LTX 2.3 text and image to video

LTX 2.3 is a fast open-source AI video model that generates video and audio together. One workflow covers both modes: start from a prompt, or switch on image-to-video to animate your own picture.

Great for:

• Fast AI influencer and character clips
• Animating cartoon and anime art
• Trying ideas quickly before a bigger render

How it works

1. Choose text-to-video or image-to-video.
2. Write your prompt (and load an image for image-to-video).
3. Run it. A second pass upscales the result, with audio.

Make it yours with LoRAs

This workflow supports LoRAs. Grab character, style, anime or cartoon LoRAs from CivitAI or Hugging Face, drop them into the LoRA loader, and keep your AI character looking the same in every shot.