1
git clone https://github.com/ostris/ai-toolkit.git
2
cd ai-toolkit
3
python -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu130
4
python -m pip install -r requirements.txt
5
cd ui
6
npm run build_and_start

1
sudo apt install python3.12-venv
2
source .venv/bin/activate
3
python -m pip install huggingface_hub
4
export HF_ENDPOINT="https://hf-mirror.com"
5
hf auth login
6
hf download black-forest-labs/FLUX.1-dev  --repo-type model  --local-dir FLUX.1-dev   --exclude "flux1-dev.safetensors"

1
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/x86_64/cuda-keyring_1.1-1_all.deb
2
sudo dpkg -i cuda-keyring_1.1-1_all.deb
3
sudo apt-get update
4
sudo apt-get -y install cuda-toolkit-12-8
5

6
sudo apt-get install -y nvidia-open
7

8
sudo apt install python3.12-venv
9
python3 -m venv .venv
10
source .venv/bin/activate
11
pip install torch torchvision
12
pip install simpletuner[cuda]
13

14
sudo apt -y install libopenmpi-dev openmpi-bin libaio-dev