Update README.md

README.md

@@ -91,6 +91,9 @@ Stable Diffusion v1-4 is a latent diffusion model which combines an autoencoder
 
 - **Hardware:** Nvidia GTX 1650 4GB vRAM, 8GB RAM
 - **Learning rate:** 1e-04
+
+---
+widget:
 - the accelerate launch script on colab goes like this:
       !accelerate launch train_text_to_image_lora.py \
         --pretrained_model_name_or_path="CompVis/stable-diffusion-v1-4" \
@@ -102,4 +105,5 @@ Stable Diffusion v1-4 is a latent diffusion model which combines an autoencoder
         --seed=42 \
         --output_dir="kanji_sakana_english" \
         --validation_prompt="A kanji meaning Elon Musk" \
-        --push_to_hub
+        --push_to_hub
+---