comfyui-mixlab-nodes is a large collection of custom nodes for ComfyUI that turns workflows into interactive apps and adds real-time multimedia, LLM, and TTS capabilities. It introduces a “Workflow-to-APP” concept, where a ComfyUI graph can be transformed into a Web App through an AppInfo node, complete with categories, batch prompts, and editable configurations. The project also brings Real-time Design features like screen capture and floating video nodes, enabling creative pipelines that mix live screen content, generative models, and visual effects. For audio and speech, it provides nodes for SpeechRecognition and SpeechSynthesis, plus workflows that combine voice generation with real-time face swapping and other audio-visual effects. On the AI side, it integrates multiple LLM providers (cloud and local), supports OpenAI-compatible endpoints, Siliconflow models, and includes prompt-focused utilities for random prompt generation, Chinese prompts, clip interrogation.
Features
- Workflow-to-APP system that turns ComfyUI graphs into configurable web apps
- Real-time screen share and floating video nodes for live design and LCM-based workflows
- SpeechRecognition and TTS nodes plus example workflows combining audio and avatars
- Multi-LLM integration with OpenAI-compatible, local, and Siliconflow-based models
- Extensive prompt, layer, 3D, image, and style nodes for advanced creative control
- Utility features like DynamicDelayByText, missing-node helpers, and right-click text-to-text shortcuts