# LLaVA-NeXT Documentation

Welcome to the LLaVA-NeXT documentation. This guide provides an overview of the different components and features of LLaVA-NeXT. Please refer to the following documents for detailed information on specific topics:

1. [LLaVA OneVision](LLaVA_OneVision.md): Learn about the most advanced and unified version: LLaVA OneVision.
    - [LLaVA OneVision: Inference Tutorials](LLaVA_OneVision_Tutorials.ipynb): Learn how to use LLaVA OneVision for inference.
    - [LLaVA Onevision Chat](LLaVA_OneVision_Chat.md): Improving Chat with Preference Learning

2. [LLaVA-NeXT Interleave](LLaVA-NeXT-Interleave.md): Explore the interleaved training approach used in LLaVA-NeXT.

3. [LLaVA-NeXT Video (0716)](LLaVA-NeXT-Video_0716.md): Discover the video processing capabilities of LLaVA-NeXT (version 0716).

4. [LLaVA-NeXT Video](LLaVA-NeXT-Video.md): Get information about the latest video processing features in LLaVA-NeXT.

5. [LLaVA-NeXT Overview](LLaVA-NeXT.md): Read a comprehensive overview of the LLaVA-NeXT project, including its architecture, features, and capabilities.

These documents provide in-depth information on various aspects of LLaVA-NeXT. Please refer to them for detailed explanations, implementation details, and usage instructions.