JST-1: The first video-3d foundation model

JST-1: The first video-3d foundation model

Viggle is powered by JST-1, the first 3D video base model with a real physical understanding.

The new model has improved the following features:

  • text-to-image model

  • character consistency, especially facial features

  • video generation speed

  • video quality

  • variety of motion

This is an amazing tool for style transfer.

Here is my experiment:

Lil Yachty version
JST-1

In conclusion, Viggle's JST-1 model represents a significant advancement in 3D video base models, offering enhanced text-to-image capabilities, character consistency, video generation speed, quality, and a wider range of motion. This tool provides exciting opportunities for style transfer and creative experimentation in video production.