Lightricks LTX 2.3 Video To Video

Prompt-guided LTX 2.3 video-to-video generation with frame-count and size controls.

Model Overview

LTX 2.3 Video To Video transforms an input video into a new output guided by a text prompt. It keeps the workflow focused on prompt-plus-video conditioning, with controls for frame count, size presets, FPS handling, multiscale generation, and conditioning strength.

Best At

• Reworking existing footage into a new motion or visual treatment.
• Fast prompt-driven video-to-video iteration.
• Controlled output sizing and frame-count tuning.

Limitations / Not Good At

• Pricing scales with generated video megapixels, so larger sizes and longer runs get expensive quickly.
• Match Video Length can make the preview estimate rougher if the input clip length is unknown in advance.
• It does not expose separate start-frame or end-frame image guidance.

Ideal Use Cases

• Prompt-guided restyling of an input clip.
• Lower-cost exploration before a heavier final render.
• Video-to-video iterations where direct video conditioning is enough.

Input & Output Format

• Input: required prompt and video_url; optional match_video_length, num_frames, video_size, generate_audio, fps, video_strength, and audio_strength.
• Output: generated video URI returned on response.

Performance Notes

• Cost is tied to output video megapixels, which means both frame count and size preset matter.
• Turning off Match Video Length gives a more predictable estimate because num_frames becomes explicit.