Skip to content

Commit 0d8efbc

Browse files
william-murray1204william-murray1204
committed
sync: update submodule
1 parent 99bdb29 commit 0d8efbc

18 files changed

+48
-47
lines changed

‎README.md‎

Lines changed: 5 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -93,13 +93,14 @@ CMAKE_ARGS="-DSD_CUDA=ON" pip install stable-diffusion-cpp-python
9393
<details>
9494
<summary>Using HIPBLAS (ROCm)</summary>
9595

96-
This provides BLAS acceleration using the ROCm cores of your AMD GPU. Make sure you have the ROCm toolkit installed and that you replace the `-DAMDGPU_TARGETS=` value with that of your GPU architecture.
96+
This provides BLAS acceleration using the ROCm cores of your AMD GPU. Make sure you have the ROCm toolkit installed and that you replace the `$GFX_NAME` value with that of your GPU architecture (`gfx1030` for consumer RDNA2 cards for example).
9797
Windows users refer to [docs/hipBLAS_on_Windows.md](docs%2FhipBLAS_on_Windows.md) for a comprehensive guide and troubleshooting tips.
9898

9999
```bash
100-
export GFX_NAME=$(rocminfo | grep -m 1 -E "gfx[^0]{1}" | sed -e 's/ *Name: *//' | awk '{$1=$1; print}' || echo "rocminfo missing")
101-
echo $GFX_NAME
102-
CMAKE_ARGS="-G Ninja -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DSD_HIPBLAS=ON -DCMAKE_BUILD_TYPE=Release -DAMDGPU_TARGETS=$GFX_NAME -DCMAKE_BUILD_WITH_INSTALL_RPATH=ON" pip install stable-diffusion-cpp-python
100+
if command -v rocminfo; then export GFX_NAME=$(rocminfo | awk '/ *Name: +gfx[1-9]/ {print $2; exit}'); else echo "rocminfo missing!"; fi
101+
if [ -z "${GFX_NAME}" ]; then echo "Error: Couldn't detect GPU!"; else echo "Building for GPU: ${GFX_NAME}"; fi
102+
103+
CMAKE_ARGS="-G Ninja -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DSD_HIPBLAS=ON -DCMAKE_BUILD_TYPE=Release -DAMDGPU_TARGETS=$GFX_NAME -DCMAKE_BUILD_WITH_INSTALL_RPATH=ON -DCMAKE_POSITION_INDEPENDENT_CODE=ON" pip install stable-diffusion-cpp-python
103104
```
104105

105106
</details>

‎docs/hipBLAS_on_Windows.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -47,8 +47,8 @@ set ninja=C:\Program Files\ninja\ninja.exe
4747

4848
## Building stable-diffusion.cpp
4949

50-
The thing different from the regular CPU build is `-DSD_HIPBLAS=ON` ,
51-
`-G "Ninja"`, `-DCMAKE_C_COMPILER=clang`, `-DCMAKE_CXX_COMPILER=clang++`, `-DAMDGPU_TARGETS=gfx1100`, `-DCMAKE_BUILD_WITH_INSTALL_RPATH=ON`
50+
The thing different from the regular CPU build is `-DSD_HIPBLAS=ON`,
51+
`-G "Ninja"`, `-DCMAKE_C_COMPILER=clang`, `-DCMAKE_CXX_COMPILER=clang++`, `-DAMDGPU_TARGETS=gfx1100`, `-DCMAKE_BUILD_WITH_INSTALL_RPATH=ON`, `-DCMAKE_POSITION_INDEPENDENT_CODE=ON`
5252

5353
Note:
5454
If you encounter an error such as the following:

‎stable_diffusion_cpp/__init__.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,4 +4,4 @@
44

55
# isort: on
66

7-
__version__ = "0.3.3"
7+
__version__ = "0.3.4"

‎tests/test_chroma.py‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -3,9 +3,9 @@
33

44
from stable_diffusion_cpp import StableDiffusion
55

6-
DIFFUSION_MODEL_PATH = "C:\\stable-diffusion\\flux-chroma\\Chroma1-HD-Flash-Q4_0.gguf"
7-
T5XXL_PATH = "C:\\stable-diffusion\\flux\\t5xxl_q8_0.gguf"
8-
VAE_PATH = "C:\\stable-diffusion\\flux\\ae-f16.gguf"
6+
DIFFUSION_MODEL_PATH = "F:\\stable-diffusion\\flux-chroma\\Chroma1-HD-Flash-Q4_0.gguf"
7+
T5XXL_PATH = "F:\\stable-diffusion\\flux\\t5xxl_q8_0.gguf"
8+
VAE_PATH = "F:\\stable-diffusion\\flux\\ae-f16.gguf"
99

1010

1111
PROMPT = "a lovely cat holding a sign says 'chroma.cpp'"

‎tests/test_controlnet.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,8 +3,8 @@
33

44
from stable_diffusion_cpp import StableDiffusion
55

6-
MODEL_PATH = "C:\\stable-diffusion\\v1-5-pruned-emaonly.safetensors"
7-
CONTROLNET_MODEL_PATH = "C:\\stable-diffusion\\control_nets\\control_openpose-fp16.safetensors"
6+
MODEL_PATH = "F:\\stable-diffusion\\v1-5-pruned-emaonly.safetensors"
7+
CONTROLNET_MODEL_PATH = "F:\\stable-diffusion\\control_nets\\control_openpose-fp16.safetensors"
88

99

1010
INPUT_IMAGE_PATH = "assets\\input.png"

‎tests/test_convert_model.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22

33
from stable_diffusion_cpp import StableDiffusion
44

5-
MODEL_PATH = "C:\\stable-diffusion\\turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae.safetensors"
5+
MODEL_PATH = "F:\\stable-diffusion\\turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae.safetensors"
66

77

88
def test_convert_model():

‎tests/test_edit.py‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -3,10 +3,10 @@
33

44
from stable_diffusion_cpp import StableDiffusion
55

6-
DIFFUSION_MODEL_PATH = "C:\\stable-diffusion\\flux-kontext\\flux1-kontext-dev-Q3_K_S.gguf"
7-
T5XXL_PATH = "C:\\stable-diffusion\\flux\\t5xxl_q8_0.gguf"
8-
CLIP_L_PATH = "C:\\stable-diffusion\\flux\\clip_l-q8_0.gguf"
9-
VAE_PATH = "C:\\stable-diffusion\\flux\\ae-f16.gguf"
6+
DIFFUSION_MODEL_PATH = "F:\\stable-diffusion\\flux-kontext\\flux1-kontext-dev-Q3_K_S.gguf"
7+
T5XXL_PATH = "F:\\stable-diffusion\\flux\\t5xxl_q8_0.gguf"
8+
CLIP_L_PATH = "F:\\stable-diffusion\\flux\\clip_l-q8_0.gguf"
9+
VAE_PATH = "F:\\stable-diffusion\\flux\\ae-f16.gguf"
1010

1111

1212
INPUT_IMAGE_PATHS = [

‎tests/test_flux.py‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -3,12 +3,12 @@
33

44
from stable_diffusion_cpp import StableDiffusion
55

6-
DIFFUSION_MODEL_PATH = "C:\\stable-diffusion\\flux\\flux1-schnell-q3_k.gguf"
7-
# DIFFUSION_MODEL_PATH = "C:\\stable-diffusion\\flux\\flux1-dev-q8_0.gguf"
8-
T5XXL_PATH = "C:\\stable-diffusion\\flux\\t5xxl_q8_0.gguf"
9-
CLIP_L_PATH = "C:\\stable-diffusion\\flux\\clip_l-q8_0.gguf"
10-
VAE_PATH = "C:\\stable-diffusion\\flux\\ae-f16.gguf"
11-
LORA_DIR = "C:\\stable-diffusion\\loras"
6+
DIFFUSION_MODEL_PATH = "F:\\stable-diffusion\\flux\\flux1-schnell-q3_k.gguf"
7+
# DIFFUSION_MODEL_PATH = "F:\\stable-diffusion\\flux\\flux1-dev-q8_0.gguf"
8+
T5XXL_PATH = "F:\\stable-diffusion\\flux\\t5xxl_q8_0.gguf"
9+
CLIP_L_PATH = "F:\\stable-diffusion\\flux\\clip_l-q8_0.gguf"
10+
VAE_PATH = "F:\\stable-diffusion\\flux\\ae-f16.gguf"
11+
LORA_DIR = "F:\\stable-diffusion\\loras"
1212

1313

1414
PROMPTS = [

‎tests/test_img2img.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@
33

44
from stable_diffusion_cpp import StableDiffusion
55

6-
MODEL_PATH = "C:\\stable-diffusion\\turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae.safetensors"
6+
MODEL_PATH = "F:\\stable-diffusion\\turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae.safetensors"
77

88

99
INPUT_IMAGE_PATH = "assets\\input.png"

‎tests/test_inpainting.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@
33

44
from stable_diffusion_cpp import StableDiffusion
55

6-
MODEL_PATH = "C:\\stable-diffusion\\turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae.safetensors"
6+
MODEL_PATH = "F:\\stable-diffusion\\turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae.safetensors"
77

88

99
INPUT_IMAGE_PATH = "assets\\input.png"

0 commit comments

Comments
 (0)