ComfyUI — ComfyUI is a modular AI creation engine featuring a visual node graph interface for generating images, videos, audio, and 3D models using state-of-the-art open-source and closed-source models.

ComfyUI is a modular AI creation engine featuring a visual node graph interface for generating images, videos, audio, and 3D models using state-of-the-art open-source and closed-source models.

About this project

ComfyUI is a powerful AI engine designed for visual professionals, providing a modular node-based interface that allows for precise control over models, parameters, and outputs. It supports a wide array of generative tasks including text-to-image, image editing, video generation, audio synthesis, and 3D vision. Key capabilities include: - Visual Workflow Design: Build and reuse complex workflows for media generation without writing code using a node graph. - Broad Model Support: Native support for numerous models such as Stable Diffusion (1.5, SDXL, SD3.5), Flux.1, Wan, Hunyuan, and various LLMs like Gemma and Qwen. - Performance Optimization: Features asynchronous queueing, smart VRAM/RAM management, model offloading, and support for quantized models. - Production Integration: Offers API endpoints for pipeline integration and an "App Mode" to simplify sophisticated workflows into a basic UI. - Extensibility: Supports custom nodes and the ComfyUI-Manager extension for easy installation and updates of community-made nodes. - Cross-Platform Availability: Runs on Windows, Linux, and macOS, supporting a variety of hardware including NVIDIA, AMD, Intel, Apple Silicon, Ascend NPUs, and Cambricon MLUs. - Media Handling: Supports high bit-depth images (16-bit PNG, 32-bit EXR) and HDR video formats.