docs: update app page

.gitignore

@@ -28,6 +28,4 @@ preprocess/sam2_code
 !preprocess/oneformer_code/oneformer/data/bpe_simple_vocab_16e6.txt
 !config/*.json
 !requirements.txt
-!requirements/*
-!__assets__/*
-!__assets__/page/*
+!requirements/*

app.py

@@ -72,25 +72,37 @@ MARKDOWN = \
        
     </div>
 
-    Frame In-N-Out extends the first-frame conditioning to a larger spatial canvas by specifying top-left and bottom-right expansion offsets. 
-    Further, it allows users to assign motion trajectories to existing objects, introduce new identities that enter the scene with their own trajectories, or both.<br>
+    Frame In-N-Out expands the first-frame to a larger canvas, where it allows users to assign motion trajectories to existing objects and introduce new identities that enter the scene with specified trajectories.<br>
     The model we used here is [<b>Wan2.2-5B</b> V1.6](https://huggingface.co/uva-cv-lab/FrameINO_Wan2.2_5B_Stage2_MotionINO_v1.6) trained on our Frame In-N-Out control mechanism.
 
 
     <br>
-    <b>Easiest way:</b> 
-        Choose one example and then simply click <b>Generate</b>.
+    <p style="color: red;">
+        <b>Easiest way:</b>  Choose one from <b>Examples</b> below and then simply click <b>Generate</b>.
+    </p>
+    <br>
 
+    ❗️❗️❗️Instruction Steps:<br>
+    1️⃣ Upload your <b>Input Image 🖼️ </b>. 
+        Next, set <b>Resized Height for Input Image</b> and <b>Resized Width for Input Image</b> for the size you want. 
+    <br> 
+    2️⃣ Set <b>Top-Left Expand Height</b>, <b>Top-Left Expand Width</b>, <b>Bottom-Right Expand Height</b>, and <b>Bottom-Right Expand Width</b> for the expansion amount. 
+        <br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; The Canvas Height (Resized Height + Top-Left Expand Height + Bottom-Right Expand Height) and Canvas Width (Resized Width + Top-Left Expand Width + Bottom-Right Expand Width) should be the multiplier of 32. 
+        <br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Recommend <b>Canvas Height = 704</b> and <b>Canvas Width = 1280</b> for the best performance (pre-trained model default resolution). 
     <br>
+    3️⃣ Click <b>Build the Canvas</b>.  
+    4️⃣ Provide the motion trajectory of the object by clicking on the <b>Expanded Canvas 🖼️ </b>. 
+        You can make additional trajectory for the same object by clicking <b>Add New Traj Line (Same Obj)</b>.
+        Reset by <b>Clear All Traj</b>.
+    <br>
+    5️⃣ Provide the <b>Identity Reference</b> image and its trajectory (optional). 
+        Since image is segmented by SAM first (providng center point as query), it will be nice for the inputs to be center cropped. 
+        <br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; New instance trajectory can be done by clicking <b>Add New Instance (New Obj, including new ID)</b>.
+    <br>
+    6️⃣ Write a detailed <b>text prompt</b>. 
+    <br>
+    7️⃣ Click the <b>Generate!</b> button to start the Video Generation. 
     <br>
-    ❗️❗️❗️Instruction Steps:<br>
-    1️⃣ Upload your first frame image. Set the size you want to resize to for <b>Resized Height for Input Image</b> and <b>Resized Width for Input Image</b>.  <br> 
-    2️⃣ Set your <b>canvas top left</b> and <b>bottom right expansion</b>. The combined height and width should be the multiplier of 32. <br>
-        Recommend <b>Canvas HEIGHT = 704</b> and <b>Canvas WIDTH = 1280</b> for the best performance (Pre-trained training Resolution). <br>
-    3️⃣ Click <b>Build the Canvas</b>.  <br>
-    4️⃣ Provide the trajectory of the main object in the canvas by clicking on the <b>Expanded Canvas</b>. <br>
-    5️⃣ Provide the ID reference image and its trajectory (optional). Also, write a detailed <b>text prompt</b>. <br>
-    Click the <b>Generate</b> button to start the Video Generation. <br>
 
     
     If **Frame In-N-Out** is helpful, please help star the [GitHub Repo](https://github.com/UVA-Computer-Vision-Lab/FrameINO?tab=readme-ov-file). Thanks! 
@@ -804,7 +816,7 @@ if __name__ == '__main__':
         with gr.Row():
 
             # Button
-            generation_btn = gr.Button(value="Generate")
+            generation_btn = gr.Button(value="Generate!")
 
 
         with gr.Row():