58 lines
2.9 KiB
Markdown
58 lines
2.9 KiB
Markdown
# ComfyUI Docker Setup
|
|
|
|
Hey there! This repository sets up ComfyUI, a powerful node-based interface for Stable Diffusion, using Docker. I've created separate configurations for AMD, Intel, and Nvidia GPUs to hopefully get everyone up and running smoothly.
|
|
|
|
## Summary
|
|
|
|
This `docker-compose.yml` file defines three ComfyUI services:
|
|
|
|
* **comfyui-amd:** Optimized for AMD GPUs.
|
|
* **comfyui-intel:** Optimized for Intel GPUs.
|
|
* **comfyui-nvidia:** Configured for Nvidia GPUs.
|
|
|
|
You'll be able to access ComfyUI through your browser at `http://localhost:8188` (assuming you're running this locally) or `http://<ip>:8188`.
|
|
|
|
## Dependencies
|
|
|
|
Before you start, make sure you have the following installed:
|
|
|
|
* **Docker:** You'll need Docker installed and running on your system. [https://docs.docker.com/get-docker/](https://docs.docker.com/get-docker/)
|
|
* **Docker Compose:** Docker Compose is used to define and run multi-container Docker applications. It's usually bundled with Docker Desktop, but if not, you can install it separately: [https://docs.docker.com/compose/install/](https://docs.docker.com/compose/install/)
|
|
* **GPU Drivers:** Make sure you have the latest drivers installed for your GPU (AMD, Intel, or Nvidia).
|
|
* **Models:** You'll need to download the Stable Diffusion models and place them in the `./models` directory. (This directory will be mounted into the container).
|
|
|
|
## Getting Started
|
|
|
|
Here's how to get everything up and running:
|
|
|
|
1. **Clone the repository:** Clone this repository to your local machine.
|
|
|
|
2. **Download Models:** Download your preferred Stable Diffusion models (e.g., checkpoints, VAEs, LoRAs) and place them in the `./models` directory.
|
|
|
|
3. **Choose your profile:** Pick the profile corresponding to your GPU: `comfyui-amd`, `comfyui-intel`, or `comfyui-nvidia`.
|
|
|
|
4. **Run Docker Compose:** Open your terminal, navigate to the directory where you cloned the repository, and run the following command, specifying the profile:
|
|
|
|
```bash
|
|
docker-compose --profile comfyui-amd up -d # For AMD
|
|
docker-compose --profile comfyui-intel up -d # For Intel
|
|
docker-compose --profile comfyui-nvidia up -d # For Nvidia
|
|
```
|
|
|
|
The `-d` flag runs the containers in detached mode (in the background).
|
|
|
|
5. **Access ComfyUI:** Once the containers are running, open your web browser and go to `http://localhost:8188`. You should see the ComfyUI interface.
|
|
|
|
**To stop the containers:**
|
|
|
|
```bash
|
|
docker-compose down
|
|
```
|
|
|
|
**Important Notes:**
|
|
|
|
* The `CLI_ARGS` environment variables in each service are specific optimizations for each GPU type. You can customize these if you want to experiment with different settings.
|
|
* The `./output` and `./user` directories are used for saving generated images and custom workflows, respectively.
|
|
* Set the right ownership/permissions for `./models`, `./output`, and `./user` (`chown 1001:1001 models`)
|
|
|
|
Let me know if you run into any issues or have suggestions for improvements! |