README.md 9.73 KB
Newer Older
comfyanonymous's avatar
comfyanonymous committed
1
2
ComfyUI
=======
comfyanonymous's avatar
comfyanonymous committed
3
A powerful and modular stable diffusion GUI and backend.
comfyanonymous's avatar
comfyanonymous committed
4
5
6
-----------
![ComfyUI Screenshot](comfyui_screenshot.png)

7
8
9
This ui will let you design and execute advanced stable diffusion pipelines using a graph/nodes/flowchart based interface. For some workflow examples and see what ComfyUI can do you can check out:
### [ComfyUI Examples](https://comfyanonymous.github.io/ComfyUI_examples/)

comfyanonymous's avatar
comfyanonymous committed
10
### [Installing ComfyUI](#installing)
11

12
13
14
15
## Features
- Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything.
- Fully supports SD1.x and SD2.x
- Asynchronous Queue system
comfyanonymous's avatar
Typo.  
comfyanonymous committed
16
- Many optimizations: Only re-executes the parts of the workflow that changes between executions.
17
18
- Command line option: ```--lowvram``` to make it work on GPUs with less than 3GB vram (enabled automatically on GPUs with low vram)
- Works even if you don't have a GPU with: ```--cpu``` (slow)
sALTaccount's avatar
sALTaccount committed
19
- Can load ckpt, safetensors and diffusers models/checkpoints. Standalone VAEs and CLIP models.
20
- Embeddings/Textual inversion
comfyanonymous's avatar
comfyanonymous committed
21
- [Loras (regular, locon and loha)](https://comfyanonymous.github.io/ComfyUI_examples/lora/)
22
- [Hypernetworks](https://comfyanonymous.github.io/ComfyUI_examples/hypernetworks/)
23
24
25
26
- Loading full workflows (with seeds) from generated PNG files.
- Saving/Loading workflows as Json files.
- Nodes interface can be used to create complex workflows like one for [Hires fix](https://comfyanonymous.github.io/ComfyUI_examples/2_pass_txt2img/) or much more advanced ones.
- [Area Composition](https://comfyanonymous.github.io/ComfyUI_examples/area_composition/)
comfyanonymous's avatar
comfyanonymous committed
27
- [Inpainting](https://comfyanonymous.github.io/ComfyUI_examples/inpaint/) with both regular and inpainting models.
comfyanonymous's avatar
comfyanonymous committed
28
- [ControlNet and T2I-Adapter](https://comfyanonymous.github.io/ComfyUI_examples/controlnet/)
29
- [Upscale Models (ESRGAN, ESRGAN variants, SwinIR, Swin2SR, etc...)](https://comfyanonymous.github.io/ComfyUI_examples/upscale_models/)
30
- [unCLIP Models](https://comfyanonymous.github.io/ComfyUI_examples/unclip/)
comfyanonymous's avatar
comfyanonymous committed
31
- [GLIGEN](https://comfyanonymous.github.io/ComfyUI_examples/gligen/)
space-nuko's avatar
space-nuko committed
32
- Latent previews with [TAESD](https://github.com/madebyollin/taesd)
33
34
- Starts up very fast.
- Works fully offline: will never download anything.
comfyanonymous's avatar
comfyanonymous committed
35
- [Config file](extra_model_paths.yaml.example) to set the search paths for models.
36
37

Workflow examples can be found on the [Examples page](https://comfyanonymous.github.io/ComfyUI_examples/)
comfyanonymous's avatar
comfyanonymous committed
38

39
## Shortcuts
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59

| Keybind | Explanation |
| - | - |
| Ctrl + Enter | Queue up current graph for generation |
| Ctrl + Shift + Enter | Queue up current graph as first for generation |
| Ctrl + S | Save workflow |
| Ctrl + O | Load workflow |
| Ctrl + A | Select all nodes |
| Ctrl + M | Mute/unmute selected nodes |
| Delete/Backspace | Delete selected nodes |
| Ctrl + Delete/Backspace | Delete the current graph |
| Space | Move the canvas around when held and moving the cursor |
| Ctrl/Shift + Click | Add clicked node to selection |
| Ctrl + C/Ctrl + V | Copy and paste selected nodes (without maintaining connections to outputs of unselected nodes) |
| Ctrl + C/Ctrl + Shift + V| Copy and paste selected nodes (maintaining connections from outputs of unselected nodes to inputs of pasted nodes) |
| Shift + Drag | Move multiple selected nodes at the same time |
| Ctrl + D | Load default graph |
| Q | Toggle visibility of the queue |
| H | Toggle visibility of history |
| R | Refresh graph |
WAS's avatar
WAS committed
60
| Double-Click LMB | Open node quick search palette |
61
62

Ctrl can also be replaced with Cmd instead for MacOS users
63

comfyanonymous's avatar
comfyanonymous committed
64
65
# Installing

comfyanonymous's avatar
comfyanonymous committed
66
## Windows
67

comfyanonymous's avatar
Typo.  
comfyanonymous committed
68
There is a portable standalone build for Windows that should work for running on Nvidia GPUs or for running on your CPU only on the [releases page](https://github.com/comfyanonymous/ComfyUI/releases).
69

70
### [Direct link to download](https://github.com/comfyanonymous/ComfyUI/releases/download/latest/ComfyUI_windows_portable_nvidia_cu118_or_cpu.7z)
71

comfyanonymous's avatar
comfyanonymous committed
72
Just download, extract and run. Make sure you put your Stable Diffusion checkpoints/models (the huge ckpt/safetensors files) in: ComfyUI\models\checkpoints
73

74
75
76
77
#### How do I share models between another UI and ComfyUI?

See the [Config file](extra_model_paths.yaml.example) to set the search paths for models. In the standalone windows build you can find this file in the ComfyUI directory. Rename this file to extra_model_paths.yaml and edit it with your favorite text editor.

78
79
80
81
## Colab Notebook

To run it on colab or paperspace you can use my [Colab Notebook](notebooks/comfyui_colab.ipynb) here: [Link to open with google colab](https://colab.research.google.com/github/comfyanonymous/ComfyUI/blob/master/notebooks/comfyui_colab.ipynb)

82
83
## Manual Install (Windows, Linux)

comfyanonymous's avatar
comfyanonymous committed
84
85
86
87
88
89
90
91
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.

92
### AMD GPUs (Linux only)
93
AMD users can install rocm and pytorch with pip if you don't have it already installed, this is the command to install the stable version:
comfyanonymous's avatar
comfyanonymous committed
94

95
```pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/rocm5.4.2```
96
97


comfyanonymous's avatar
comfyanonymous committed
98
99
### NVIDIA

100
Nvidia users should install torch and xformers using this command:
101

comfyanonymous's avatar
comfyanonymous committed
102
```pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu118 xformers```
103

104
105
106
107
108
109
110
#### 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.
comfyanonymous's avatar
comfyanonymous committed
111
112
113

### Dependencies

114
Install the dependencies by opening your terminal inside the ComfyUI folder and:
comfyanonymous's avatar
comfyanonymous committed
115
116
117

```pip install -r requirements.txt```

118
119
After this you should have everything installed and can proceed to running ComfyUI.

120
121
122
123
124
### Others:

[Intel Arc](https://github.com/comfyanonymous/ComfyUI/discussions/476)

Mac/MPS: There is basic support in the code but until someone makes some install instruction you are on your own.
125

comfyanonymous's avatar
comfyanonymous committed
126
### I already have another UI for Stable Diffusion installed do I really have to install all of these dependencies?
127
128
129
130
131
132
133
134
135
136
137
138

You don't. If you have another UI installed and working with it's own python venv you can use that venv to run ComfyUI. You can open up your favorite terminal and activate it:

```source path_to_other_sd_gui/venv/bin/activate```

or on Windows:

With Powershell: ```"path_to_other_sd_gui\venv\Scripts\Activate.ps1"```

With cmd.exe: ```"path_to_other_sd_gui\venv\Scripts\activate.bat"```

And then you can use that terminal to run Comfyui without installing any dependencies. Note that the venv folder might be called something else depending on the SD UI.
comfyanonymous's avatar
comfyanonymous committed
139
140
141
142
143

# Running

```python main.py```

144
145
146
147
148
### For AMD 6700, 6600 and maybe others

Try running it with this command if you have issues:

```HSA_OVERRIDE_GFX_VERSION=10.3.0 python main.py```
comfyanonymous's avatar
comfyanonymous committed
149
150
151
152
153
154
155
156
157
158
159

# 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 \\).

160
161
You can use {day|night}, for wildcard/dynamic prompts. With this syntax "{wild|card|test}" will be randomly replaced by either "wild", "card" or "test" by the frontend every time you queue the prompt. To use {} characters in your actual prompt escape them like: \\{ or \\}.

162
163
164
165
To use a textual inversion concepts/embeddings in a text prompt put them in the models/embeddings directory and use them in the CLIPTextEncode node like this (you can omit the .pt extension):

```embedding:embedding_filename.pt```

comfyanonymous's avatar
comfyanonymous committed
166
167
168
169
170
171
172
173
174
175
176
### 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.

comfyanonymous's avatar
comfyanonymous committed
177
178
## How to increase generation speed?

comfyanonymous's avatar
comfyanonymous committed
179
Make sure you use the regular loaders/Load Checkpoint node to load checkpoints. It will auto pick the right settings depending on your GPU.
comfyanonymous's avatar
comfyanonymous committed
180

comfyanonymous's avatar
comfyanonymous committed
181
You can set this command line setting to disable the upcasting to fp32 in some cross attention operations which will increase your speed. Note that this will very likely give you black images on SD2.x models. If you use xformers this option does not do anything.
comfyanonymous's avatar
comfyanonymous committed
182
183
184

```--dont-upcast-attention```

space-nuko's avatar
space-nuko committed
185
186
## How to show high-quality previews?

187
188
189
Use ```--preview-method auto``` to enable previews.

The default installation includes a fast latent preview method that's low-resolution. To enable higher-quality previews with [TAESD](https://github.com/madebyollin/taesd), download the [taesd_encoder.pth](https://github.com/madebyollin/taesd/raw/main/taesd_encoder.pth) and [taesd_decoder.pth](https://github.com/madebyollin/taesd/raw/main/taesd_decoder.pth) models and place them in the `models/vae_approx` folder. Once they're installed, restart ComfyUI to enable high-quality previews.
space-nuko's avatar
space-nuko committed
190

191
192
## Support and dev channel

193
[Matrix space: #comfyui_space:matrix.org](https://app.element.io/#/room/%23comfyui_space%3Amatrix.org) (it's like discord but open source).
comfyanonymous's avatar
comfyanonymous committed
194
195
196
197
198
199
200
201
202
203

# 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.