| (Draft v1) | |
| Download the pretrained SD-2.1-base models from HuggingFace. | |
| https://huggingface.co/stabilityai/stable-diffusion-2-1-base/resolve/main/v2-1_512-ema-pruned.ckpt | |
| https://github.com/csslc/CCSR/issues/30#issuecomment-2314607165 | |
| CUDA version 12.5. | |
| conda install pytorch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 pytorch-cuda=12.1 -c pytorch -c nvidia | |
| export CUDA_HOME=/usr/local/cuda-12.5 | |
| export PATH=$CUDA_HOME/bin:$PATH | |
| export LD_LIBRARY_PATH=$CUDA_HOME/lib64:$LD_LIBRARY_PATH | |
| https://github.com/csslc/CCSR/issues/41#issuecomment-2553300085 | |
| Hello, the --pretrained_model_path sholud be preset/models/stable-diffusion-2-1-base, which you can download from HuggingFace. | |
| Reupload of models from | |
| https://github.com/csslc/CCSR/tree/CCSR-v2.0 | |
| Maintaining original project license: apache-2.0 | |