chore: improve ci

.github/workflows/build.yml

@@ -30,7 +30,6 @@ jobs:
  with:
  submodules: recursive
 
-
  - name: Dependencies
  id: depends
  run: |
@@ -42,14 +41,37 @@ jobs:
  run: |
  mkdir build
  cd build
- cmake ..
+ cmake .. -DGGML_AVX2=ON -DSD_BUILD_SHARED_LIBS=ON
  cmake --build . --config Release
 
- #- name: Test
- #id: cmake_test
- #run: |
- #cd build
- #ctest --verbose --timeout 900
+ - name: Get commit hash
+ id: commit
+ if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/main' ) || github.event.inputs.create_release == 'true' }}
+ uses: pr-mpt/actions-commit-hash@v2
+
+ - name: Fetch system info
+ id: system-info
+ run: |
+ echo "CPU_ARCH=`uname -m`" >> "$GITHUB_OUTPUT"
+ echo "OS_NAME=`lsb_release -s -i`" >> "$GITHUB_OUTPUT"
+ echo "OS_VERSION=`lsb_release -s -r`" >> "$GITHUB_OUTPUT"
+ echo "OS_TYPE=`uname -s`" >> "$GITHUB_OUTPUT"
+
+ - name: Pack artifacts
+ id: pack_artifacts
+ if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+ run: |
+ cp ggml/LICENSE ./build/bin/ggml.txt
+ cp LICENSE ./build/bin/stable-diffusion.cpp.txt
+ zip -j sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}.zip ./build/bin/*
+
+ - name: Upload artifacts
+ if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+ uses: actions/upload-artifact@v3
+ with:
+ path: |
+ sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}.zip
+
 
  macOS-latest-cmake:
  runs-on: macos-latest
@@ -63,24 +85,46 @@ jobs:
 
  - name: Dependencies
  id: depends
- continue-on-error: true
  run: |
- brew update
+ brew install zip
 
  - name: Build
  id: cmake_build
  run: |
  sysctl -a
  mkdir build
  cd build
- cmake ..
+ cmake .. -DGGML_AVX2=ON -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64" -DSD_BUILD_SHARED_LIBS=ON
  cmake --build . --config Release
 
- #- name: Test
- #id: cmake_test
- #run: |
- #cd build
- #ctest --verbose --timeout 900
+ - name: Get commit hash
+ id: commit
+ if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/main' ) || github.event.inputs.create_release == 'true' }}
+ uses: pr-mpt/actions-commit-hash@v2
+
+ - name: Fetch system info
+ id: system-info
+ run: |
+ echo "CPU_ARCH=`uname -m`" >> "$GITHUB_OUTPUT"
+ echo "OS_NAME=`sw_vers -productName`" >> "$GITHUB_OUTPUT"
+ echo "OS_VERSION=`sw_vers -productVersion`" >> "$GITHUB_OUTPUT"
+ echo "OS_TYPE=`uname -s`" >> "$GITHUB_OUTPUT"
+
+ - name: Pack artifacts
+ id: pack_artifacts
+ if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+ run: |
+ cp ggml/LICENSE ./build/bin/ggml.txt
+ cp LICENSE ./build/bin/stable-diffusion.cpp.txt
+ zip -j sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}.zip ./build/bin/*
+
+ - name: Upload artifacts
+ if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+ uses: actions/upload-artifact@v3
+ with:
+ path: |
+ sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}.zip
+
 
  windows-latest-cmake:
  runs-on: windows-latest
@@ -89,21 +133,47 @@ jobs:
  matrix:
  include:
  - build: 'noavx'
- defines: '-DGGML_AVX=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF'
+ defines: '-DGGML_AVX=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF -DSD_BUILD_SHARED_LIBS=ON'
  - build: 'avx2'
- defines: '-DGGML_AVX2=ON'
+ defines: '-DGGML_AVX2=ON -DSD_BUILD_SHARED_LIBS=ON'
  - build: 'avx'
- defines: '-DGGML_AVX2=OFF'
+ defines: '-DGGML_AVX2=OFF -DSD_BUILD_SHARED_LIBS=ON'
  - build: 'avx512'
- defines: '-DGGML_AVX512=ON'
-
+ defines: '-DGGML_AVX512=ON -DSD_BUILD_SHARED_LIBS=ON'
+ - build: 'cuda12'
+ defines: '-DSD_CUBLAS=ON -DSD_BUILD_SHARED_LIBS=ON'
+ - build: 'rocm5.5'
+ defines: '-G Ninja -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DSD_HIPBLAS=ON -DCMAKE_BUILD_TYPE=Release -DAMDGPU_TARGETS="gfx1100;gfx1102;gfx1030" -DSD_BUILD_SHARED_LIBS=ON'
  steps:
  - name: Clone
  id: checkout
  uses: actions/checkout@v3
  with:
  submodules: recursive
 
+ - name: Install cuda-toolkit
+ id: cuda-toolkit
+ if: ${{ matrix.build == 'cuda12' }}
+ uses: Jimver/cuda-toolkit@v0.2.11
+ with:
+ cuda: '12.2.0'
+ method: 'network'
+ sub-packages: '["nvcc", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]'
+
+ - name: Install rocm-toolkit
+ id: rocm-toolkit
+ if: ${{ matrix.build == 'rocm5.5' }}
+ uses: Cyberhan123/rocm-toolkit@v0.1.0
+ with:
+ rocm: '5.5.0'
+
+ - name: Install Ninja
+ id: install-ninja
+ if: ${{ matrix.build == 'rocm5.5' }}
+ uses: urkle/action-get-ninja@v1
+ with:
+ version: 1.11.1
+
  - name: Build
  id: cmake_build
  run: |
@@ -125,12 +195,6 @@ jobs:
  & $cl /O2 /GS- /kernel avx512f.c /link /nodefaultlib /entry:main
  .\avx512f.exe && echo "AVX512F: YES" && ( echo HAS_AVX512F=1 >> $env:GITHUB_ENV ) || echo "AVX512F: NO"
 
- #- name: Test
- #id: cmake_test
- #run: |
- #cd build
- #ctest -C Release --verbose --timeout 900
-
  - name: Get commit hash
  id: commit
  if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
@@ -140,9 +204,37 @@ jobs:
  id: pack_artifacts
  if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
  run: |
- Copy-Item ggml/LICENSE .\build\bin\Release\ggml.txt
- Copy-Item LICENSE .\build\bin\Release\stable-diffusion.cpp.txt
- 7z a sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\*
+ $filePath = ".\build\bin\Release\*"
+ if (Test-Path $filePath) {
+ echo "Exists at path $filePath"
+ Copy-Item ggml/LICENSE .\build\bin\Release\ggml.txt
+ Copy-Item LICENSE .\build\bin\Release\stable-diffusion.cpp.txt
+ } elseif (Test-Path ".\build\bin\stable-diffusion.dll") {
+ $filePath = ".\build\bin\*"
+ echo "Exists at path $filePath"
+ Copy-Item ggml/LICENSE .\build\bin\ggml.txt
+ Copy-Item LICENSE .\build\bin\stable-diffusion.cpp.txt
+ } else {
+ ls .\build\bin
+ throw "Can't find stable-diffusion.dll"
+ }
+ 7z a sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-x64.zip $filePath
+
+ - name: Copy and pack Cuda runtime
+ id: pack_cuda_runtime
+ if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' && matrix.build == 'cuda12' ) || github.event.inputs.create_release == 'true' }}
+ run: |
+ echo "Cuda install location: ${{steps.cuda-toolkit.outputs.CUDA_PATH}}"
+ $dst='.\build\bin\cudart\'
+ robocopy "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
+ 7z a cudart-sd-bin-win-cu12-x64.zip $dst\*
+
+ - name: Upload Cuda runtime
+ if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' && matrix.build == 'cuda12' ) || github.event.inputs.create_release == 'true' }}
+ uses: actions/upload-artifact@v3
+ with:
+ path: |
+ cudart-sd-bin-win-cu12-x64.zip
 
  - name: Upload artifacts
  if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}

CMakeLists.txt

@@ -28,7 +28,8 @@ option(SD_CUBLAS "sd: cuda backend" OFF)
 option(SD_HIPBLAS "sd: rocm backend" OFF)
 option(SD_METAL "sd: metal backend" OFF)
 option(SD_FLASH_ATTN "sd: use flash attention for x4 less memory usage" OFF)
-option(BUILD_SHARED_LIBS "sd: build shared libs" OFF)
+option(SD_FAST_SOFTMAX "sd: x1.5 faster softmax, indeterministic (sometimes, same seed don't generate same image), cuda only" OFF)
+option(SD_BUILD_SHARED_LIBS "sd: build shared libs" OFF)
 #option(SD_BUILD_SERVER "sd: build server example" ON)
 
 if(SD_CUBLAS)
@@ -59,17 +60,24 @@ endif()
 
 set(SD_LIB stable-diffusion)
 
-add_library(${SD_LIB} stable-diffusion.h stable-diffusion.cpp model.h model.cpp util.h util.cpp upscaler.cpp
- ggml_extend.hpp clip.hpp common.hpp unet.hpp tae.hpp esrgan.hpp lora.hpp denoiser.hpp rng.hpp rng_philox.hpp
- control.hpp preprocessing.hpp)
+file(GLOB SD_LIB_SOURCES 
+ "*.h"
+ "*.cpp"
+ "*.hpp"
+)
 
-if(BUILD_SHARED_LIBS)
+# we can get only one share lib
+if(SD_BUILD_SHARED_LIBS)
  message("Build shared library")
+ set(BUILD_SHARED_LIBS OFF)
+ message(${SD_LIB_SOURCES})
+ add_library(${SD_LIB} SHARED ${SD_LIB_SOURCES})
  add_definitions(-DSD_BUILD_SHARED_LIB)
  target_compile_definitions(${SD_LIB} PRIVATE -DSD_BUILD_DLL)
  set(CMAKE_POSITION_INDEPENDENT_CODE ON)
 else()
  message("Build static library")
+ add_library(${SD_LIB} STATIC ${SD_LIB_SOURCES})
 endif()
 
 

examples/cli/main.cpp

@@ -6,7 +6,7 @@
 #include <string>
 #include <vector>
 
-#include "preprocessing.hpp"
+// #include "preprocessing.hpp"
 #include "stable-diffusion.h"
 
 #define STB_IMAGE_IMPLEMENTATION
@@ -642,7 +642,6 @@ int main(int argc, const char* argv[]) {
  3,
  input_image_buffer};
  if (params.canny_preprocess) { // apply preprocessor
- LOG_INFO("Applying canny preprocessor");
  control_image->data = preprocess_canny(control_image->data,
  control_image->width,
  control_image->height,

util.cpp

@@ -10,6 +10,7 @@
 #include <thread>
 #include <unordered_set>
 #include <vector>
+#include "preprocessing.hpp"
 
 #if defined(__APPLE__) && defined(__MACH__)
 #include <sys/sysctl.h>