LLaVA is an open-source multimodal model (vision + language): it combines a vision encoder with a large language model to chat about images, screenshots and charts, widely used as It is listed on hedirbase, a curated directory of AI tools, developer resources, and direct-to-consumer brands for the independent workforce.

What category does LLaVA belong to?

LLaVA is listed under the Open Source LLMs category on hedirbase.com.

Where can I visit LLaVA?

You can visit LLaVA at its official website: https://llava-vl.github.io.

Is LLaVA open source?

Yes, LLaVA is open source. Its source code is available on GitHub: https://github.com/haotian-liu/LLaVA.

What are similar tools or brands to LLaVA?

Similar listings in the same Open Source LLMs category include: DeepSeek, Ollama, Whisper, Aya Expanse. Browse the category page on hedirbase.com for more options.

Open Source LLMs

LLaVA

🇨🇳 中文 / 🇬🇧 English — 双语介绍

🔗 https://llava-vl.github.io

🇨🇳 中文

LLaVA 是开源的多模态大模型（视觉+语言）：把视觉编码器和大语言模型结合，能看图聊天、理解截图和图表，被社区广泛用作本地多模态 AI 的基座。项目由威斯康星大学团队开源。 🔗 GitHub: https://github.com/haotian-liu/LLaVA | ⭐ 25k+

🇬🇧 English

LLaVA is an open-source multimodal model (vision + language): it combines a vision encoder with a large language model to chat about images, screenshots and charts, widely used as the base for local multimodal AI. Open-sourced by a University of Wisconsin team. 🔗 GitHub: https://github.com/haotian-liu/LLaVA | ⭐ 25k+