Install a model with LoRAs in one command
Find a model (language, image and video, robotics or anything else), add the LoRAs made for it and pick a GPU. One command below installs it all.
1. Model
Ready ComfyUI builds
For these families: Comfy-Org's official files at the right precision.
Chosen model: LiliPixel-V1
Pick another model3. LoRAs
No LoRAs for this model on the site yet.
4. GPU and precision
Your command
Diffusers model: the script sets up the environment and writes run.py, which loads the model with every LoRA and generates.
Needs ≈ 1.7 GB of GPU memory, you have 24 GB. It fits.
A30 on Massed Compute fits: $0.26 an hour with the coupon.Open Massed Compute
#!/usr/bin/env bash
# LiliPixel-V1
# NVIDIA driver: CUDA 13 needs 580+. If older or missing, the current nvidia-open is installed (keep yours: KEEP_DRIVER=1)
DRV=$(nvidia-smi --query-gpu=driver_version --format=csv,noheader 2>/dev/null | head -1 | cut -d. -f1)
case "$DRV" in ""|*[!0-9]*) DRV=0 ;; esac
if [ "$DRV" -lt 580 ] && [ -z "${KEEP_DRIVER:-}" ]; then
. /etc/os-release && \
curl -fsSLO "https://developer.download.nvidia.com/compute/cuda/repos/ubuntu${VERSION_ID//./}/x86_64/cuda-keyring_1.1-1_all.deb" && \
sudo dpkg -i cuda-keyring_1.1-1_all.deb && rm -f cuda-keyring_1.1-1_all.deb && \
sudo apt-get update && \
sudo DEBIAN_FRONTEND=noninteractive apt-get install -y nvidia-open || \
{ echo "Could not install the NVIDIA driver: see the error above. To keep the current one, run with KEEP_DRIVER=1."; exit 1; }
echo "NVIDIA driver updated. Reboot the machine (sudo reboot) and run this same script again."
exit 0
fi
curl -LsSf https://astral.sh/uv/install.sh | sh
source "$HOME/.local/bin/env"
mkdir -p ~/gen && cd ~/gen
uv venv --python 3.12 --allow-existing && source .venv/bin/activate
CU=$(nvidia-smi | grep -oP 'CUDA Version: \K[0-9]+' || echo 12)
[ "$CU" -ge 13 ] && TORCH=cu130 || TORCH=cu128
uv pip install torch torchvision --index-url https://download.pytorch.org/whl/$TORCH
# Libraries
uv pip install diffusers transformers accelerate peft sentencepiece "huggingface_hub[cli]"
cat > run.py <<'PY'
import glob, os, sys, torch
from diffusers import DiffusionPipeline
pipe = DiffusionPipeline.from_pretrained("Pinkstack/LiliPixel-V1-190M", torch_dtype=torch.bfloat16)
DIRS = []
names = []
files = [f for d in DIRS for f in sorted(glob.glob(f"{d}/**/*.safetensors", recursive=True))]
for i, f in enumerate(files):
pipe.load_lora_weights(os.path.dirname(f), weight_name=os.path.basename(f), adapter_name=f"l{i}")
names.append(f"l{i}")
if names:
pipe.set_adapters(names, adapter_weights=[1.0] * len(names))
pipe.to("cuda")
out = pipe(prompt=" ".join(sys.argv[1:]) or "a photo of a cat")
out.images[0].save("out.png")
PY
# Generate: python run.py "your prompt"
python run.py "your prompt"