chore: add sd Dockerfile

leejet · leejet · commit 721cb324af3d · 2023-08-22T22:14:20.000+08:00
diff --git a/.dockerignore b/.dockerignore
@@ -0,0 +1,6 @@
+build*/
+test/
+
+.cache/
+*.swp
+models/
diff --git a/Dockerfile b/Dockerfile
@@ -0,0 +1,17 @@
+ARG UBUNTU_VERSION=22.04
+
+FROM ubuntu:$UBUNTU_VERSION as build
+
+RUN apt-get update && apt-get install -y build-essential git cmake
+
+WORKDIR /sd.cpp
+
+COPY . .
+
+RUN mkdir build && cd build && cmake .. && cmake --build . --config Release
+
+FROM ubuntu:$UBUNTU_VERSION as runtime
+
+COPY --from=build /sd.cpp/build/bin/sd /sd
+
+ENTRYPOINT [ "/sd" ]
diff --git a/README.md b/README.md
@@ -86,14 +86,16 @@ You can specify the output model format using the --out_type parameter
 
 ### Build
 
+#### Build from scratch
+
 ```shell
 mkdir build
 cd build
 cmake ..
 cmake --build . --config Release
 ```
 
-#### Using OpenBLAS
+##### Using OpenBLAS
 
 ```
 cmake .. -DGGML_OPENBLAS=ON
@@ -151,6 +153,22 @@ Using formats of different precisions will yield results of varying quality.
   <img src="./assets/img2img_output.png" width="256x">
 </p>
 
+### Docker
+
+#### Building using Docker
+
+```shell
+docker build -t sd .
+```
+
+#### Run
+
+```shell
+docker run -v /path/to/models:/models -v /path/to/output/:/output sd [args...]
+# For example
+# docker run -v ./models:/models -v ./build:/output sd -m /models/sd-v1-4-ggml-model-f16.bin -p "a lovely cat" -v -o /output/output.png
+```
+
 ## Memory/Disk Requirements
 
 | precision | f32  | f16  |q8_0  |q5_0  |q5_1  |q4_0  |q4_1  |

-Original file line number
+Diff line change
@@ @@ -0,0 +1,6 @@ @@
 +build*/
 +test/
++
 +.cache/
 +*.swp
 +models/