multimodal

Anything Llm

JavaScript

AnythingLLM is a full-stack RAG application that turns documents into intelligent chatbots. Run local LLMs via Ollama or LM Studio for complete data privacy.

GLM Image

GLM Image is a multimodal model for text-to-image and image-to-image synthesis. Generate high-fidelity visual assets via transformer-based diffusion APIs.

GLM-V: Open-source VLM for advanced video & audio understanding. Integrates multimodal inputs for reasoning & image2text. Explore & contribute!