ComfyUI 是 一个基于节点流程的 Stable Diffusion 操作界面,可以通过流程,实现了更加精准的工作流定制和完善的可复现性。每一个模块都有特定的的功能,我们可以通过调整模块连接达到不同的出图效果。但节点式的工作流也提高了一部分使用门槛。同时,因为内部生成流程做了优化,生成图片时的速度相较于 webui 有明显提升,对显存要求也更低(4G 就能很好的运行)。
Go to file
comfyanonymous e6aa9f0c0a Modal now actually shows up on colab. 2023-01-27 22:51:08 -05:00
comfy Add ConditioningSetArea node. 2023-01-26 12:06:48 -05:00
input Add a LoadImage node to load images for img2img. 2023-01-22 15:07:18 -05:00
models Initial commit. 2023-01-16 22:37:14 -05:00
notebooks Small colab notebook fix. 2023-01-27 21:54:46 -05:00
output Initial commit. 2023-01-16 22:37:14 -05:00
webshit Modal now actually shows up on colab. 2023-01-27 22:51:08 -05:00
.gitignore Initial commit. 2023-01-16 22:37:14 -05:00
LICENSE Initial commit. 2023-01-16 22:37:14 -05:00
README.md Added better instructions for nvidia. 2023-01-27 17:23:47 -05:00
comfyui_screenshot.png Initial commit. 2023-01-16 22:37:14 -05:00
main.py Slightly better errors. 2023-01-26 23:30:29 -05:00
nodes.py Right category for latent upscale node. 2023-01-27 14:11:57 -05:00
requirements.txt Initial commit. 2023-01-16 22:37:14 -05:00

README.md

ComfyUI

A powerful and modular stable diffusion GUI.

ComfyUI Screenshot

This ui will let you design and execute advanced stable diffusion pipelines using a graph/nodes/flowchart based interface.

Installing

Git clone this repo.

Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints

Put your VAE in: models/vae

At the time of writing this pytorch has issues with python versions higher than 3.10 so make sure your python/pip versions are 3.10.

AMD

AMD users can install rocm and pytorch with pip if you don't have it already installed:

pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/rocm5.2

NVIDIA

Nvidia users should install torch using this command:

pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu117

Nvidia users should also install Xformers for a speed boost but can still run the software without it.

Troubleshooting

If you get the "Torch not compiled with CUDA enabled" error, uninstall torch with:

pip uninstall torch

And install it again with the command above.

Dependencies

Install the dependencies:

pip install -r requirements.txt

Running

python main.py

Notes

Only parts of the graph that have an output with all the correct inputs will be executed.

Only parts of the graph that change from each execution to the next will be executed, if you submit the same graph twice only the first will be executed. If you change the last part of the graph only the part you changed and the part that depends on it will be executed.

Dragging a generated png on the webpage or loading one will give you the full workflow including seeds that were used to create it.

You can use () to change emphasis of a word or phrase like: (good code:1.2) or (bad code:0.8). The default emphasis for () is 1.1. To use () characters in your actual prompt escape them like \( or \).

Colab Notebook

To run it on colab you can use my Colab Notebook here: Link to open with google colab

Fedora

To get python 3.10 on fedora: dnf install python3.10

Then you can:

python3.10 -m ensurepip

This will let you use: pip3.10 to install all the dependencies.

Support and dev channel

Matrix room: #comfyui:matrix.org (it's like discord but open source).

QA

Why did you make this?

I wanted to learn how Stable Diffusion worked in detail. I also wanted something clean and powerful that would let me experiment with SD without restrictions.

Who is this for?

This is for anyone that wants to make complex workflows with SD or that wants to learn more how SD works. The interface follows closely how SD works and the code should be much more simple to understand than other SD UIs.