Refactor advanced options sliders and enhance UI with instructional tips for video generation

app.py

@@ -309,15 +309,12 @@ def create_advanced_options():
         inference_steps = gr.Slider(
             label="4.2 Inference Steps", minimum=1, maximum=100, step=1, value=40
         )
-        images_per_prompt = gr.Slider(
-            label="4.3 Images per Prompt", minimum=1, maximum=10, step=1, value=1
-        )
         guidance_scale = gr.Slider(
-            label="4.4 Guidance Scale", minimum=1.0, maximum=20.0, step=0.1, value=3.0
+            label="4.3 Guidance Scale", minimum=1.0, maximum=20.0, step=0.1, value=3.0
         )
 
         height_slider = gr.Slider(
-            label="4.5 Height",
+            label="4.4 Height",
             minimum=256,
             maximum=1024,
             step=64,
@@ -325,7 +322,7 @@ def create_advanced_options():
             visible=False,
         )
         width_slider = gr.Slider(
-            label="4.6 Width",
+            label="4.5 Width",
             minimum=256,
             maximum=1024,
             step=64,
@@ -333,7 +330,7 @@ def create_advanced_options():
             visible=False,
         )
         num_frames_slider = gr.Slider(
-            label="4.7 Number of Frames",
+            label="4.5 Number of Frames",
             minimum=1,
             maximum=200,
             step=1,
@@ -341,7 +338,7 @@ def create_advanced_options():
             visible=False,
         )
         frame_rate = gr.Slider(
-            label="4.8 Frame Rate",
+            label="4.7 Frame Rate",
             minimum=1,
             maximum=60,
             step=1,
@@ -352,7 +349,6 @@ def create_advanced_options():
         return [
             seed,
             inference_steps,
-            images_per_prompt,
             guidance_scale,
             height_slider,
             width_slider,
@@ -363,7 +359,40 @@ def create_advanced_options():
 
 # Define the Gradio interface with tabs
 with gr.Blocks(theme=gr.themes.Soft()) as iface:
-    gr.Markdown("# Video Generation with LTX Video")
+    with gr.Row(elem_id="title-row"):
+        gr.Markdown(
+            """
+        <div style="text-align: center; margin-bottom: 1em">
+            <h1 style="font-size: 2.5em; font-weight: 600; margin: 0.5em 0;">Video Generation with LTX Video</h1>
+        </div>
+        """
+        )
+    with gr.Accordion(
+        " 📖 Tips for Best Results", open=False, elem_id="instructions-accordion"
+    ):
+        gr.Markdown(
+            """
+        📝 Prompt Engineering
+
+        When writing prompts, focus on detailed, chronological descriptions of actions and scenes. Include specific movements, appearances, camera angles, and environmental details - all in a single flowing paragraph. Start directly with the action, and keep descriptions literal and precise. Think like a cinematographer describing a shot list. Keep within 200 words.
+        For best results, build your prompts using this structure:
+
+        - Start with main action in a single sentence
+        - Add specific details about movements and gestures
+        - Describe character/object appearances precisely
+        - Include background and environment details
+        - Specify camera angles and movements
+        - Describe lighting and colors
+        - Note any changes or sudden events
+
+        🎮 Parameter Guide
+
+        - Resolution Preset: Higher resolutions for detailed scenes, lower for faster generation and simpler scenes
+        - Seed: Save seed values to recreate specific styles or compositions you like
+        - Guidance Scale: Higher values (5-7) for accurate prompt following, lower values (3-5) for more creative freedom
+        - Inference Steps: More steps (40+) for quality, fewer steps (20-30) for speed
+        """
+        )
 
     with gr.Tabs():
         # Text to Video Tab