AI Video Multi-Angle Generation
Other Other 2026-08-20
Footage © @magnific · View original post
The clip was published publicly by its creator and is linked here directly; rights holders may request removal.
Full prompt
Generate new camera angles from any video MiniMax H3 lets you switch POV without reshooting. Same scene, same performance, completely different angle Prompt breakdown below 👇 https://t.co/VA1zq8cJGi ### 作者补充 [补充1] Generate new camera angles from any video MiniMax H3 lets you switch POV without reshooting. Same scene, same performance, completely different angle Prompt breakdown below 👇 https://t.co/VA1zq8cJGi [补充2] Powered by @MiniMax_AI, available on Magnific Prompt: [vid1] defines the woman's identity. It also defines the scene: a busy Tokyo pedestrian crossing in soft overcast daylight, blurred crowds walking past in both directions, a red bus and city buildings in the background. It defines her performance and timing: she stands completely still facing forward while the crowd flows around her, her hair moving slightly in the breeze, her expression calm and steady with subtle lip movement. Do not inherit the camera position, framing, or shot size from [vid1]. Generate the same sequence, at the same location and the same moment, seen from a different camera position: [Add the camera description] <City crossing ambience: footsteps, distant traffic, a crossing signal chirping> Keep the woman's identity, hairstyle, trench coat, sweater, bag strap, posture, and stillness exactly as in [vid1]. Exactly one instance of the woman. The crowd flows around her without colliding. Do not change the time of day, weather, or location.
Details
| Target model | MiniMax H3 |
|---|---|
| Use case | Other |
| Style | Other |
| Media | Video |
| Duration | 8.1s |
| Aspect ratio | 9:16 |
| Likes | 284 |
| Published | 2026-08-20 |
Attribution
Author: @magnific · View original post
Prompts remain the copyright of their authors. We index and quote them with attribution plus a link to the original post; rights holders may request removal.
Run this prompt through the API
Copy the prompt above into a MiniMax H3 (Hailuo) text-to-video call to reproduce the shot. When adapting it, swap subject, setting and camera move one clause at a time. Access and licensing details are on About.