
Video Edits
Lipsync
Make a portrait speak a voice clip, with the lips in sync and the look of the image kept.
Video Edits
Music Video
Your characters sing and dance to a track in a music video with cinematic camera work.
Essentials
Generate
Any image, video, or audio on the right Mage model, priced before it runs and delivered as a link.








