Correct pipeline tag and add link to Github repo

This PR updates the `pipeline_tag` to `text-to-image` to more accurately reflect the model's function as a prompt enhancer for text-to-image generation and adds a link to the Github repository.

README.md

@@ -1,14 +1,14 @@
 ---
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+datasets:
+- X-ART/LeX-R1-60K
 library_name: transformers
 license: mit
-datasets:
-  - X-ART/LeX-R1-60K
-base_model:
-  - deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
-pipeline_tag: text-generation
+pipeline_tag: text-to-image
 tags:
-  - art
-  - text-rendering
+- art
+- text-rendering
 ---
 
 # 🎨 LeX-Enhancer: Visual Prompt Generator
@@ -71,7 +71,9 @@ def create_user_prompt(simple_caption):
         "5. The detailed caption should be human readable and fluent. "
         "6. Avoid using vague expressions such as \"may be\" or \"might be\"; the generated caption must be in a definitive, narrative tone. "
         "7. Do not use negative sentence structures, such as \"there is nothing in the image,\" etc. The entire caption should directly describe the content of the image. "
-        "8. The entire output should be limited to 200 words.\n\n"
+        "8. The entire output should be limited to 200 words.
+
+"
         f"SIMPLE CAPTION: {simple_caption}"
     )
 
@@ -96,4 +98,7 @@ output = model.generate(
 )
 
 print("*" * 80)
-# Output will stream via TextStreamer
+# Output will stream via TextStreamer
+```
+
+Github repository: https://github.com/zhaoshitian/LeX-Art