Model
Trends
.ai
Model
Trends
.ai
최고의 오픈 소스 AI 모델

SwarmUI 설치 방법

A friendly, modern interface on top of a ComfyUI engine: simple generate tab for everyone, full node graph when you want it.
이미지 생성
Windows
Mac
Linux
라이선스: MIT

SwarmUI란?

SwarmUI (formerly StableSwarmUI) is a free, open source web interface that uses ComfyUI as its backend. You get a clean Generate tab with a prompt box, parameter sliders and a model browser with previews, while the Comfy Workflow tab lets you open the underlying graph for anything the simple tab cannot do. It supports images and video, multiple GPUs and even several machines at once, hence the name.
SwarmUI is ideal if you want ComfyUI's model support (Flux, Wan, Hunyuan, Qwen, Chroma and more) with a normal interface. It is also a good choice for people who switch between quick generation and detailed workflows. The installer takes care of ComfyUI for you.
AD
설치 불필요 – 클라우드에서 AI 모델 실행
BitVector Prism은 가장 쉽게 시작하는 방법입니다. 모델을 고르고 프롬프트를 입력하면 설정 없이 깔끔한 웹 앱에서 바로 생성됩니다. BitVector는 Discord와 웹(SpyGlass)에서도 사용할 수 있습니다.

필요한 것

Windows 10 or 11, Linux or macOS (Apple Silicon). NVIDIA GPU recommended (8 GB VRAM for SDXL, 12 GB or more for Flux and video); AMD on Linux with ROCm, or on Windows with some setup. .NET 8 runtime is installed by the installer. Disk space as for ComfyUI: tens of gigabytes for models.

SwarmUI 받기와 설치

  1. Download the Windows installer (install-windows.bat) from the GitHub README or the site, put it in the folder where you want SwarmUI, and run it. Linux and Mac have equivalent install scripts.
  2. The installer opens a browser page: choose Just Install Everything for a fresh ComfyUI backend, or point it at an existing ComfyUI if you have one.
  3. Pick a starter model to download during setup (SDXL, Flux or SD 1.5), or skip and add your own later.
  4. Put your own models in Models/Stable-Diffusion (checkpoints and Flux), Models/Lora, Models/VAE and Models/clip. SwarmUI can also read the folders of an existing ComfyUI install.
  5. Start SwarmUI with launch-windows.bat (or the Linux/Mac launch script). The interface runs at http://localhost:7801.
이 페이지의 공식 링크에서만 다운로드하세요. 다른 곳의 설치 파일은 오래되었거나 변조되었을 수 있습니다. ModelTrends.ai는 어떤 파일도 호스팅하지 않습니다.
AD
PirateDiffusion
설치 불필요 – 클라우드에서 AI 모델 실행
PirateDiffusion은 Telegram 전용이며 전문가를 위해 만들어졌습니다. 수천 개의 모델, LoRA, 워크플로를 채팅 명령으로 다루며 고정 요금제로 무제한 생성할 수 있습니다.

SwarmUI 사용법

  1. Click the Models tab at the bottom, pick a model (hover for its preview and description) and it becomes the active model.
  2. Write your prompt in the box, set Images, Steps, CFG Scale, Resolution and Seed in the left panel, and press Generate.
  3. Add a LoRA by selecting it in the LoRAs tab at the bottom, then set its weight in the prompt tag it creates. Remember the trigger words from the model page.
  4. Use the Init Image section for image to image, the Refiner section for a second pass, and ControlNet for guided generation; everything is a checkbox in the left panel.
  5. Open the Comfy Workflow tab to see and edit the node graph behind your current settings, or to load any ComfyUI workflow.

팁과 흔한 문제

  • Edit a model's metadata (right click in the Models tab) to save its trigger words and default settings; they are applied automatically.
  • Use the Grid Generator tool to compare several models, LoRAs or settings in one run.
  • If the backend fails to start, open the Server > Backends tab: it shows the ComfyUI log and lets you restart it.
  • Video models (Wan, Hunyuan, LTX) appear in the Models tab like any other model; set the frame count in the Video section.

SwarmUI에서 실행할 수 있는 모델

Through its ComfyUI backend, SwarmUI runs almost everything in this catalog: Stable Diffusion 1.5, SDXL, Flux, Flux 2, Qwen Image, Chroma, Hunyuan, Wan and their LoRAs.
AD
설치 불필요 – 클라우드에서 AI 모델 실행
GPU도, 다운로드도, Python도 필요 없습니다. 이 서비스들은 같은 오픈소스 모델을 자체 서버에서 실행하므로 브라우저, Discord, Telegram에서 1분 만에 생성을 시작할 수 있습니다.

링크

이 링크들은 제작사의 사이트로 이동합니다. ModelTrends.ai는 이들과 제휴 관계가 없으며 소프트웨어를 호스팅하지 않습니다.

다른 로컬 앱

ComfyUI 설치 방법
The node-based powerhouse for Stable Diffusion, Flux, Wan video and almost every new open source model. Free, open source, for Windows, Mac and Linux.
Windows
Mac
Linux
Stable Diffusion WebUI (AUTOMATIC1111) 설치 방법
The classic Stable Diffusion web interface: tabs, sliders and thousands of extensions. The app most tutorials were written for.
Windows
Mac
Linux
Stable Diffusion WebUI Forge 설치 방법
The faster, lighter fork of the AUTOMATIC1111 interface with Flux support. Same tabs, much less VRAM.
Windows
Linux
Fooocus 설치 방법
Type a prompt, get a great SDXL image. Fooocus hides the settings and does the prompt engineering for you.
Windows
Mac
Linux
SD.Next 설치 방법
A heavily modernized fork of the original WebUI that runs Stable Diffusion, SDXL, Flux, Qwen, Chroma and dozens of other model families on NVIDIA, AMD, Intel and Apple hardware.
Windows
Mac
Linux
Invoke (InvokeAI) 설치 방법
A polished creative studio with an infinite canvas, layers and inpainting, built for artists rather than engineers.
Windows
Mac
Linux
Draw Things 설치 방법
The best native app for Mac, iPhone and iPad: Stable Diffusion, Flux, Wan video and more with no setup and no terminal.
Mac
iPhone
iPad
DiffusionBee 설치 방법
The one-click Stable Diffusion app for Mac: download, open, type, done. A Windows version exists too.
Mac
Windows
Stability Matrix 설치 방법
One launcher that installs and updates ComfyUI, Forge, A1111, Fooocus, SwarmUI and more, and shares your models between them.
Windows
Mac
Linux
Pinokio 설치 방법
A browser for AI apps: one-click installs for ComfyUI, Forge, Wan2GP, FramePack, voice and music tools, each in its own isolated environment.
Windows
Mac
Linux
Krita AI Diffusion 설치 방법
Generative AI inside the free Krita painting program: paint, mask and generate on layers with live preview.
Windows
Mac
Linux
Amuse 설치 방법
A simple Windows app for AMD and other PCs that generates images with no Python and no command line.
Windows
Easy Diffusion 설치 방법
A one-click installer and simple web interface for Stable Diffusion that just works on Windows, Mac and Linux.
Windows
Mac
Linux
Wan2GP 설치 방법
Video generation for the GPU poor: Wan, Hunyuan, LTX and more on 6 to 12 GB cards with a simple web interface.
Windows
Linux
FramePack 설치 방법
Generate long videos frame by frame on a 6 GB laptop GPU, with progressive preview as it renders.
Windows
Linux
LM Studio 설치 방법
Run open text models like Llama, Qwen, Gemma and Mistral on your Mac or PC with a chat window and a local API.
Windows
Mac
Linux
Ollama 설치 방법
The developer favourite for local LLMs: one command downloads and runs Llama, Qwen, Gemma, DeepSeek and more, with a built-in API.
Windows
Mac
Linux