diff --git a/README.md b/README.md
index df0e0f17d8e31911d333b3bbbc61627304b51c7e..23ac8647d4435f915f094ff52c928f2d0368e302 100644
--- a/README.md
+++ b/README.md
@@ -394,6 +394,8 @@ to any service that supports Docker images.
 
 You can try the Docker image locally by running: `docker-compose up --build`
 
+There are also [several prebuilt Docker images.](docker/README.md)
+
 Linux users with a GPU (drivers >= 384.81) and [Nvidia-Docker](https://github.com/NVIDIA/nvidia-docker) installed can run the example on the GPU: Open the [docker-compose.yml](docker-compose.yml) file and uncomment the `dockerfile: Dockerfile.gpu` and `runtime: nvidia` lines.
 
 ## Having problems?
diff --git a/docker/Dockerfile-python-example b/docker/Dockerfile-python-example
new file mode 100644
index 0000000000000000000000000000000000000000..159fab37f1526f89dd116e9f6b85b62a6c6a5cc0
--- /dev/null
+++ b/docker/Dockerfile-python-example
@@ -0,0 +1,17 @@
+FROM animcogn/face_recognition:cpu
+
+# The rest of this file just runs an example script.
+
+# If you wanted to use this Dockerfile to run your own app instead, maybe you would do this:
+# COPY . /root/your_app_or_whatever
+# RUN cd /root/your_app_or_whatever && \
+#     pip3 install -r requirements.txt
+# RUN whatever_command_you_run_to_start_your_app
+
+COPY . /root/face_recognition
+RUN cd /root/face_recognition && \
+    pip3 install -r requirements.txt && \
+    python3 setup.py install
+
+CMD cd /root/face_recognition/examples && \
+    python3 recognize_faces_in_pictures.py
diff --git a/docker/README.md b/docker/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..6feffe1e462604d951a3f7804b0b71e20b461895
--- /dev/null
+++ b/docker/README.md
@@ -0,0 +1,56 @@
+# Docker Builds
+
+If you've never used Docker before, check out the [getting started guide.](https://docs.docker.com/get-started/)
+
+Up-to-date prebuilt images can be found [on Docker hub.](https://hub.docker.com/repository/docker/animcogn/face_recognition)
+
+## CPU Images
+
+-	[`cpu-latest`, `cpu`, `cpu-0.1`, `latest`](cpu/Dockerfile)
+-	[`cpu-jupyter-kubeflow-latest`, `cpu-jupyter-kubeflow`, `cpu-jupyter-kubeflow-0.1`](cpu-jupyter-kubeflow/Dockerfile)
+
+### GPU Images
+-	[`gpu-latest`, `gpu`, `gpu-0.1`](gpu/Dockerfile)
+-	[`gpu-jupyter-kubeflow-latest`, `gpu-jupyter-kubeflow`, `gpu-jupyter-kubeflow-0.1`](gpu-jupyter-kubeflow/Dockerfile)
+
+The CPU images should run out of the box without any driver prerequisites.
+
+## GPU Images
+
+### Prerequisites
+
+To use the GPU images, you need to have:
+- [The Nvidia drivers](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#nvidia-drivers)
+- [The Nvidia-docker container runtime](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#setting-up-nvidia-container-toolkit)
+- [Docker configured to use the Nvidia container runtime](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/user-guide.html#daemon-configuration-file)
+
+Once you have those installed, you should be ready to start running the GPU instances.
+
+### Testing GPUs
+
+To make sure your GPU instance is setup correctly, run the following in a container:
+
+```python3
+import dlib
+print(dlib.cuda.get_num_devices())
+```
+
+## Jupyter Images
+
+The Jupyter images are built to be deployed on [Kubeflow](https://www.kubeflow.org/). However, if you just want to run a normal Jupyter instance, they're a great template to build your own.
+
+## Example Dockerfile
+
+Here's an example Dockerfile using the prebuilt images:
+
+```Dockerfile
+FROM animcogn/face_recognition:gpu
+
+COPY requirements.txt requirements.txt
+
+RUN pip3 install -r ./requirements.txt
+
+COPY my_app /my_app
+
+CMD [ "python3", "/my_app/my_app.py" ]
+```
diff --git a/docker/cpu-jupyter-kubeflow/Dockerfile b/docker/cpu-jupyter-kubeflow/Dockerfile
new file mode 100644
index 0000000000000000000000000000000000000000..9979c548a1411f3f90b9652b79db0d0ddda628f1
--- /dev/null
+++ b/docker/cpu-jupyter-kubeflow/Dockerfile
@@ -0,0 +1,15 @@
+FROM animcogn/face_recognition:cpu
+
+RUN useradd -ms /bin/bash jovyan && \
+    chown -R jovyan:jovyan /opt/venv && \
+    echo 'PATH="/opt/venv/bin:$PATH"' >> /home/jovyan/.bashrc
+
+USER jovyan
+
+ENV PATH="/opt/venv/bin:$PATH"
+
+RUN pip3 install jupyterlab
+
+ENV NB_PREFIX /
+
+CMD ["sh", "-c", "jupyter lab --notebook-dir=/home/jovyan --ip=0.0.0.0 --no-browser --allow-root --port=8888 --NotebookApp.token='' --NotebookApp.password='' --NotebookApp.allow_origin='*' --NotebookApp.base_url=${NB_PREFIX}"]
diff --git a/docker/cpu/Dockerfile b/docker/cpu/Dockerfile
new file mode 100644
index 0000000000000000000000000000000000000000..08a40e25c3c9bb72698899f7bf0a1978e4c309b6
--- /dev/null
+++ b/docker/cpu/Dockerfile
@@ -0,0 +1,74 @@
+# Builder Image
+FROM python:3.8-slim-buster AS compile
+
+# Install Dependencies
+RUN apt-get -y update && apt-get install -y --fix-missing \
+    build-essential \
+    cmake \
+    gfortran \
+    git \
+    wget \
+    curl \
+    graphicsmagick \
+    libgraphicsmagick1-dev \
+    libatlas-base-dev \
+    libavcodec-dev \
+    libavformat-dev \
+    libgtk2.0-dev \
+    libjpeg-dev \
+    liblapack-dev \
+    libswscale-dev \
+    pkg-config \
+    python3-dev \
+    python3-numpy \
+    software-properties-common \
+    zip \
+    && apt-get clean && rm -rf /tmp/* /var/tmp/*
+
+# Virtual Environment
+ENV VIRTUAL_ENV=/opt/venv
+RUN python3 -m venv $VIRTUAL_ENV
+ENV PATH="$VIRTUAL_ENV/bin:$PATH"
+
+# Install Dlib
+ENV CFLAGS=-static
+RUN pip3 install --upgrade pip && \
+    git clone -b 'v19.21' --single-branch https://github.com/davisking/dlib.git && \
+    cd dlib/ && \
+    python3 setup.py install --set BUILD_SHARED_LIBS=OFF
+
+RUN pip3 install face_recognition
+
+
+# Runtime Image
+FROM python:3.8-slim-buster
+
+COPY --from=compile /opt/venv /opt/venv
+COPY --from=compile \
+    # Sources
+    /lib/x86_64-linux-gnu/libpthread.so.0 \
+    /lib/x86_64-linux-gnu/libz.so.1 \
+    /lib/x86_64-linux-gnu/libm.so.6 \
+    /lib/x86_64-linux-gnu/libgcc_s.so.1 \
+    /lib/x86_64-linux-gnu/libc.so.6 \
+    /lib/x86_64-linux-gnu/libdl.so.2 \
+    /lib/x86_64-linux-gnu/librt.so.1 \
+    # Destination
+    /lib/x86_64-linux-gnu/
+
+COPY --from=compile \
+    # Sources
+    /usr/lib/x86_64-linux-gnu/libX11.so.6 \
+    /usr/lib/x86_64-linux-gnu/libXext.so.6 \
+    /usr/lib/x86_64-linux-gnu/libpng16.so.16 \
+    /usr/lib/x86_64-linux-gnu/libjpeg.so.62 \
+    /usr/lib/x86_64-linux-gnu/libstdc++.so.6 \
+    /usr/lib/x86_64-linux-gnu/libxcb.so.1 \
+    /usr/lib/x86_64-linux-gnu/libXau.so.6 \
+    /usr/lib/x86_64-linux-gnu/libXdmcp.so.6 \
+    /usr/lib/x86_64-linux-gnu/libbsd.so.0 \
+    # Destination
+    /usr/lib/x86_64-linux-gnu/
+
+# Add our packages
+ENV PATH="/opt/venv/bin:$PATH"
diff --git a/docker/gpu-jupyter-kubeflow/Dockerfile b/docker/gpu-jupyter-kubeflow/Dockerfile
new file mode 100644
index 0000000000000000000000000000000000000000..df0aa8ac88f95aacdd8c6c54ac99867f027a23d3
--- /dev/null
+++ b/docker/gpu-jupyter-kubeflow/Dockerfile
@@ -0,0 +1,15 @@
+FROM animcogn/face_recognition:gpu
+
+RUN useradd -ms /bin/bash jovyan && \
+    chown -R jovyan:jovyan /opt/venv && \
+    echo 'PATH="/opt/venv/bin:$PATH"' >> /home/jovyan/.bashrc
+
+USER jovyan
+
+ENV PATH="/opt/venv/bin:$PATH"
+
+RUN pip3 install jupyterlab
+
+ENV NB_PREFIX /
+
+CMD ["sh", "-c", "jupyter lab --notebook-dir=/home/jovyan --ip=0.0.0.0 --no-browser --allow-root --port=8888 --NotebookApp.token='' --NotebookApp.password='' --NotebookApp.allow_origin='*' --NotebookApp.base_url=${NB_PREFIX}"]
diff --git a/docker/gpu/Dockerfile b/docker/gpu/Dockerfile
new file mode 100644
index 0000000000000000000000000000000000000000..8ece32dec82126c0c6590991d4da75658ae26f9b
--- /dev/null
+++ b/docker/gpu/Dockerfile
@@ -0,0 +1,97 @@
+FROM nvidia/cuda:11.2.0-cudnn8-devel AS compile
+
+# Install dependencies
+ENV DEBIAN_FRONTEND=noninteractive
+RUN apt-get update -y && apt-get install -y \
+    git \
+    cmake \
+    libsm6 \
+    libxext6 \
+    libxrender-dev \
+    python3 \
+    python3-pip \
+    python3-venv \
+    python3-dev \
+    python3-numpy \
+    gcc \
+    build-essential \
+    gfortran \
+    wget \
+    curl \
+    graphicsmagick \
+    libgraphicsmagick1-dev \
+    libatlas-base-dev \
+    libavcodec-dev \
+    libavformat-dev \
+    libgtk2.0-dev \
+    libjpeg-dev \
+    liblapack-dev \
+    libswscale-dev \
+    pkg-config \
+    software-properties-common \
+    zip \
+    && apt-get clean && rm -rf /tmp/* /var/tmp/*
+
+
+# Virtual Environment
+ENV VIRTUAL_ENV=/opt/venv
+RUN python3 -m venv $VIRTUAL_ENV
+ENV PATH="$VIRTUAL_ENV/bin:$PATH"
+
+# Scikit learn
+RUN pip3 install --upgrade pip && \
+    pip3 install scikit-build
+
+# Install dlib
+ENV CFLAGS=-static
+RUN git clone -b 'v19.21' --single-branch https://github.com/davisking/dlib.git dlib/ && \
+    mkdir -p /dlib/build && \
+    cmake -H/dlib -B/dlib/build -DDLIB_USE_CUDA=1 -DUSE_AVX_INSTRUCTIONS=1 && \
+    cmake --build /dlib/build && \
+    cd /dlib && \
+    python3 /dlib/setup.py install --set BUILD_SHARED_LIBS=OFF
+
+# Install face recognition
+RUN pip3 install face_recognition
+
+# Runtime Image
+FROM nvidia/cuda:11.2.0-cudnn8-runtime
+
+# Install requirements
+RUN apt-get update && apt-get install -y \
+    python3 \
+    python3-distutils
+
+# Copy in libs
+COPY --from=compile /opt/venv /opt/venv
+COPY --from=compile \
+    # Sources
+    /lib/x86_64-linux-gnu/libpthread.so.0 \
+    /lib/x86_64-linux-gnu/libdl.so.2 \
+    /lib/x86_64-linux-gnu/librt.so.1 \
+    /lib/x86_64-linux-gnu/libX11.so.6 \
+    /lib/x86_64-linux-gnu/libpng16.so.16 \
+    /lib/x86_64-linux-gnu/libjpeg.so.8 \
+    /lib/x86_64-linux-gnu/libcudnn.so.8 \
+    /lib/x86_64-linux-gnu/libstdc++.so.6 \
+    /lib/x86_64-linux-gnu/libm.so.6 \
+    /lib/x86_64-linux-gnu/libgcc_s.so.1 \
+    /lib/x86_64-linux-gnu/libc.so.6 \
+    /lib/x86_64-linux-gnu/libxcb.so.1 \
+    /lib/x86_64-linux-gnu/libz.so.1 \
+    /lib/x86_64-linux-gnu/libXau.so.6 \
+    /lib/x86_64-linux-gnu/libXdmcp.so.6 \
+    /lib/x86_64-linux-gnu/libbsd.so.0 \
+    # Destination
+    /lib/x86_64-linux-gnu/
+COPY --from=compile \
+    # Sources
+    /usr/local/cuda/lib64/libcublas.so.11 \
+    /usr/local/cuda/lib64/libcurand.so.10 \
+    /usr/local/cuda/lib64/libcusolver.so.11 \
+    /usr/local/cuda/lib64/libcublasLt.so.11 \
+    # Destination
+    /usr/local/cuda/lib64/
+
+# Add our packages
+ENV PATH="/opt/venv/bin:$PATH"