LTX-2.3
Introducing LTX-2.3 — a major leap in quality and speed for AI video generation. LTX-2.3 is now the default model across the API, available in two variants:
- LTX-2.3 Pro (
ltx-2-3-pro) — best-in-class quality, supports all endpoints including audio-to-video, retake, and extend. - LTX-2.3 Fast (
ltx-2-3-fast) — blazing fast generation, supports text-to-video and image-to-video.
What’s new
- Sharper fine details — new latent space with an updated VAE delivers noticeably crisper output.
- Cleaner audio — improved data filtering reduces background noise and artifacts.
- Stronger image-to-video — more natural motion, fewer static clips, and better visual consistency.
- Better prompt understanding — improved text connector architecture for closer adherence to complex prompts.
- Last-frame interpolation — provide a first and last frame to the image-to-video endpoint, and the model generates the video in between.
- Portrait video support — native 9:16 vertical video generation across all resolutions.
- 24/48 FPS — new frame rate options alongside the existing 25/50 FPS.
Extend Video Endpoint
New v1/extend endpoint for extending video duration by generating additional frames at the beginning or end.
Upload Endpoint
New v1/upload endpoint for uploading assets via signed URLs.
Camera Motion Effects
Camera motion support for image-to-video and text-to-video endpoints, giving direct control over camera movement in generated videos. Options: dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, and focus_shift.
Developer Console Public Launch
The developer console is now open to the public with self-service signup, automatic organization creation, and prepaid billing with credit top-up.
Audio-to-Video API
New audio-to-video endpoint for generating videos driven by audio input, with dedicated prompt enhancement.
Retake (Video Editing) Endpoint
New retake endpoint for editing specific sections of existing videos using text prompts.
LTX Video API Launch
Initial public API with image-to-video and text-to-video endpoints. Multiple model support, built-in prompt enhancement, concurrency-based quotas, and full API documentation.
