MotionLab

Prompting Guide

Learn how to write effective prompts for video, image, and 3D generation.

01
✏️

Writing Great Prompts

The Basics

The key to great results is painting a complete picture — a scene that flows naturally from beginning to end, covering all the elements the model needs to bring your vision to life.

Write as a single paragraph: Describe your scene as one flowing paragraph in present tense. Aim for 4–8 descriptive sentences.
Be specific, not vague: Instead of tagging keywords, describe the scene naturally. The model understands context and relationships between elements.

Pro Tip: You don't need to repeat yourself or use tag-style prompts. State your intent clearly in natural language and let the model interpret the full scene.

02
🎬

The Screenplay Standard

Cinematic Structure

For optimal results, write your prompt as a screenplay scene. Use present tense and describe things as they happen.

Prompt Formula

[Setting/Context] + [Subject & Action]

Weak Prompt

"Cool robot, fighting, explosions, loud noise, HD."

Strong Prompt

"INT. HANGAR. A rusted battle-droid repairs its own arm."

03
🧩

Key Elements to Include

Building Your Scene

Every great prompt addresses these elements. You don't need all of them every time, but the more you include, the better the result.

1. Establish the Shot

Use cinematography terms that match your genre. Include shot scale (close-up, wide, medium) to refine the visual style.

2. Set the Scene

Describe lighting conditions, color palette, surface textures, and atmosphere to establish mood and tone.

3. Describe the Action

Write the core action as a natural sequence, flowing clearly from beginning to end.

4. Define the Character(s)

Include age, hairstyle, clothing, and distinguishing features. Express emotion through physical cues, not abstract labels.

5. Camera Movement

Specify how and when the camera moves. Describing how subjects appear after the movement helps the model complete the motion accurately.

04
📷

Camera & Visual Language

Cinematography

Use camera terms directly in your prompt to control framing and movement. The model understands standard cinematography language.

Camera Movements

Use terms like: follows, tracks, pans across, circles around, tilts upward, pushes in, pulls back, overhead view, handheld movement, static frame.

Film Effects

Film grain, lens flares, shallow depth of field, motion blur, slow motion, time-lapse, freeze-frame, fade-in/fade-out.

Scale & Framing

Close-up, medium shot, wide establishing shot, over-the-shoulder. Match detail level to shot scale — close-ups need more detail than wide shots.

05
🔁

Loop & Animation Tips

VJ & Motion Graphics

MotionLab excels at continuous motion and seamless loops.

For Seamless Loops

Use keywords like "Seamless loop," "Cyclic motion," and "Infinite flow."

Subject Isolation

Keep the background description minimal or solid-colored if you plan to extract the subject later for transparent overlays.

06

What Works Well

Strengths

The model excels at these types of content:

Cinematic Compositions

Wide, medium, and close-up shots with thoughtful lighting, shallow depth of field, and natural motion.

Emotive Human Moments

Strong single-subject emotional expressions, subtle gestures, and facial nuance.

Atmosphere & Setting

Fog, mist, golden-hour light, rain, reflections, ambient textures.

Stylized Aesthetics

Painterly, noir, analog film, fashion editorial, pixelated animation, stop-motion, claymation.

07
⚠️

What to Avoid

Known Limitations

To get the best results, avoid these patterns:

Things to Avoid

Internal emotions (use visual cues instead)Readable text or logosComplex physics / chaotic motionToo many characters in one sceneConflicting lighting directionsOverly complex prompts (start simple, add detail gradually)
Prompting Guide — How to Get the Best Results | MotionLab