Creating Your First Video

Video generation in Larpable uses motion control: you provide an image of your AI identity and a reference video that defines the motion. Larpable combines them to create a video of your identity performing that motion.

Step-by-Step

1. 1Open your identity's canvas workspace
2. 2Generate or select an image of your identity (or use a reference photo)
3. 3Add an Upload node and upload a short reference video (5–10 seconds)
4. 4Add a Video Generation node
5. 5Connect the image source to the generation node's scene/image input
6. 6Connect the reference video upload to the generation node's video input
7. 7Optionally add a prompt node and connect it
8. 8Click 'Generate' on the video generation node

Video generation takes longer than image generation — typically several minutes. The video will appear in the generation node and your library when ready.

Understanding the Inputs

The image input defines what your character looks like — their face, clothing, and the background. The reference video defines how they move. The system takes the appearance from the image and the motion from the reference video.

For best results, the image and reference video should have similar framing — if the reference video is a close-up, use a close-up image.

Next Steps

Learn about reference videos and video best practices for better results.