LTX 2.3 Text to Video Fast is LTX's text-to-video model on Versely. This page is its structured prompting reference: the 6 parameters its schema actually exposes, the t2v technique that applies to it, copy-ready templates.
Everything here is grounded in the same sources Versely's agent reads — the model's input schema. Where a line is general craft advice rather than a documented fact about LTX 2.3 Text to Video Fast, the page says so.
What LTX 2.3 Text to Video Fast wants
The exact input surface, from the same schema the Versely agent fetches with get_model_input_schema before every generation.
| Parameter | What it does | Values |
|---|---|---|
promptreq | Text prompt | string |
duration | Seconds (up to 20s for fast) | integer |
aspect_ratio | Aspect ratio (landscape & 9:16 portrait) | stringdefault: auto |
audio | Audio toggle (alias for generate_audio) | boolean |
generate_audio | Generate audio | boolean |
resolution | Resolution | 1080p · 1440p · 2160pdefault: 1080p |
Technique that applies here
Text-to-video: scene narrative, camera movement, temporal flow; negative prompts where supported
- VEO, Kling, and Sora all carry a MODEL_TIPS rule the prompt enhancer applies automatically, and all three converge on naming the camera: VEO's tip says to 'include camera angles, movement types (dolly, crane, steadicam), lighting setup, and temporal flow' and to 'be specific about scene transitions'; Kling's tip asks for 'camera movement (pan, zoom, tracking shot), subject action, and environment details... motion direction and pacing'; Sora's tip wants 'clear scene narratives, camera movements, and temporal progression.' None of these schemas expose a camera-movement parameter — the enhancer is rewriting your prose toward this language, so writing the move by name yourself ('slow dolly-in,' 'tracking shot following the subject') works with the family instead of getting rewritten.
- Seedance and MiniMax want a different register from the camera-forward families. Seedance's tip is 'motion-focused descriptions... movement patterns, choreography, and dynamic visual elements'; MiniMax's is 'narrative prompts... scene progression, character actions, and visual atmosphere in natural language.' Neither asks for named camera hardware — lead with what's moving and how the scene unfolds, not with lens or shot vocabulary.
- General technique, not model-specific: where a model exposes a real negative_prompt field (Kling, Pixverse, LTX, Wan, VEO's fal variant), put exclusions there instead of writing 'no X' into the scene description — it's a separate parameter, read independently of the prompt. And where a generate_audio-style boolean exists, decide sound as that parameter, not as a prose request — defaults vary even within one family (Kling's O3 tier defaults generate_audio to false while its V2.6/V3 tiers default it to true).
Copy-ready templates
Replace the bracketed slots; each template says when it's the right shape.
[SUBJECT] [ACTION] in [SETTING]. Camera: [CAMERA MOVEMENT — e.g. slow dolly-in / handheld tracking shot / static locked-off]. Lighting: [LIGHT DESCRIPTION]. Transition: [HOW THE SHOT RESOLVES].
Use when: VEO, Kling, or Sora-family t2v models — their applied MODEL_TIPS reward named camera movement and explicit transitions.
[MAIN PROMPT TEXT]. Negative prompt: [ELEMENTS TO EXCLUDE — e.g. text, watermark, blurry, extra limbs, distorted hands].
Use when: models whose schema exposes a separate negative_prompt field (Kling, Pixverse, LTX, Wan, VEO's fal variant) — exclusions belong in that field, not folded into the scene description.
How the Versely agent does this automatically
You can use this page by hand, or let the agent apply the same knowledge. Four real mechanisms — no more, no less:
get_model_input_schema— before generating, the agent looks up LTX 2.3 Text to Video Fast's exact input fields, required fields, allowed values, defaults, and min/max bounds. The parameter table above is that same surface.- The prompt enhancer's family rules — 12 per-family rewrite rules (this model's family isn't one of the 12, so only general enhancement applies) shape how a rough prompt gets rewritten.
- The per-provider speech guide — for TTS scripts, the agent follows a provider-specific tag scheme — not relevant to this model, but it's why voiceover scripts come out marked up correctly.
expand_movie_scene— in movie flows, brief scene ideas are rewritten into detailed cinematic descriptions before generation.
Mistakes that waste generations
- Writing a multi-beat script (three different actions or cuts) into one generation call on a model capped well under 15s — VEO tops out at 8s per call, Sora 2's kie variant only offers 10 or 15 frames — and the model compresses everything into a blur or drops the later beats rather than pacing through your scenes.
- Describing aspect ratio or resolution in prose ('shot in glorious 4K widescreen') instead of setting the actual aspect_ratio/resolution enum — the text has no effect on frame shape or output resolution, only the parameter does, and on Sora 2 the valid values are the words 'portrait'/'landscape', not a ratio string at all.
- Using one family's register on another: a dense Kling-style shot list ('slow pan, then a hard cut to a tracking shot') fights a Wan model's 'straightforward... style keywords' tip, and a plain narrative sentence undersells VEO or Sora's named-camera-movement tip.
The long-form guide
This page is the structured reference. For the essay treatment — worked examples, failure modes, and narrative — read LTX 2.3 Prompting Guide: Fast Iteration Patterns.
This guide also covers
These siblings share LTX 2.3 Text to Video Fast's prompting-relevant input surface, so their prompting URLs resolve here — tier and pricing differences live on their own model pages:
Frequently asked questions
Does LTX 2.3 Text to Video Fast support negative prompts?+
No — LTX 2.3 Text to Video Fast's published schema has no negative_prompt parameter. Exclusions have to be phrased positively inside the main prompt, or dropped.
How does the Versely agent know LTX 2.3 Text to Video Fast's parameters?+
Before generating, the agent calls its get_model_input_schema tool, which looks up the exact input fields, required fields, allowed values, defaults, and min/max bounds for the model. Nothing on this page is guessed — it is the same schema surface those tools read.
Does this guide also cover LTX 2 Text to Video Pro and LTX 2 Text to Video Fast?+
Yes. LTX 2 Text to Video Pro, LTX 2 Text to Video Fast share the same prompting-relevant input surface as LTX 2.3 Text to Video Fast, so their prompting URLs redirect here instead of duplicating this page. Tier and pricing differences live on each model's own /models page.
Related prompting guides
Generate with LTX 2.3 Text to Video Fast
LTX 2.3 Text to Video Fast is live in Versely — paste a template above, or just describe what you want and let the agent map it onto the schema for you.