Skip to content

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: MiniMax H3

Pick another model

2. Main model

3. LoRAs

Tick the ones you want, up to 12.

4. GPU and precision

H3 mode

FL2VA works from the first and last frame, Ref2VA from character references.

Precision

The chosen model's file is 4.5 GB and already compressed: the file sets the precision.

8-bit: weights compressed to 8 bits, half the memory, looks the same as the original. Recommended.

Your command

Needs ≈ 29 GB of GPU memory, you have 24 GB. It does not fit: pick a lower precision or rent a bigger GPU.

RTX A6000 on Massed Compute fits: $0.43 an hour with the coupon.Open Massed Compute
#!/usr/bin/env bash
# Pika H3 Flex PTD
set -e
# NVIDIA driver: CUDA 13 needs 580+. If older or missing, the current nvidia-open is installed (keep yours: KEEP_DRIVER=1)
DRV=$(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 "$HOME/.local/bin/env"
# CUDA 13+ → int8_convrot (Comfy-Org's advice), else fp8_scaled
CU=$(nvidia-smi | grep -oP 'CUDA Version: \K[0-9]+' || echo 12)
[ "$CU" -ge 13 ] && TORCH=cu130 || TORCH=cu128
[ -d ~/ComfyUI ] || git clone https://github.com/comfyanonymous/ComfyUI ~/ComfyUI
cd ~/ComfyUI
uv venv --python 3.12 --allow-existing && source .venv/bin/activate
uv pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$TORCH
uv pip install -r requirements.txt "huggingface_hub[cli]"
# Base files: MiniMax H3, 8-bit
if [ "$CU" -ge 13 ]; then
  hf download Comfy-Org/MiniMax-H3 text_encoders/qwen3vl_32b_minimax_h3_int8_convrot.safetensors vae/minimax_h3_video_vae_fp16.safetensors vae/minimax_h3_audio_vae_fp32.safetensors --local-dir models
else
  hf download Comfy-Org/MiniMax-H3 text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors vae/minimax_h3_video_vae_fp16.safetensors vae/minimax_h3_audio_vae_fp32.safetensors --local-dir models
fi
# Main model: Pika H3 Flex PTD
hf download WAS/Pika-H3-Flex-PTD pika_h3_flex_td_ref2va_4step_s050.safetensors --local-dir models/diffusion_models
# Start ComfyUI. From your computer: ssh -L 8188:localhost:8188 user@IP, then http://localhost:8188
python main.py --listen 127.0.0.1 --port 8188

Once it runs: from your computer ssh -L 8188:localhost:8188 user@machine-IP and open http://localhost:8188.