chunzhi/stable-diffusion-cli-on-modal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Uddate onnxruntime to 1.18.0.

Browse Source
This commit is contained in:
hodanov 2024-06-30 18:13:21 +09:00
parent 6a5c98891e
commit c07e787dbc
1 changed files with 11 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
app/requirements.txt
View File

@ -5,7 +5,7 @@ transformers==4.40.2
xformers==0.0.26.post1 xformers==0.0.26.post1
invisible_watermark # To help viewers identify the images as machine-generated. invisible_watermark # To help viewers identify the images as machine-generated.
onnxruntime==1.17.3 # ONNX Runtime uses the following optimizations to speed up Stable Diffusion in CUDA. onnxruntime==1.18.0 # ONNX Runtime uses the following optimizations to speed up Stable Diffusion in CUDA.
safetensors==0.4.3 # To store tensors safely. safetensors==0.4.3 # To store tensors safely.
controlnet_aux controlnet_aux
@ -13,3 +13,13 @@ Pillow
pillow-avif-plugin # To save images in AVIF format. pillow-avif-plugin # To save images in AVIF format.
pyyaml # To read the configuration file by written YAML. pyyaml # To read the configuration file by written YAML.
peft peft
numpy==1.26.4
# A module that was compiled using NumPy 1.x cannot be run in
# NumPy 2.0.0 as it may crash. To support both 1.x and 2.x
# versions of NumPy, modules must be compiled with NumPy 2.0.
# Some module may need to rebuild instead e.g. with 'pybind11>=2.12'.
# If you are a user of the module, the easiest solution will be to
# downgrade to 'numpy<2' or try to upgrade the affected module.
# We expect that some modules will need time to support NumPy 2.