Optimized Docker image for cloud and local use, with external model cache

.dockerignore

@@ -1,3 +1,27 @@
 *
-!environment*.yml
+
+!backend
+!frontend
+!scripts
+!server
+!static
+!LICENSE*
+!main.py
+!setup.py
 !docker-build
+docker-build/Dockerfile
+!ldm
+!installer
+
+# Guard against pulling in any models that might exist in the directory tree
+**/*.pt*
+
+# unignore configs, but only ignore the custom models.yaml, in case it exists
+!configs
+configs/models.yaml
+
+# unignore environment dirs/files, but ignore the environment.yml file or symlink in case it exists
+!environment*
+environment.yml
+
+**/__pycache__

.github/workflows/build-cloud-img.yml

@@ -0,0 +1,65 @@
+name: Build and push cloud image
+on:
+  workflow_dispatch:
+  push:
+    branches:
+    - main
+    - development
+    ## temp
+    - docker-min
+    tags:
+      - v*
+
+permissions:
+  contents: read
+  packages: write
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  docker:
+    strategy:
+      fail-fast: false
+      matrix:
+        # only x86_64 for now. aarch64+cuda isn't really a thing yet
+        arch:
+        - x86_64
+    runs-on: ubuntu-latest
+    name: ${{ matrix.arch }}
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v3
+
+    - name: Docker meta
+      id: meta
+      uses: docker/metadata-action@v4
+      with:
+        images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+        tags: |
+          type=ref,event=branch
+          type=ref,event=tag
+          type=ref,event=pr
+          type=sha
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v2
+
+    - if: github.event_name != 'pull_request'
+      name: Docker login
+      uses: docker/login-action@v2
+      with:
+        registry: ghcr.io
+        username: ${{ github.actor }}
+        password: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Build and push cloud image
+      uses: docker/build-push-action@v3
+      with:
+        context: .
+        file: docker-build/Dockerfile.cloud
+        platforms: Linux/${{ matrix.arch }}
+        push: ${{ github.event_name != 'pull_request' }}
+        tags: ${{ steps.meta.outputs.tags }}
+        labels: ${{ steps.meta.outputs.labels }}

docker-build/Dockerfile.cloud

@@ -0,0 +1,62 @@
+# Copyright (c) 2022 Eugene Brodsky (https://github.com/ebr)
+
+#### Builder stage ####
+
+FROM library/ubuntu:22.04 AS builder
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV PYTHONDONTWRITEBYTECODE=1
+# unbuffered output, ensures stdout and stderr are printed in the correct order
+ENV PYTHONUNBUFFERED=1
+
+RUN --mount=type=cache,target=/var/cache/apt \
+    apt update && apt install -y \
+    libglib2.0-0 \
+    libgl1-mesa-glx \
+    python3-venv \
+    python3-pip
+
+
+ARG APP_ROOT=/invokeai
+WORKDIR ${APP_ROOT}
+
+ENV VIRTUAL_ENV=${APP_ROOT}/.venv
+ENV PATH="$VIRTUAL_ENV/bin:$PATH"
+
+COPY . .
+RUN --mount=type=cache,target=/root/.cache/pip \
+    cp installer/py3.10-linux-x86_64-cuda-reqs.txt requirements.txt && \
+    python3 -m venv ${VIRTUAL_ENV} &&\
+    pip install --extra-index-url https://download.pytorch.org/whl/cu116 \
+        torch==1.12.0+cu116 \
+        torchvision==0.13.0+cu116 &&\
+    pip install -r requirements.txt &&\
+    pip install -e .
+
+
+#### Runtime stage ####
+
+FROM ubuntu:22.04 as runtime
+RUN apt update && apt install -y \
+    git \
+    curl \
+    ncdu \
+    iotop \
+    bzip2 \
+    libglib2.0-0 \
+    libgl1-mesa-glx \
+    python3-venv \
+    python3-pip \
+    && apt-get clean
+
+ARG APP_ROOT=/invokeai
+WORKDIR ${APP_ROOT}
+
+ENV VIRTUAL_ENV=${APP_ROOT}/.venv
+ENV PATH="$VIRTUAL_ENV/bin:$PATH"
+
+COPY --from=builder ${APP_ROOT} ${APP_ROOT}
+
+ENTRYPOINT ["bash", "-c", "python3 scripts/invoke.py" ]
+
+CMD ["--web", "--host 0.0.0.0"]

docker-build/Makefile

@@ -0,0 +1,58 @@
+# Copyright (c) 2022 Eugene Brodsky (https://github.com/ebr)
+
+# Directory in the container where the INVOKEAI_ROOT will be mounted
+INVOKEAI_ROOT=/mnt/invokeai
+# Host directory to contain the model cache. Will be mounted at INVOKEAI_ROOT path in the container
+INVOKEAI_CACHEDIR=${HOME}/invokeai
+
+DOCKER_BUILDKIT=1
+IMAGE=local/invokeai:latest
+
+USER=$(shell id -u)
+GROUP=$(shell id -g)
+
+# All downloaded models and config will end up in ${INVOKEAI_CACHEDIR}.
+# Contents can be moved to a persistent storage and used to rehydrate the cache on another host
+
+build:
+	docker build -t local/invokeai:latest -f Dockerfile.cloud ..
+
+# Copy only the content of config dir first, such that the configuration
+# script can run with the expected config dir already populated.
+# Then, run the configuration script.
+configure:
+	docker run --rm -it \
+		-v ${INVOKEAI_CACHEDIR}/configs:/mnt/configs \
+		--entrypoint bash ${IMAGE} \
+		-c "cp -r ./configs/* /mnt/configs/"
+	docker run --rm -it --runtime=nvidia --gpus=all \
+		-v ${INVOKEAI_CACHEDIR}:${INVOKEAI_ROOT} \
+		-v ${INVOKEAI_CACHEDIR}/.cache:/root/.cache \
+		${IMAGE} \
+		-c "scripts/configure_invokeai.py --root ${INVOKEAI_ROOT}"
+	sudo chown -R ${USER}:${GROUP} ${INVOKEAI_CACHEDIR}
+
+# Run the container with the cache mounted and the web server exposed on port 9090
+web:
+	docker run --rm -it --runtime=nvidia --gpus=all \
+		-v ${INVOKEAI_CACHEDIR}:${INVOKEAI_ROOT} \
+		-v ${INVOKEAI_CACHEDIR}/.cache:/root/.cache \
+		--entrypoint bash -p9090:9090 ${IMAGE} \
+		-c "scripts/invoke.py --web --host 0.0.0.0 --root ${INVOKEAI_ROOT}"
+
+cli:
+	docker run --rm -it --runtime=nvidia --gpus=all \
+		-v ${INVOKEAI_CACHEDIR}:${INVOKEAI_ROOT} \
+		-v ${INVOKEAI_CACHEDIR}/.cache:/root/.cache \
+		--entrypoint bash ${IMAGE} \
+		-c "scripts/invoke.py --root ${INVOKEAI_ROOT}"
+
+# Run the container with the cache mounted and open a bash shell instead of the Invoke CLI or webserver
+shell:
+	docker run --rm -it --runtime=nvidia --gpus=all \
+		-v ${INVOKEAI_CACHEDIR}:${INVOKEAI_ROOT} \
+		-v ${INVOKEAI_CACHEDIR}/.cache:/root/.cache \
+		-e INVOKEAI_ROOT=${INVOKEAI_ROOT} \
+		--entrypoint bash ${IMAGE} --
+
+.PHONY: build configure web cli shell