
Generate one clear character still first. Same face, same wardrobe.
That photo is your actor for every shot.
Reuse the model as a reference. Make 8 to 12 angles: walk, close-up, over-shoulder, window, hands on tablet.
Image-to-video the best landscape still. Prompt the MOTION only: walk, dolly, shallow DOF.
Keep her identity locked.
This guide is the full process. The ready-made version lives inside AI Creative OS on Skool, next to every other prompt pack I post.