Model
Trends
.ai
Model
Trends
.ai
the best open source ai models

How to install ComfyUI

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.
Image generation
Windows
Mac
Linux
License: GPL-3.0
ComfyUI node guide and troubleshooting
Every popular node explained, with the errors it throws and how to fix them.

What is ComfyUI?

ComfyUI is a free, open source program for running AI image and video models on your own computer. Instead of one fixed form, it shows your generation as a graph of connected nodes: a model loader, a text encoder, a sampler, a decoder and so on. Each node does one job, and you wire them together into a workflow. That sounds technical, and it is, but it is also why ComfyUI is usually the first app to support a new model: the pieces can be rearranged for anything.
It is the right choice if you want the newest models (Flux, Flux 2, Wan, Hunyuan, Qwen Image, Chroma, LTX), want to run LoRAs, ControlNets, upscalers and video in one place, or want to share exact, reproducible workflows with others. The ComfyUI Desktop app makes the first install easy; the classic portable build gives full control. If you only want to type a prompt and get a picture, Fooocus or Invoke are gentler starts.
AD
No install required - run AI models on the cloud
BitVector Prism is the easiest way to start: pick a model, type a prompt and generate in a clean web app, with nothing to configure. BitVector is also available on Discord and on the web (SpyGlass).

What you need

Windows 10 or 11 with an NVIDIA graphics card (6 GB VRAM for SDXL, 12 GB or more for Flux and video; 24 GB is comfortable) is the best supported setup. AMD cards work on Linux with ROCm and on Windows through DirectML or ZLUDA, with more effort. Apple Silicon Macs (M1 and later) run ComfyUI natively through PyTorch MPS; 16 GB of unified memory is the practical minimum, 32 GB or more for Flux. You also need 20 to 100 GB of free disk space for model files, since one Flux checkpoint alone is about 12 to 24 GB.

How to get and install ComfyUI

  1. Open the official site (comfy.org) and download ComfyUI Desktop for Windows or Mac. It is a normal installer that sets up Python and everything else for you.
  2. Windows alternative: download the portable ZIP from the GitHub releases page, extract it to a short path such as C:\ComfyUI, and start run_nvidia_gpu.bat (or run_cpu.bat without a GPU).
  3. Linux, or manual install on any system: clone the GitHub repository, create a Python virtual environment, install PyTorch for your GPU (CUDA, ROCm or MPS) and then run pip install -r requirements.txt.
  4. Download at least one model file: for example an SDXL checkpoint, or Flux (the unet file plus the clip_l, t5xxl text encoders and the ae VAE). Civitai and Hugging Face are the usual sources.
  5. Put the files in the models folder: checkpoints go in models/checkpoints, Flux and video diffusion models in models/diffusion_models (or models/unet), text encoders in models/text_encoders (models/clip), VAEs in models/vae and LoRAs in models/loras.
  6. Start ComfyUI. The browser opens at http://127.0.0.1:8188 (the Desktop app has its own window). Install ComfyUI Manager from the menu if it is not already there; it finds missing custom nodes and models for you.
Download only from the official links on this page. Installers found elsewhere may be out of date or tampered with. ModelTrends.ai hosts no files.
AD
PirateDiffusion
No install required - run AI models on the cloud
PirateDiffusion is Telegram only and built for pros: thousands of models, LoRAs and workflows driven by chat commands, with unlimited generation on a fixed price plan.

How to use ComfyUI

  1. Load a template: the menu (Workflow > Browse Templates) has ready-made graphs for text to image with SD 1.5, SDXL, Flux and the video models. Pick one that matches a model you downloaded.
  2. In the Load Checkpoint (or Load Diffusion Model) node, choose your model from the list. If the list is empty, the file is in the wrong folder; press R to refresh after moving it.
  3. Type your prompt in the positive CLIP Text Encode node and anything you do not want in the negative one (Flux ignores negatives). Set the width and height in the Empty Latent Image node.
  4. In the KSampler node set the steps (20 to 30 for SDXL, 20 for Flux dev, 4 for Flux schnell and other distilled models), the CFG (5 to 7 for SDXL, 1 for Flux) and the sampler (euler or dpmpp_2m are safe choices).
  5. Press Run (or Ctrl+Enter). The image appears in the Save Image node and is also written to the output folder. Change the seed to get a different picture with the same prompt.
  6. To add a LoRA, add a Load LoRA node between the checkpoint and the text encoders, choose the file and keep the strength near 0.7 to 1.0. Every model page on ModelTrends.ai lists the trigger words to put in your prompt.

Tips and common problems

  • Out of memory? Start with --lowvram, pick an fp8 or GGUF version of the model, lower the resolution or close other GPU programs. Flux fp8 fits in 12 GB; GGUF Q4 versions fit in 8 GB.
  • Red nodes after loading a workflow mean a missing custom node. Open ComfyUI Manager, choose Install Missing Custom Nodes, then restart.
  • Drag any image generated by ComfyUI back onto the canvas to restore the exact workflow that made it, including prompt, seed and model.
  • Keep the models folder outside the ComfyUI folder and point to it with extra_model_paths.yaml, so you can update or reinstall ComfyUI without moving dozens of gigabytes.
  • On a Mac, the first generation after starting is slow while shaders compile; the second one is much faster. Keep the image size at or below 1024 on 16 GB machines.

Models you can run in ComfyUI

ComfyUI runs nearly every open source model in this catalog: Stable Diffusion 1.5 and SDXL checkpoints, Flux and Flux 2, Qwen Image, Chroma, Z-Image, the Hunyuan, Wan and LTX video models, and their LoRAs. Check a model page here for the base model and trigger words, then put the file in the matching folder.
AD
No install required - run AI models on the cloud
No GPU, no downloads, no Python. These services run the same open source models on their own servers, so you can start generating from a browser, Discord or Telegram in a minute.

Links

These links go to the makers' own sites. ModelTrends.ai is not affiliated with them and does not host any software.

Other local apps

How to install Stable Diffusion WebUI (AUTOMATIC1111)
The classic Stable Diffusion web interface: tabs, sliders and thousands of extensions. The app most tutorials were written for.
Windows
Mac
Linux
How to install Stable Diffusion WebUI Forge
The faster, lighter fork of the AUTOMATIC1111 interface with Flux support. Same tabs, much less VRAM.
Windows
Linux
How to install Fooocus
Type a prompt, get a great SDXL image. Fooocus hides the settings and does the prompt engineering for you.
Windows
Mac
Linux
How to install SD.Next
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
How to install Invoke (InvokeAI)
A polished creative studio with an infinite canvas, layers and inpainting, built for artists rather than engineers.
Windows
Mac
Linux
How to install SwarmUI
A friendly, modern interface on top of a ComfyUI engine: simple generate tab for everyone, full node graph when you want it.
Windows
Mac
Linux
How to install Draw Things
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
How to install DiffusionBee
The one-click Stable Diffusion app for Mac: download, open, type, done. A Windows version exists too.
Mac
Windows
How to install Stability Matrix
One launcher that installs and updates ComfyUI, Forge, A1111, Fooocus, SwarmUI and more, and shares your models between them.
Windows
Mac
Linux
How to install Pinokio
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
How to install Krita AI Diffusion
Generative AI inside the free Krita painting program: paint, mask and generate on layers with live preview.
Windows
Mac
Linux
How to install Amuse
A simple Windows app for AMD and other PCs that generates images with no Python and no command line.
Windows
How to install Easy Diffusion
A one-click installer and simple web interface for Stable Diffusion that just works on Windows, Mac and Linux.
Windows
Mac
Linux
How to install Wan2GP
Video generation for the GPU poor: Wan, Hunyuan, LTX and more on 6 to 12 GB cards with a simple web interface.
Windows
Linux
How to install FramePack
Generate long videos frame by frame on a 6 GB laptop GPU, with progressive preview as it renders.
Windows
Linux
How to install LM Studio
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
How to install Ollama
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