- LTX-2.3 responds best to long, detailed prompts — the more specific you are about subject, action, lighting, camera movement, and audio, the closer the output matches your vision
- Break dialogue into short phrases with acting directions between each line, and use physical cues rather than emotional labels to direct character performance
- Match your prompt length to your video length — short prompts for long videos leave the model without enough direction to fill the duration
Strong prompts produce better videos. LTX models respond best to detailed, descriptive prompts that paint a complete picture of the scene you're generating. Think of it as writing a shot description for a cinematographer.
If you're new to writing prompts for video generation, this guide will help you construct effective, production-ready prompts.
Core Principles
Be specific and descriptive
Instead of "a person walking," try "a young woman in a red coat walking briskly through a rain-soaked Tokyo street at night, neon reflections on wet pavement, handheld camera following from behind."
Describe the full scene
Include the subject, their action, the environment, the lighting, and the camera behavior. The more complete your description, the closer the output matches your intent.
Use cinematic language
Terms like "macro lens," "tracking shot," "shallow depth of field," "golden hour," and "low angle" are understood by the model and directly influence the output.
Describe audio when relevant
For endpoints that generate synchronized audio, include audio descriptions in your prompt: "the sound of rain on pavement," "soft ambient music," "a crowd cheering in the distance."
What Changed in LTX-2.3
LTX-2.3 has a redesigned text connector architecture that makes it significantly more responsive to prompt details. This means:
More faithful prompt adherence
Specific descriptions of facial expressions, timing, pauses, and emotional beats translate more reliably into the output. You can direct acting at a granular level — "he pauses, looks to the side, then continues speaking with a cracking voice" — and expect the model to follow.
Prompt length matters
Longer, more descriptive prompts consistently outperform short ones on 2.3. If you're generating longer videos (8–10 seconds), make sure your prompt is detailed enough to fill the duration. A short prompt for a long video often results in the model rushing through the described action.
Break dialogue into segments
When prompting for speaking characters, break long sentences into shorter phrases with acting directions between them. For example:
A middle-aged man with greying hair speaks in a sad, slow-paced voice, "I remember after you kids came along..." He pauses and looks to the side, then continues, "your mom..." His eyes widen momentarily. He finishes with a cracking voice, "said something to me I never quite understood." The camera slowly zooms into his face. The audio is crisp with faint room tone.
This gives the model explicit direction on pacing, emotion, and physical acting for each beat.
Audio descriptions have more impact
With improved audio quality in 2.3, it's worth spending more attention on audio prompts. Describe the acoustic environment, the character's voice qualities, and any ambient sounds you want.
Key Elements to Include
When writing a prompt, aim to include the following elements:
1. Establish the Shot
Use cinematography terms that match your intended genre. Include shot scale or category-specific characteristics 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. Identify Camera Movement(s)
Specify how and when the camera moves. Describing how subjects appear after the movement helps the model complete the motion accurately.
6. Describe the Audio
Clearly describe ambient sound, music, speech, or singing.
- Place spoken dialogue in quotation marks
- Specify language and accent if needed
For Best Results
- Write your prompt as a single flowing paragraph
- Use present tense verbs for action and movement
- Match the level of detail to the shot scale — close-ups need more detail than wide shots
- Describe camera movement relative to the subject
Tips by Use Case
Text-to-Video
Start with a strong visual description. Include subject, action, environment, lighting, camera movement, and audio. The model generates everything from scratch, so detail is your primary lever.
Image-to-Video
Focus your prompt on the motion and action you want — the visual starting point is already defined by your input image. Describe what happens next: how the subject moves, how the camera follows, what sounds emerge. Avoid describing the static elements already visible in the image. Instead, describe the transition from stillness to motion.
Audio-to-Video
Your audio input anchors the temporal structure. Use the prompt to describe the visual interpretation of that audio — what scenes, subjects, and camera work should accompany the soundtrack.
What Works Well
What to Avoid
Common Mistakes
- Too vague: "A nice video of nature" — the model has too many options and picks arbitrarily. Be specific about what's in the frame.
- Over-constrained: "Exactly 3 birds flying left to right at 45 degrees while the camera pans right at 2 degrees per second" — the model works best with natural language descriptions, not numerical specifications.
- Mismatched duration: A 10-word prompt for a 10-second video — the model doesn't have enough direction to fill the duration. Long videos need long prompts.
- Conflicting directions: "A still, peaceful lake with dramatic waves crashing" — contradictions confuse the model. Be internally consistent.
Sample Prompts
Example 1
EXT. SMALL TOWN STREET – MORNING – LIVE NEWS BROADCASTThe shot opens on a news reporter standing in front of a row of cordoned-off cars, yellow caution tape fluttering behind him. The light is warm, early sun reflecting off the camera lens. The faint hum of chatter and distant drilling fills the air. The reporter, composed but visibly excited, looks directly into the camera, microphone in hand. Reporter (live): "Thank you, Sylvia. And yes — this is a sentence I never thought I'd say on live television — but this morning, here in the quiet town of New Castle, Vermont… black gold has been found!" He gestures slightly toward the field behind him. Reporter (grinning): "If my cameraman can pan over, you'll see what all the excitement's about." The camera pans right, slowly revealing a construction site surrounded by workers in hard hats. A beat of silence — then, with a sudden roar, a geyser of oil erupts from the ground, blasting upward in a violent plume. Workers cheer and scramble, the black stream glistening in the morning light. The camera shakes slightly, trying to stay focused through the chaos. Reporter (off-screen, shouting over the noise): "There it is, folks — the moment New Castle will never forget!" The camera catches the sunlight gleaming off the oil mist before pulling back, revealing the entire scene — the small-town skyline silhouetted against the wild fountain of oil.
Example 2
The camera opens in a calm, sunlit frog yoga studio. Warm morning light washes over the wooden floor as incense smoke drifts lazily in the air. The senior frog instructor sits cross-legged at the center, eyes closed, voice deep and calm. "We are one with the pond." All the frogs answer softly: "Ommm..." "We are one with the mud." "Ommm..." He smiles faintly. "We are one with the flies." A pause. The camera pans to the side towards one frog who twitches, eyes darting. Suddenly its tongue snaps out, catching a fly mid-air and pulling it into its mouth. The master exhales slowly, still serene. "But we do not chase the flies..." Beat. "not during class." The guilty frog lowers its head in shame, folding its hands back into a meditative pose. The other frogs resume their chant: "Ommm..." Camera holds for a moment on the embarrassed frog, eyes closed too tightly, pretending nothing happened.
Helpful Terms
Categories
- Animation: Stop-motion, 2D / 3D animation, Claymation, Hand-drawn
- Stylized: Comic book, Cyberpunk, 8-bit pixel, Surreal, Minimalist, Painterly, Illustrated
- Cinematic: Period drama, Film noir, Fantasy, Epic space opera, Thriller, Modern romance, Experimental film, Arthouse, Documentary
Visual Details
- Lighting: Flickering candles, Neon glow, Natural sunlight, Dramatic shadows
- Textures: Rough stone, Smooth metal, Worn fabric, Glossy surfaces
- Color Palette: Vibrant, Muted, Monochromatic, High contrast
- Atmosphere: Fog, Rain, Dust, Smoke, Particles
Sound and Voice
- Ambient Settings: Coffeeshop noise, Wind and rain, Forest ambience with birds
- Dialogue Style: Energetic announcer, Resonant voice with gravitas, Distorted radio-style, Robotic monotone, Childlike curiosity
- Volume: Whisper, Mutter, Shout, Scream
Technical Style Markers
- Camera Language: Follows, Tracks, Pans across, Circles around, Tilts upward, Pushes in / pulls back, Overhead view, Handheld movement, Over-the-shoulder, Wide establishing shot, Static frame
- Film Characteristics: Film grain, Lens flares, Pixelated edges, Jittery stop-motion
- Scale Indicators: Expansive, Epic, Intimate, Claustrophobic
- Pacing and Temporal Effects: Slow motion, Time-lapse, Rapid cuts, Lingering shot, Continuous shot, Freeze-frame, Fade-in / fade-out, Seamless transition, Sudden stop
- Visual Effects: Particle systems, Motion blur, Depth of field
