Generate AI video clips from a text prompt alone or from a reference image using Swift, StandIn Labs' video AI. Produces smooth, high-quality video in three duration tiers.

How to generate a video

1. 1Navigate to Create → Video in the sidebar.
2. 2Write a prompt describing the scene, motion, and mood.
3. 3Optionally upload a reference image to use as the first frame of the video.
4. 4Choose a duration: 5 s, 10 s, or 15 s.
5. 5Select an aspect ratio: 16:9 (landscape), 9:16 (vertical/portrait), or 1:1 (square).
6. 6Click Generate. The job is queued — video generation typically takes 1–3 minutes.
7. 7Once complete, the video is playable inline and available in My Library for download.

Tips for better video prompts

• Describe camera motion explicitly: 'slow push-in', 'tracking shot', 'handheld'
• Include lighting cues: 'golden hour', 'studio lighting', 'neon glow'
• Keep the prompt focused — one clear subject + one clear action produces better results than complex multi-subject scenes
• Use a reference image for consistent subject appearance across clips