Add a step about accelerate config to the examples (#130)

2022-07-22 13:48:26 +02:00
parent 570d3f1eb9
commit cde0ed162a
1 changed files with 6 additions and 0 deletions
@@ -10,6 +10,12 @@ Before running the scipts, make sure to install the library's training dependenc
 pip install diffusers[training] accelerate datasets
 ```

+And initialize an [🤗Accelerate](https://github.com/huggingface/accelerate/) environment with:
+
+```bash
+accelerate config
+```
+
 ### Unconditional Flowers  

 The command to train a DDPM UNet model on the Oxford Flowers dataset: