Update README.md

README.md

@@ -15,15 +15,19 @@ license: mit
 ---
 # bagan-text-to-image
 ### Text-To-Image (Bagan Ai Generated)
+
 ### Results
-  All our results are based on fine-tuning https://huggingface.co/runwayml/stable-diffusion-v1-5 model.
 
-  We display the results using a range of training samples and images from different image categories, such as pagodas and Buddha statues.
-  ![Screenshot 2023-10-12 165137](https://github.com/simbolo-ai/Text-to-Image/assets/106800189/fa92aaf2-0346-4563-8d59-17c73440638e)
+We display the results using a range of training samples and images from different image categories, such as pagodas and Buddha statues.
+  
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6598b82502c4796342239a35/TpLTtrQBFLFQmbIvzdF5V.png)
+
 ### Ai Generated Bagan Images:
-![ananda bagan](https://github.com/simbolo-ai/Text-to-Image/assets/106800189/6965b965-73ec-436e-9210-5da550b1fe5b) ![download (2)](https://github.com/simbolo-ai/Text-to-Image/assets/106800189/b1b9af8e-5346-4b52-aa64-2f5839efa9c4)
 
-In order to get those images, we trained over 223 General Bagan Images and 137 Ananda Pagodas.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6598b82502c4796342239a35/MwR8pZ8xd6IXrNrvNL5ru.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6598b82502c4796342239a35/w-7_MOhc0dMt6uEcdPoay.png)
 
 ### Problem Statement:
 When we prompted the stable diffusion model to generate an image of Bagan, it produced an image depicting a pagoda from Thailand. Hence, our decision was to fine-tune the current stable diffusion model using a multitude of Bagan photos in order to attain a clearer outcome.
@@ -58,9 +62,6 @@ with autocast("cuda"), torch.inference_mode():
 for img in images:
     display(img)
 
-### Data:
-We used the stable diffusion v1.5 model to train with 223 bagan pictures.
-
 ### Contributors:
 Main Contributor: [Ye Bhone Lin](https://github.com/Ye-Bhone-Lin)