The thing that took me longest to work out: you cannot prompt a camera move. You describe it, the model invents its own, and you burn a run every time. So I stopped describing it. I block the move in Blender first. Grey boxes, no textures, no lighting, nothing in there except where the camera goes and when it gets there. Then I hand that grey clip to Seedance as a movement reference and it copies the path frame for frame. The prompt then does one job only, which is saying what things look like. The previz already decided where the camera goes. This F1 one is thirteen shots and twelve hard cuts in a single generation. The cuts are baked into the previz, not into an edit. The .blend files are attached at the bottom of the lessons in the Classroom. Open one, press play, watch it through the camera.

Every lesson in the Classroom is named after the word you commented on Instagram. Commented MOTO, look for MOTO. Commented RALLY, look for RALLY. Newest at the top. Each one has the film first, then the exact prompt underneath. Copy it, swap the car or the product for yours, run it. Some have the Blender previz file attached at the bottom as well, so you can open the camera move and see how it was built. Classroom > Prompt Library > Instagram. Two keywords still have no page yet, CAVE and SKYLINE. Those are next.

Tell me the product, the car, whatever it is you want to film, and I'll point you at the prompt in the Classroom that gets you closest. If nothing in there fits, say that instead. That's the one I'll build next. I'd rather know what people are actually trying to make than guess.