Comfy-Org / ComfyUI

查看原文 / View Original 编辑 / Edit

Comfy-Org / ComfyUI

ComfyUI is the most powerful and modular AI engine for content creation. ComfyUI is the AI creation engine for visual professionals who demand control over every model, every parameter, and every output. Its powerful and modular node graph interface empowers creatives to generate images, videos, 3D models, audio, and more… ComfyUI 是目前功能最强大且模块化的 AI 内容创作引擎。它是专为视觉专业人士打造的 AI 创作工具，能够精准控制每一个模型、每一个参数以及每一个输出结果。其强大且模块化的节点图界面，助力创作者生成图像、视频、3D 模型、音频等多种内容。

ComfyUI natively supports the latest open-source state of the art models. API nodes provide access to the best closed source models such as Nano Banana, Seedance, Hunyuan3D, etc. It is available on Windows, Linux, and macOS, locally with our desktop application, our portable install or on our cloud. The most sophisticated workflows can be exposed through a simple UI thanks to App Mode. It integrates seamlessly into production pipelines with our API endpoints. ComfyUI 原生支持最新的开源顶尖模型。通过 API 节点，用户还可以访问 Nano Banana、Seedance、Hunyuan3D 等顶尖闭源模型。它支持 Windows、Linux 和 macOS 系统，可通过桌面应用程序、便携版安装包或云端进行本地部署。借助“应用模式”（App Mode），即使是最复杂的流程也能通过简洁的 UI 呈现。此外，它还能通过 API 端点无缝集成到生产工作流中。

Get Started

开始使用

Local Desktop Application: The easiest way to get started. Available on Windows & macOS. 本地桌面应用程序： 最简单的入门方式，适用于 Windows 和 macOS。

Windows Portable Package: Get the latest commits and completely portable. Available on Windows. Windows 便携版安装包： 获取最新提交版本，完全便携，适用于 Windows。

Manual Install: Supports all operating systems and GPU types (NVIDIA, AMD, Intel, Apple Silicon, Ascend). 手动安装： 支持所有操作系统及各类 GPU（NVIDIA、AMD、Intel、Apple Silicon、昇腾）。

Cloud: Comfy Cloud - Our official paid cloud version for those who can’t afford local hardware. 云端： Comfy Cloud —— 我们官方提供的付费云端版本，适合没有本地高性能硬件的用户。

Features

功能特性

A visual node graph for building and reusing image, video, audio, 3D, and text workflows without code. Reusable subgraphs, workflow templates, App Mode, and a local API for integrating workflows into applications. 提供可视化节点图，无需代码即可构建和复用图像、视频、音频、3D 及文本工作流。支持可复用的子图、工作流模板、应用模式以及用于集成到应用程序中的本地 API。

Efficient local execution with asynchronous queueing, partial graph re-execution, smart VRAM and RAM management, model offloading, and support for quantized models. 高效的本地执行能力，支持异步队列、局部图重执行、智能显存与内存管理、模型卸载以及量化模型支持。

Broad native model support: 广泛的原生模型支持：

  • Image generation: Stable Diffusion 1.5, SDXL, SD3.5, Flux.1, Flux.2, Qwen Image, Z-Image, Hunyuan Image 2.1, HiDream, Lumina Image 2.0, Chroma, Anima, LongCat Image, Ideogram 4, Krea 2, MageFlow, Microsoft Lens, PixelDiT, Kandinsky 5, and Ernie Image. 图像生成： 支持 Stable Diffusion 1.5, SDXL, SD3.5, Flux.1, Flux.2, Qwen Image, Z-Image, Hunyuan Image 2.1, HiDream, Lumina Image 2.0, Chroma, Anima, LongCat Image, Ideogram 4, Krea 2, MageFlow, Microsoft Lens, PixelDiT, Kandinsky 5 以及文心一格 (Ernie Image)。
  • Image editing: Flux Kontext, Flux.2 Klein, Qwen Image Edit, HiDream E1.1 and O1, OmniGen2, Boogu, JoyImage Edit, MageFlow Edit, and LongCat Image Edit. 图像编辑： 支持 Flux Kontext, Flux.2 Klein, Qwen Image Edit, HiDream E1.1/O1, OmniGen2, Boogu, JoyImage Edit, MageFlow Edit 以及 LongCat Image Edit。
  • Video generation: Wan 2.1 and 2.2, LTX-Video 2 and 2.3, HunyuanVideo 1.5, Kandinsky 5 Video, CogVideoX, Cosmos Predict2, Bernini-R, SCAIL 2, and Mochi. 视频生成： 支持 Wan 2.1/2.2, LTX-Video 2/2.3, HunyuanVideo 1.5, Kandinsky 5 Video, CogVideoX, Cosmos Predict2, Bernini-R, SCAIL 2 以及 Mochi。
  • Audio and video generation: MiniMax H3 and LTX-AV. 音视频生成： 支持 MiniMax H3 和 LTX-AV。
  • Audio generation: ACE-Step 1.5 and Stable Audio 3. 音频生成： 支持 ACE-Step 1.5 和 Stable Audio 3。
  • 3D and vision: Hunyuan3D 2.1, TripoSplat, SeedVR2, SUPIR, Depth Anything 3, MoGe, SAM 3 and 3.1, RT-DETRv4, and BiRefNet. 3D 与视觉： 支持 Hunyuan3D 2.1, TripoSplat, SeedVR2, SUPIR, Depth Anything 3, MoGe, SAM 3/3.1, RT-DETRv4 以及 BiRefNet。
  • Text generation: Gemma 3 and 4, Qwen3, Qwen3.5, and Qwen3-VL, including multimodal inputs. 文本生成： 支持 Gemma 3/4, Qwen3, Qwen3.5 以及 Qwen3-VL（包含多模态输入）。

Load complete checkpoints or separate diffusion models, VAEs, text encoders, LoRAs, ControlNets, adapters, and upscalers from supported model formats. Built-in tools for inpainting, outpainting, reference conditioning, masks and compositing, model merging, upscaling, frame interpolation, segmentation, depth estimation, and media processing. 支持加载完整的 Checkpoint 或分离的扩散模型、VAE、文本编码器、LoRA、ControlNet、Adapter 及放大器。内置工具涵盖重绘 (Inpainting)、外绘 (Outpainting)、参考条件控制、遮罩与合成、模型合并、放大、帧插值、分割、深度估计及媒体处理。

Runs fully offline: core does not download anything unless you request it. Use --disable-api-nodes to disable the optional paid Comfy API nodes and force all built-in functionality to stay offline. 完全离线运行：除非用户主动请求，否则核心程序不会下载任何内容。使用 --disable-api-nodes 参数可禁用可选的付费 Comfy API 节点，强制所有内置功能保持离线状态。

Release Process

发布流程

ComfyUI follows a weekly release cycle targeting Monday but this regularly changes because of model releases or large changes to the codebase. There are three interconnected repositories: ComfyUI 遵循每周一发布的周期，但常因模型发布或代码库重大变更而调整。项目包含三个互相关联的仓库：

  1. ComfyUI Core: Releases a new major stable version (e.g., v0.7.0) roughly every 2 weeks. ComfyUI Core： 大约每两周发布一个主要稳定版本（如 v0.7.0）。
  2. Comfy Desktop: Builds a new release using the latest stable core version. Comfy Desktop： 使用最新的稳定核心版本构建发布。
  3. ComfyUI Frontend: Every 2+ weeks frontend updates are merged into the core repository. ComfyUI Frontend： 每两周以上将前端更新合并到核心仓库中。

Shortcuts

快捷键

  • Ctrl + Enter: Queue up current graph for generation (将当前图加入生成队列)
  • Ctrl + S: Save workflow (保存工作流)
  • Ctrl + O: Load workflow (加载工作流)
  • Ctrl + Z/Y: Undo/Redo (撤销/重做)
  • Space: Move the canvas (按住并移动鼠标以平移画布)
  • Alt + +/-: Canvas Zoom in/out (画布缩放)
  • (Note: macOS users can replace Ctrl with Cmd) (注：macOS 用户可将 Ctrl 替换为 Cmd)
← 返回新闻列表 / Back to news list