Update README.md

README.md

@@ -14,7 +14,7 @@ widget:
 
 # DreamBooth model for the zzelda concept trained by Sanderbaduk on dataset of cats.
 
-This is a Stable Diffusion model fine-tuned on the zzelda concept with DreamBooth. It can be used by using the phrase 'zzelda cat' in a prompt.
+This is a Stable Diffusion model fine-tuned on pictures of my mum's cat "Zelda" with DreamBooth. It can be used by using the phrase 'zzelda cat' in a prompt.
 
 This model was created as part of the DreamBooth Hackathon 🔥. Visit the [organisation page](https://huggingface.co/dreambooth-hackathon) for instructions on how to take part!
 
@@ -25,10 +25,10 @@ This model was created as part of the DreamBooth Hackathon 🔥. Visit the [orga
   </tr>
   <tr>
     <td>
- <img src="http://i.imgur.com/zFOzQtf.jpg" style="height:400px"> 
+ <img src="http://i.imgur.com/zFOzQtf.jpg" style="max-height:400px"> 
     </td>
     <td>
-    <img src="http://i.imgur.com/12Nilhg.png" style="height:400px">
+    <img src="http://i.imgur.com/12Nilhg.png" style="max-height:400px">
     </td>
   </tr>
 </table>
@@ -38,8 +38,8 @@ This model was created as part of the DreamBooth Hackathon 🔥. Visit the [orga
 
 This is a Stable Diffusion model fine-tuned on images of my mum's cat Zelda for the animal theme.
 
-To experiment a bit, I used a custom prompt for each image based on the file name.
-This was trained on CPU after encountering issues with CUDA, taking around 2 hours on 32 cores.
+To experiment a bit, I used a custom prompt for each image based on the file name. This works, but does not seem to have made much of a difference.
+The model was trained on CPU after encountering issues with CUDA, taking around 2 hours on 32 cores.
 
 It works a lot better locally than in the widget, where it tends to take a few more tries to get the right cat.