Today we're launching three new LoRAs for our open source video model, LTX Video! 🕺 Pose LoRA 🏞️ Depth LoRA ✏️ Canny LoRA Get unprecedented control over your AI videos and train new control types with just a few samples on consumer hardware. Details below 👇

1. Pose LoRA 🕺 Pose LoRA captures body skeletons from reference videos, letting you guide motion and character positioning with incredible accuracy and precise control over character movement. 1/4

2. Depth LoRA 🏞️ This feature reads the spatial relationships in a frame, maintaining perfect depth, scale, and 3D structure in your videos. Say goodbye to flat scenes. 2/4

3. Canny LoRA ✏️ For sharp, precise style translation, Canny LoRA extracts high-fidelity edge details like facial features and outlines. Achieve remarkable clarity and detail in your creations. 3/4

We're also releasing open-source training code for true accessibility. Try them today: 4/4

Posting great content on X? Subscribe to Premium to join our revenue share program.

Cool! How exactly would I use this?

You can download and run them locally using ComfyUI.

Outstanding!

Thank you 🙏❤️

🫡

Let's connect for collaboration @LTXStudio