Update app.py

app.py

@@ -14,7 +14,6 @@ import torchvision.transforms.functional as TVF
 CLIP_PATH = "google/siglip-so400m-patch14-384"
 MODEL_PATH = "meta-llama/Meta-Llama-3.1-8B"
 CHECKPOINT_PATH = Path("9em124t2-499968")
-TITLE = "<h1><center>JoyCaption Alpha One (2024-09-20a)</center></h1>"
 CAPTION_TYPE_MAP = {
 	("descriptive", "formal", False, False): ["Write a descriptive caption for this image in a formal tone."],
 	("descriptive", "formal", False, True): ["Write a descriptive caption for this image in a formal tone within {word_count} words."],
@@ -217,41 +216,79 @@ def stream_chat(input_image: Image.Image, caption_type: str, caption_tone: str,
 
 	return caption.strip()
 
+css = """
+h1, h2, h3, h4, h5, h6, p, li, ul, ol, a, .centered-image {
+    text-align: center;
+    display: block;
+    margin-left: auto;
+    margin-right: auto;
+}
+ul, ol {
+    margin-left: auto;
+    margin-right: auto;
+    display: table;
+}
+.centered-image {
+    max-width: 100%;
+    height: auto;
+}
+"""
 
-with gr.Blocks() as demo:
-	gr.HTML(TITLE)
-
-	with gr.Row():
-		with gr.Column():
-			input_image = gr.Image(type="pil", label="Input Image")
+with gr.Blocks(theme="Hev832/Applio", css=css) as demo:
+    with gr.Tab("Welcome"):
+        gr.Markdown(
+			"""
+            <img src="https://path-to-yamamoto-logo.png" alt="Yamamoto Logo" class="centered-image">
 
-			caption_type = gr.Dropdown(
-				choices=["descriptive", "training_prompt", "rng-tags"],
-				label="Caption Type",
-				value="descriptive",
-			)
+            # 🎨 Yamamoto JoyCaption: AI-Powered Art Inspiration
 
-			caption_tone = gr.Dropdown(
-				choices=["formal", "informal"],
-				label="Caption Tone",
-				value="formal",
-			)
+            ## Accelerate Your Creative Workflow with Intelligent Image Analysis
 
-			caption_length = gr.Dropdown(
-				choices=["any", "very short", "short", "medium-length", "long", "very long"] +
-						[str(i) for i in range(20, 261, 10)],
-				label="Caption Length",
-				value="any",
-			)
+            This innovative tool empowers Yamamoto's artists to quickly generate descriptive captions,<br>
+            training prompts, and tags from existing artwork, fueling the creative process for GenAI models.
 
-			gr.Markdown("**Note:** Caption tone doesn't affect `rng-tags` and `training_prompt`.")
+            ## 🚀 How It Works:
+            1. **Upload Your Inspiration**: Drop in an image (e.g., a charcoal horse picture) that embodies your desired style.
+            2. **Choose Your Output**: Select from descriptive captions, training prompts, or tags.
+            3. **Customize the Results**: Adjust tone, length, and other parameters to fine-tune the output.
+            4. **Generate and Iterate**: Click 'Caption' to analyze your image and use the results to inspire new creations.
 
-			run_button = gr.Button("Caption")
+            <h6><center>JoyCaption Alpha One</center></h6>
+            """
+        )
 		
-		with gr.Column():
-			output_caption = gr.Textbox(label="Caption")
-	
-	run_button.click(fn=stream_chat, inputs=[input_image, caption_type, caption_tone, caption_length], outputs=[output_caption])
+    with gr.Tab("JoyCaption"):          
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(type="pil", label="Input Image")
+
+                caption_type = gr.Dropdown(
+                    choices=["descriptive", "training_prompt", "rng-tags"],
+                    label="Caption Type",
+                    value="descriptive",
+                )
+
+                caption_tone = gr.Dropdown(
+                    choices=["formal", "informal"],
+                    label="Caption Tone",
+                    value="formal",
+                )
+
+                caption_length = gr.Dropdown(
+                    choices=["any", "very short", "short", "medium-length", "long", "very long"] +
+                            [str(i) for i in range(20, 261, 10)],
+                    label="Caption Length",
+                    value="any",
+                )
+
+                gr.Markdown("**Note:** Caption tone doesn't affect `rng-tags` and `training_prompt`.")
+
+                run_button = gr.Button("Caption")
+            
+            with gr.Column():
+                output_caption = gr.Textbox(label="Caption")
+
+        run_button.click(fn=stream_chat, inputs=[input_image, caption_type, caption_tone, caption_length], outputs=[output_caption])
 
 
 if __name__ == "__main__":