$ loading_
Build multi-model agent workflows in ComfyUI with voice, OCR, and LAG integration.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "comfyui_LLM_party" yet — see the docs or source repo.
Design a ComfyUI workflow using comfyui_LLM_party: after a user submits a question, first use an OCR node to extract text from an image, then pass it to a local LLM for summarization, and finally send the result to Feishu. List the node structure, connections, and configuration suggestions.
A practical multi-node workflow plan with OCR, LLM, and Feishu integration details.
I want to connect both an Ollama local model and the Gemini API in comfyui_LLM_party, and switch between them through a unified interface. Provide setup steps, parameter examples, and how to configure them in ComfyUI nodes.
Instructions covering local and cloud model setup, unified invocation config, and example node parameters.
Use comfyui_LLM_party to design an assistant that receives user text, generates a reply with an LLM, then synthesizes speech with ChatTTS or GPT-SoVITS, and sends both the text and audio to Discord. Output the workflow design and key node explanations.
An agent workflow plan linking text generation, speech synthesis, and Discord delivery.
Expose ComfyUI workflows as MCP tools for LLM-driven image generation.
Let AI agents control local ComfyUI for workflows, image generation, and model management.
Edit ComfyUI workflows in Claude to generate media and manage models.
Turn ComfyUI character avatars into tools with controllable expressions, poses, and parameters.
Generate anime-style images with ComfyUI and preview them directly in chat.
Connect external coding agents with ComfyUI for image, text, and workflow runs.