Do you want to use your AMD GPU with ComfyUI to generate images and videos, but don’t know how to install it? You are in the right place! In this guide I will help you to Install ComfyUI with AMD HIP/ROCm support on Windows to accelerate your creativity.
Prerequisite: Installation of ROCm and PyTorch
Before installing ComfyUI you must install ROCm and PyTorch. I covered these topics on two articles:
Installation of ComfyUI enhanced by HIP/ROCm
The installation of ComfyUI for AMD HIP/ROCm is quite simple. Let’s start by opening a terminal, cloning the repository:
git clone https://github.com/comfyanonymous/ComfyUI.gitAnd enter the directory just created:
cd ComfyUIIf you followed my tutorials you will need to enter the python virtual environment where you had previously installed PyTorch:
conda activate py312After that you must install the requirements with the command:
pip install -r requirements.txtThe installation is finished. To run the program use this command:
python main.py --use-pytorch-cross-attentionTo update the program open a terminal in the directory that contain the program and run the following commands after entered the Conda environment:
Update the local repository:
git pullAnd update the requirements:
pip install -r requirements.txtFor more information about using ComfyUI visit their main site.
Improve performance on AMD GPU
To improve performance you can try to run the command with an additional flag:
TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 python main.py --use-pytorch-cross-attentionIt can generate errors so ,if needed, remove the additional flag.
- Install ComfyUI for AMD HIP/ROCm on Windows
Learn how to install ComfyUI for AMD HIP ROCm on Windows and generate images and videos. - Install PyTorch for AMD HIP ROCm on WindowsLearn how to install PyTorch for AMD HIP ROCm on Windows and accelerate AI programs.
- How to install ROCm python packages on WindowsLearn how to install AMD HIP/ROCm on Windows trough python packages
- Install axolotl for AMD HIP/ROCm on LinuxLearn how to install Llama-Factory on AMD GPUs using HIP/ROCm. Step-by-step guide for setting up LLM fine-tuning with AMD hardware and open-source tools.
- Install Llama-Factory for AMD HIP/ROCm on LinuxLearn how to install Llama-Factory on AMD GPUs using HIP/ROCm. Step-by-step guide for setting up LLM fine-tuning with AMD hardware and open-source tools.
