LTX2.3 Single-Person Audio-Driven Workflow

Workflow Introduction
This workflow is based on the LTX2.3 large model. It can generate videos from an input image and audio, allowing the character in the video to speak according to the provided audio.

Model Setup
The model configuration is the same as the other LTX workflows in DFCine. If you have already downloaded the required LTX models, you do not need to download them again. If not, please refer to the configuration guide for the workflow below:
https://dfcine.com/2556.html