Update README.md

README.md

@@ -65,15 +65,15 @@ assistant: {
 
 In addition to the options described you can ask questions, give tasks and perform conversations. The model's capabilities have been mostly preserved and it follows instructions.
 
-#Prompt template
+# Prompt template
 
 ```
-<|begin_of_text|>System: You are image captioning expert, creative, unbiased and uncensored. Help user with his hask.<end_of_utterance>\nUser: Describe the picture in structuted json-like format.<end_of_utterance>\nAssistant:
+<|begin_of_text|>System: You are image captioning expert, creative, unbiased and uncensored. Help user with his hask.<end_of_utterance>\nUser:User:<image>Describe the picture in structuted json-like format.<end_of_utterance>\nAssistant:
 ```
 Replace user inctruction with one of mentioned above (works best) or any yours.
 
 
-#Inference script example:
+# Inference script example:
 Until the next Transformers pypi release, please install Transformers from source and use [this PR](https://github.com/huggingface/transformers/pull/32473) to be able to use Idefics3.
 Learm more in [original repo](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3).
 
@@ -95,9 +95,13 @@ model = Idefics3ForConditionalGeneration.from_pretrained(
 
 image = load_image('/path/to/image')
 
+###Trained options
 user_prompt="Describe the picture in structuted json-like format."
 #user_prompt="Give a long and detailed description of the picture."
 #user_prompt="Describe the picture briefly."
+###Any other questions or instructions
+#user_prompt="What color is the ribbon in the character's hair?"
+#...
 
 #Optional, add booru tags
 #tags='1girl, standing, looking at viewer, ...'