Prompting Guide
Production Guides
Practical workflows for screen-based visuals
Studio-grade notes for live visuals, stage screens, and motion tests before the work moves into playback, compositing, or finishing.
Made for MotionLab
Read This First
This guide is written for the MotionLab video model. MotionLab starts from an image and turns it into a moving clip of 4–20 seconds — so your prompt's job is to direct what happens over time, not to repaint the picture. Renders now carry a soundtrack too, but it is generated from what happens on screen, so keep every sentence about what the camera can see.
Pro Tip: If you re-describe the image in detail, the model spends its effort confirming the frame instead of animating it. One short anchor sentence about the scene is enough — then move straight to motion.
Prompt the Motion, Not the Picture
The Golden Rule
The model already sees your image. Focus every sentence on what happens next: how the subject moves, how the camera travels, and what shifts in the light and atmosphere around them.
Prompt Formula
[Scene anchor] + [Subject action] + [Camera movement] + [Environment in motion]
Weak Prompt
"A red sports car parked on a wet city street at night, neon signs, reflections, cinematic, 4K."
Strong Prompt
"The camera slowly orbits the parked sports car as neon reflections slide across its wet paint. Steam drifts up from a grate behind it, and light rain begins to streak through the glow of the signs."
Structure & Length
Writing the Prompt
Write one flowing paragraph in present tense — not keyword tags, not bullet points. Use connectors like "as," "then," and "while" so actions flow into each other naturally from beginning to end.
One paragraph, present tense
"The dancer spins, her dress flaring outward" — not "dancer, spinning, dramatic, HD." The model understands natural language and the relationships between elements.
Match length to duration
2–3 sentences of motion suit a 4–6 second clip; a 12–15 second clip needs 5–8 sentences describing a sequence of beats. A short prompt on a long clip makes the model rush or drift.
Sequence longer clips in time
Give longer clips an order of events: "The camera holds steady at first. Then it begins a slow push-in as the fog thickens and the figure turns toward the light."
Show emotion physically
Write "her shoulders slump and she stares at the empty cup" instead of "she is sad." The model renders what a camera can see, not internal states.
Camera Language
Cinematography
The model understands standard cinematography vocabulary. Commit to one clear camera behavior per clip — a single clean move always looks better than two competing ones.
Pick one move
Dolly in / pull back, tracking shot alongside the subject, pan across, tilt upward, slow orbit, handheld follow, or a static locked-off frame.
Set the intensity
Pair the move with a speed: "subtle," "gentle," "steady," "gradual" for calm shots — "sweeping," "rapid" for energy. An unqualified camera move tends to come out medium-fast.
Scale & framing
Close-up, medium shot, wide establishing shot, overhead view. Close-ups need more fine detail in the prompt; wide shots need more environment.
Film effects
Film grain, lens flares, shallow depth of field, motion blur, slow motion, time-lapse — name them explicitly if you want them.
Light, Atmosphere & Style
Setting the Mood
Light and atmosphere are the strongest mood levers — and the best source of motion in otherwise static parts of the frame.
One lighting logic
Pick a single light source and give it behavior: "low golden-hour sun casts long shadows," "a neon sign flickers, tinting the fog pink." Conflicting light directions confuse the model.
Animate the atmosphere
Fog rolls, dust drifts through light beams, rain streaks, reflections shift, embers rise. Atmosphere in motion is what makes a clip feel alive.
Give static regions a job
If part of your image is empty — sky, water, a wall — assign it motion: "clouds drift slowly across the sky," "ripples spread across the still water."
Name the medium for stylized looks
"Watercolor," "hand-drawn animation," "claymation," "analog film" — committing to a medium keeps the style stable across every frame.
Reference Images in MotionLab LTX 2.5
Direct the Cast
Use the Start image as the scene anchor, then add 1–4 Reference images for the people, objects, clothing, or locations you want MotionLab LTX 2.5 to bring into that scene. The model plans the images together, so the prompt should give every reference a clear purpose, role, action, and position instead of simply asking it to copy the uploads.
Pro Tip: Describe relationships, actions, and placement rather than re-describing every pixel. Clear direction gives MotionLab LTX 2.5 a better plan for combining the scene and subjects.
Prompt Formula
[Scene from the Start image] + [Reference 1 role and action] + [Reference 2 role and action] + [Camera and environment motion]
Weak Prompt
"Use these references in the scene."
Strong Prompt
"On the subway platform from the Start image, Reference 1 is the woman in the red coat walking toward the camera. Reference 2 is the silver case in her right hand, and Reference 3 supplies her black jacket. The camera tracks backward as train lights sweep across the platform."
Start image = scene anchor
Treat the Start image as the composition, background, and spatial logic of the shot. References are the cast and ingredients placed inside it; they should not compete with or replace the scene.
Name every reference
Use the exact slot names — "Reference 1," "Reference 2," and so on — and state what each one is doing and where it belongs. The numbering follows the slots from left to right.
Choose the correct type
Tag each slot as Person, Object, Clothing, or Location. The type helps MotionLab LTX 2.5 frame and crop that source correctly.
Prepare clean source images
Use one clear subject per image. A transparent PNG is ideal; a plain, high-contrast background is the next best option. Ordinary photos can work, but extra scenery may be interpreted as part of the reference.
Camera remains available
You can still choose a Camera move in LTX 2.5 reference mode. Other incompatible controls are disabled automatically while Reference images are present.
Identity is guidance, not a guarantee
References strongly guide appearance, palette, and silhouette, but exact identity, fine details, readable text, and logos are not guaranteed. Use fewer, cleaner references with non-conflicting roles for the most consistent result.
Motion Reference Video
Bring Your Own Movement
Drop an MP4 into the cyan MOTION slot next to your image and the render follows that clip's movement instead of inventing its own. It transfers motion — the camera path, the timing, the rhythm — not the look: the subject, palette, and style still come from your start image and prompt.
Use it when timing matters
A move you already storyboarded, a beat you have to hit, a camera path from an existing shot, or a gesture you want repeated across several clips. A phone clip is enough — it is read for movement, not quality.
Clip requirements
MP4, up to 50 MB and 60 seconds, and at least as long as the clip you are rendering. MotionLab re-encodes it in your browser to the fps you selected and trims it to your duration before it is sent.
The prompt still directs the scene
Keep writing the shot as usual. The reference decides how things move; the prompt decides what is moving, how it is lit, and what the atmosphere does.
Costs a small add-on
A reference video adds a fixed amount of credits to the render, shown in the price next to the generate button before you commit.
Loop & Cyclic Motion
VJ & Motion Graphics
Turn on Loop in the video page and MotionLab renders the clip back to its opening frame — a seamless loop straight out of the generator, with no crossfade pass in an editor. Loop runs on MotionLab image-to-video renders: it needs a start image (the frame it returns to) and cannot be combined with an End image. Every Loop render is seam-checked, and the clip is marked when the join is still visible.
Prompt motion that wants to cycle
The switch closes the seam; the motion decides whether it reads. Direction like "cyclic motion," "steady rhythm," or "continuous repetitive movement" — wind, waves, smoke, rotation, breathing light — loops convincingly. A one-time event inside the clip still reads as a restart on the second pass.
Loop and audio
The soundtrack is joined smoothly at the seam. If you upload your own audio, it only loops cleanly when its length matches the clip — so you can either keep the smooth join or mute the audio and let the video loop on its own.
Subject Isolation
Keep the background description minimal or solid-colored if you plan to extract the subject later for transparent overlays.
Sound & Music
Audio
MotionLab renders used to be silent. They are not any more: the Audio switch on the video page is on by default, and the soundtrack is generated to match what happens on screen. You can also hand the render a track of your own, or write music from scratch in the separate Music mode.
Pro Tip: For lyrics, use tags such as [Verse], [Chorus], and [Bridge]; for a timed arrangement, write lines like "[0:00 - 0:10] soft piano intro". Choosing Instrumental explicitly is more reliable than hoping a prompt stays wordless.
Audio switch
On by default — the finished MP4 carries a generated soundtrack. Turn it off when you need a silent deliverable: LED walls, loops running under a live set, or footage going into an edit with its own mix.
Audio to Video
Drop an MP3 or WAV into the amber AUDIO slot and the render follows your track's timing and energy instead of generating its own. The file is trimmed in your browser to the clip length before upload, and the render costs a small add-on.
Audio and Loop together
With Loop on, the audio is joined smoothly at the seam. If you uploaded your own track, it only loops cleanly when its length matches the clip — so you can keep the smooth join, or mute the audio and let the picture loop on its own.
Music mode
Switch the create dock to Music to generate a track: Lyria 3 writes 30 seconds, Lyria 3 Pro up to three minutes, both as MP3. Describe the brief in plain language, then open Advanced for genre, mood, instruments, structure, BPM, key, vocals, language, lyrics, and a timed arrangement.
What Works Well
Strengths
The MotionLab 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.
What to Avoid
Known Limitations
To get the best results, avoid these patterns:
Things to Avoid
Motion Studio (Beta)
Chat-to-Motion-Graphics
Motion Studio is a different kind of tool: instead of generating footage from a model, you describe a motion-graphics piece in chat — a stage opener, kinetic type, an LED loop, a product reveal — and it is composed as live motion code that previews instantly and exports to MP4 from your browser. It works best for graphic, typographic, and geometric motion rather than photorealistic scenes.
Pro Tip: Motion Studio is in beta: behavior and available models may change, and complex requests can take a retry or two. Precise, incremental direction gets the best results.