Larpable generates AI videos using motion control technology. 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.
Video generation uses a two-input system:
The system takes the visual appearance from the image and the motion pattern from the reference video, then combines them into a new video. Your AI identity appears in the image's setting and performs the motion from the reference video.
Some AI video tools try to generate video from a text prompt alone, which produces unpredictable results. Motion control gives you precise control by separating appearance (image) from motion (reference video). This separation is what makes it ideal for AI influencer content — your identity's appearance stays consistent while you can vary the motion freely.
The reference video is the most important factor in video quality. Use short clips (5–10 seconds) with smooth, natural motion. The reference video doesn't need to feature your AI identity — it only provides the motion pattern. Read the reference videos guide for details.
A common workflow is to generate a photo first, then turn it into a video. On the canvas, connect an image generation node's output to a video generation node's image input, creating a pipeline from scene to photo to video. Read about motion workflows.
Read our guide to creating realistic AI videos and the video best practices docs.
Video generation costs more credits than image generation because it's more computationally intensive. The cost depends on the video's duration. See how credits work.
Create your first AI identity and generate realistic photos and videos in minutes — no photoshoot required.