docs: add CLI-GUI to list (#546)

.github/workflows/build.yml

@@ -155,15 +155,15 @@ jobs:
       matrix:
         include:
           - build: "noavx"
-            defines: "-DGGML_AVX=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF -DSD_BUILD_SHARED_LIBS=ON"
+            defines: "-DGGML_NATIVE=OFF -DGGML_AVX=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF -DSD_BUILD_SHARED_LIBS=ON"
           - build: "avx2"
-            defines: "-DGGML_AVX2=ON -DSD_BUILD_SHARED_LIBS=ON"
+            defines: "-DGGML_NATIVE=OFF -DGGML_AVX2=ON -DSD_BUILD_SHARED_LIBS=ON"
           - build: "avx"
-            defines: "-DGGML_AVX2=OFF -DSD_BUILD_SHARED_LIBS=ON"
+            defines: "-DGGML_NATIVE=OFF -DGGML_AVX=ON -DGGML_AVX2=OFF -DSD_BUILD_SHARED_LIBS=ON"
           - build: "avx512"
-            defines: "-DGGML_AVX512=ON -DSD_BUILD_SHARED_LIBS=ON"
+            defines: "-DGGML_NATIVE=OFF -DGGML_AVX512=ON -DGGML_AVX=ON -DGGML_AVX2=ON -DSD_BUILD_SHARED_LIBS=ON"
           - build: "cuda12"
-            defines: "-DSD_CUDA=ON -DSD_BUILD_SHARED_LIBS=ON"
+            defines: "-DSD_CUDA=ON -DSD_BUILD_SHARED_LIBS=ON -DCMAKE_CUDA_ARCHITECTURES=60;61;70;75"
           # - 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'
           - build: 'vulkan'

CMakeLists.txt

@@ -54,7 +54,7 @@ endif ()
 
 if (SD_HIPBLAS)
     message("-- Use HIPBLAS as backend stable-diffusion")
-    set(GGML_HIPBLAS ON)
+    set(GGML_HIP ON)
     add_definitions(-DSD_USE_CUDA)
     if(SD_FAST_SOFTMAX)
         set(GGML_CUDA_FAST_SOFTMAX ON)

README.md

@@ -326,6 +326,7 @@ These projects use `stable-diffusion.cpp` as a backend for their image generatio
 
 - [Jellybox](https://jellybox.com)
 - [Stable Diffusion GUI](https://github.com/fszontagh/sd.cpp.gui.wx)
+- [Stable Diffusion CLI-GUI] (https://github.com/piallai/stable-diffusion.cpp)
 
 ## Contributors
 

stable-diffusion.cpp

@@ -525,6 +525,10 @@ public:
             if (is_using_v_parameterization_for_sd2(ctx, sd_version_is_inpaint(version))) {
                 is_using_v_parameterization = true;
             }
+        } else if (sd_version_is_sdxl(version)) {
+            if (model_loader.tensor_storages_types.find("v_pred") != model_loader.tensor_storages_types.end()) {
+                is_using_v_parameterization = true;
+            }
         } else if (version == VERSION_SVD) {
             // TODO: V_PREDICTION_EDM
             is_using_v_parameterization = true;
@@ -606,7 +610,9 @@ public:
         ggml_set_f32(timesteps, 999);
 
         struct ggml_tensor* concat = is_inpaint ? ggml_new_tensor_4d(work_ctx, GGML_TYPE_F32, 8, 8, 5, 1) : NULL;
-        ggml_set_f32(concat, 0);
+        if (concat != NULL) {
+            ggml_set_f32(concat, 0);
+        }
 
         int64_t t0              = ggml_time_ms();
         struct ggml_tensor* out = ggml_dup_tensor(work_ctx, x_t);