Models / LTX / Text to video

LTX text to video prompting guide

How to prompt LTX in text-to-video mode. Every point links its source; community tips are marked. Your agent gets the same guide through the Atlas MCP (get_guide).

Prompt structure

shot→scene→action→characters→camera→audio

• Establish the shot (cinematography, scale); set the scene (light, palette, texture, atmosphere); action as a flowing sequence with active verbs; characters with emotion shown physically; camera movement and how subjects look after it; audio. source ↗

Responds well to

• Best: cinematic single-subject scenes, clear camera language, consistent lighting, described audio; dialogue in quotes with language/accent. source ↗

Duration and limits

• API: generate_audio default true; fps default 24; retake section ≥2 s on inputs ≥73 frames; extend 2–20 s (context+duration ≤505 frames); audio-to-video length follows the audio. source ↗

Multi-shot

• Several shots joined by explicit cuts; re-establish framing, identity and audio at each cut. source ↗
• At every cut say whether music/dialogue/ambience continues or changes, and re-identify subjects. source ↗

Avoid and failure modes

• On-screen text spelling not guaranteed; chaotic physics causes artifacts. source ↗
• Don't paste a Kling/Seedance prompt into LTX unchanged: tag syntax and shot-list formatting don't carry over. Aim for ~4–8 descriptive sentences, present tense. source ↗

Negative prompt

Supported via .

Real prompts, credited

Steadicam walking shot, 15 seconds. Moving through a bustling outdoor night market in Southeast Asia. Food stalls with hanging lights, smoke rising from grills, colorful ingredients on display. Camera passes close to a vendor flipping noodles in a wok with visible flames. Shallow focus pulls between stalls. Warm tungsten lighting mixed with neon signs.

Aerial drone footage sweeping over a misty mountain valley at sunrise. Pine trees emerge through low clouds as golden light breaks over the ridgeline. A winding river reflects the warm sky below. The camera glides forward smoothly, gradually descending toward the treeline. Birds chirp in the distance, wind rushes past the microphone. Shot in 4K cinematic style, natural color grading.

Top-down shot slowly pushing in on hundreds of pastel dominoes perfectly aligned in a spiral pattern across a glossy white surface, each domino toppling in slow motion with

Next

Sources

• docs-dev.ltx.io/open-source-model/usage-guides/prompting-guide.md
• docs.ltx.io/api-documentation/api-reference/async-video-generation/submit-extend.md
• huggingface.co/Lightricks/LTX-2.5