Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
|
| 2 |
|
| 3 |
Reupload of models from
|
|
|
|
| 1 |
+
(Draft v1)
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
Download the pretrained SD-2.1-base models from HuggingFace.
|
| 5 |
+
https://huggingface.co/stabilityai/stable-diffusion-2-1-base/resolve/main/v2-1_512-ema-pruned.ckpt
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
https://github.com/csslc/CCSR/issues/30#issuecomment-2314607165
|
| 9 |
+
|
| 10 |
+
CUDA version 12.5.
|
| 11 |
+
conda install pytorch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 pytorch-cuda=12.1 -c pytorch -c nvidia
|
| 12 |
+
export CUDA_HOME=/usr/local/cuda-12.5
|
| 13 |
+
export PATH=$CUDA_HOME/bin:$PATH
|
| 14 |
+
export LD_LIBRARY_PATH=$CUDA_HOME/lib64:$LD_LIBRARY_PATH
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
https://github.com/csslc/CCSR/issues/41#issuecomment-2553300085
|
| 18 |
+
Hello, the --pretrained_model_path sholud be preset/models/stable-diffusion-2-1-base, which you can download from HuggingFace.
|
| 19 |
|
| 20 |
|
| 21 |
Reupload of models from
|