What types of LLMs does comfyui_LLM_party support?
The tool supports a wide range of LLMs, including those with OpenAI-like interfaces (e.g., OpenAI, Ollama, Gemini, Grok), AISuite-compatible models (Anthropic, AWS Vertex, Huggingface), and local models in distributed, GGUF, and VLM formats like Llama-3.2-Vision and Janus-Pro.
Can I integrate comfyui_LLM_party with social applications?
Yes, the framework allows for access and integration with social applications such as Feishu and Discord. This enables users to build AI assistants that can interact with these platforms, enhancing communication and workflow automation.
How do I install comfyui_LLM_party?
You can install it by searching in the ComfyUI Manager, cloning the GitHub repository into your custom_nodes folder, or downloading the zip and extracting it. For Windows users, a portable package is also available.
Does this tool support local LLMs and VLMs?
Absolutely. comfyui_LLM_party is adapted to local LLMs, VLMs, and GGUF models. It provides specific nodes for managing and utilizing local models, including support for Llama-3.2-Vision, Qwen/Qwen2.5-VL, and deepseek-ai/Janus-Pro.
What is the purpose of the MCP tool integration?
The MCP tool allows connection to an MCP server, converting its tools into directly usable tools for LLMs. By configuring different local or cloud servers, users can access and utilize a wide array of LLM tools available globally.