ArtArch Newsroom
AI Video TechniquesAI Video Motion Reference Prompt: Plan a Controlled Long Take
Use an AI video motion reference prompt to guide character routes, camera movement, pacing, and final framing in a controlled long take.

An AI video motion reference prompt helps turn a planned route into a cinematic long take. Start with a character and setting reference, then use a simple motion clip to guide where the character travels, how the camera moves, and where the shot lands. The result is a continuous scene with a readable destination instead of a collection of disconnected actions.
For a train-platform scene, the character begins on the left with a suitcase, walks along the platform, and arrives at an open carriage door on the right. The still reference carries the character, wardrobe, station layout, evening light, and train design. The motion reference carries the travel path, pace, camera direction, and final framing. This division gives every source one clear job.
What to put in a motion reference
Build the reference as a simple animatic or proxy pass. A human-shaped stand-in, basic geometry, and an outlined destination are enough when the movement reads clearly. Focus on six pieces of information:
- The character's starting position and facing direction
- A single route through the space
- The camera's starting viewpoint
- The main camera move and its pace
- A pause, turn, or interaction point when the scene needs one
- The final frame and the information it should hold
Keep the motion clip visually simple. The character image and scene image establish the visible world, while the motion pass establishes the timing and spatial plan.
Write the AI video motion reference prompt by role
Use a prompt that names the authority of each source before describing the scene:
Character reference: identity, face, hairstyle, clothing, and suitcase.
Scene reference: platform layout, train, lighting, materials, and atmosphere.
Motion reference: starting position, left-to-right route, camera path, pace, stop point, and final framing.
Create one continuous eye-level tracking shot. The character walks at an even pace from the left side of the platform to the open train door on the right, pulling the same suitcase. Preserve the character, wardrobe, train, platform layout, dusk light, and route. End with the character beside the door.
This structure is especially useful when the same shot needs a character move, a camera move, and a final story beat. Each instruction has a specific place, so the final prompt stays readable even when the scene becomes more detailed.
Three practical long-take scenes
Arrival at a destination
A travel-film creator can begin with a portrait or character image and a platform, airport, hotel, or street reference. The motion reference sets the walk from the arrival point to a clearly visible destination. The final frame can hold a door, sign, vehicle, or waiting person so the shot ends with a usable narrative beat.
Choreographed product movement
Keep exploring
More in AI Video Techniques

Motivated Cut AI Video Continuity: Change the Shot for a Reason
Learn how a visible action trigger, clear shot-size change, and locked screen direction create more intentional same-scene AI video edits.

Deep Depth of Field AI Video: Keep Every Story Layer Readable
Learn how deep depth of field AI video prompts keep foreground tools, central action, and distant location cues readable in one layered shot.

Medium Depth of Field AI Video: Balance Subject and Setting
Learn how medium depth of field AI video prompts keep hands and active objects readable while preserving recognizable environmental context.

AI Video Character Reference Framing: Match Portraits to Landscape Shots
Prepare vertical character portraits for landscape AI video by matching aspect ratio, body scale, headroom, floor space, and movement room before generation.

