LTX examples, prompts, settings and outputs
Examples for current LTX 2.3 Pro and LTX 2.3 Fast workflows, plus supported older LTX setups.
Browse LTX 2.3 Pro and LTX 2.3 Fast prompt examples, reusable settings, and output patterns, then review supported LTX 2 and LTX 2 Fast setups for older workflows, historical prompt baselines, and migration context. Use this page to study prompt structure, image-to-video AI patterns, and model-specific settings before opening the matching LTX model page.
Strengths and limits by model
Pricing notes (varies by model)
LTX 2.3 Pro and LTX 2.3 Fast lead this page for prompt examples, reusable settings, outputs, and image-to-video patterns, with LTX 2 and LTX 2 Fast kept below for supported older workflows and migration context.
Next steps
LTX models FAQ
What are the best LTX 2.3 prompt examples to start from?
The best starting point is a simple structure: subject, action, camera direction, and style goal. The strongest examples keep that structure stable while changing only one variable at a time.
How should I structure an LTX 2.3 prompt?
Start with one clear subject, one main action, one camera instruction, and one visual style cue. LTX 2.3 prompts usually work better when the motion goal is explicit and the scene description stays tight.
What settings matter most for LTX 2.3 outputs?
The main settings to watch are duration, aspect ratio, source image choice for image-to-video, and how much motion complexity you ask for in a single prompt. Keeping those stable makes prompt testing much easier.
How should I prompt LTX 2.3 for image-to-video?
Start from a strong source image, then add one motion instruction, one camera movement, and one output goal. LTX 2.3 image-to-video works best when the prompt extends the source image instead of replacing it with a completely different scene.
Which LTX model should I use: LTX 2.3 Pro or LTX 2.3 Fast?
Use LTX 2.3 Pro when you want the strongest current LTX output quality and more advanced workflows like audio, Extend, and Retake. Use LTX 2.3 Fast when you want quicker, lower-cost prompt testing and longer draft iteration loops.