Architectural walkthrough: an interior on a steadicam in natural light
A filled 7-part prompt for a real-estate or design walkthrough: one slow steadicam path through a room, windows as the only light, straight verticals, and the turns that make geometry drift.
SUBJECT: {the interior: room type, two materials, one piece of furniture that anchors the space} ACTION: {what moves in the room, one thing only, e.g. 'a sheer curtain lifts in a draught' / 'nothing moves'} SETTING: a finished, furnished interior, mid-morning, overcast daylight through large windows on one side, no people, no pets CAMERA: steadicam walkthrough at walking pace, starting at the doorway, moving forward in a straight line for the whole shot, lens height 1.5 metres, verticals kept perfectly straight; no turns, no tilt, no zoom LENS & LIGHT: 24mm wide-angle look with no distortion, deep focus; natural light only, soft shadows from the windows, no lamps on, no HDR look STYLE: clean architectural film, true-to-life colour, neutral white balance, matte surfaces rendered as matte, glass with faint reflections, light grain; no lens flare, no colour grading, no fisheye SOUND: quiet room tone, distant street, a wooden floor creak under the camera; no music DURATION: 8 seconds, 16:9. No on-screen text, no logos, no people.
Paste into the video model as one paragraph; remove the labels once you are happy with the content.
Tips
- What it breaks: turns and doorways. A camera that turns a corner asks the model to invent the room it cannot see, and walls bend. One straight line per clip; cut the turn in the editor between two straight clips.
- Speed: walking pace or slower. A faster move produces furniture that slides.
- Aspect: 16:9. A vertical crop cuts the ceiling and the floor, which is where straight verticals are judged. If a 9:16 version is needed, generate a separate static shot of a detail for it.
- Try first: Veo from text, or image-to-video from a still of the room (a real photo works, and keeps the real finishes); a suggestion, not a benchmark.
| works with | Veo: Google text-to-video / image-to-video prompts. · Kling: Kling text/image-to-video prompts. · Runway: Runway Gen prompts and camera controls. · Image models: Midjourney, Flux, Imagen: keyframes and style boards for image-to-video. |
| cost | Free. The video or image model you paste it into has its own pricing. |
| status | Unverified: written from the technique, not yet run end to end by us. |
| license | CC BY 4.0 for the text here; skills are MIT. |
| updated | 2026-11-01 |
| for agents | architectural-walkthrough-interior-prompt.md |
Related
Camera movement vocabulary that video models understand
The 14 camera moves that generation models respond to reliably, with the phrasing that works and the phrasing that produces a wobbling mess.
Image-to-video: generate the first frame, then animate it
Make a still with an image model first, fix the composition there, and only then ask the video model to animate it. Cheaper iterations and the look you chose, not the one the video model guessed.
Anime style: 2D cel look, limited animation, clean line weight
A filled 7-part prompt for a hand-drawn anime shot: flat cel shading, animation on twos, a held painted background, and the three things the style breaks in current video models.
Claymation and stop motion: 12 fps feel, fingerprints, slight jitter
A filled 7-part prompt for a clay stop-motion shot where the imperfections are the point: visible fingerprints, a frame-by-frame stutter, a set that looks built by hand, and what not to ask for.
Fashion lookbook: a model walks in a studio at 24 fps
A filled 7-part prompt for a lookbook clip: seamless backdrop, one walk toward the camera, cinema frame rate so the fabric moves like fabric, and the faces, feet and prints that need extra care.
Food close-up: macro, steam, a slow pour
A filled 7-part prompt for a food shot that looks edible: one macro framing, one slow physical event (a pour, steam, a crack), side light that shows texture, and the hands and labels to keep out.