Update app.py

app.py

@@ -31,6 +31,7 @@ from diffusers import (
 )
 from huggingface_hub import snapshot_download
 import spaces
+from gradio_imageslider import ImageSlider
 
 
 models_path = snapshot_download(repo_id="Snapchat/w2w")
@@ -400,7 +401,7 @@ def run_inversion(net, dict, pcs, epochs, weight_decay,lr):
     return net, net, image
     
     
-@spaces.GPU
+#@spaces.GPU
 def file_upload(file, net):
     device="cuda"
     weights = torch.load(file.name).to(device)
@@ -444,22 +445,23 @@ with gr.Blocks(css="style.css") as demo:
     net = gr.State()  
     gr.HTML(intro)
         
-    gr.Markdown("""<div style="text-align: justify;"> In this demo, you can get an identity-encoding model by sampling or inverting. To use a model previously downloaded from this demo see \"Uploading a model\" in the Advanced Options. Next, you can generate new images from it, or edit the identity encoded in the model and generate images from the edited model. We provide detailed instructions and tips at the bottom of the page.""")
+    gr.Markdown(""" **Getting Started:** Sample a random identity or invert to get an identity-encoding model 👩🏻‍🎨(or - Upload a previously downloaded model using the `Uploading a model` option in `Advanced Options`). 
+    **What You Can Do?** Generate new images & edit the encoded identity 👩🏻->👩🏻‍🦱. See further instructions and tips at the bottom of the page 🤗.""")
     with gr.Column():
             with gr.Row():
                 with gr.Column(): 
-                    gr.Markdown("""1) Either sample a new model, or upload an image (optionally draw a mask over the head) and click `invert`.""")
-                    sample = gr.Button("🎲 Sample New Model")
+                    gr.Markdown(""" ❶ sample a face -or- upload an image (optional - draw a mask over the head) and invert""")
                     input_image = gr.ImageEditor(elem_id="image_upload", type='pil', label="Reference Identity",
                                                width=512, height=512)    
                       
                     with gr.Row():
+                        sample = gr.Button("🎲 Sample random face")
                         invert_button = gr.Button("⬆️ Invert")
     
     
     
                 with gr.Column():
-                    gr.Markdown("""2) Generate images of the sampled/inverted identity or edit the identity with the sliders and generate new images with various prompts and seeds.""")
+                    gr.Markdown("""❷ Generate new images of the sampled/inverted identity & edit with the sliders""")
                     gallery = gr.Image(label="Generated Image",height=512, width=512, interactive=False)
                     submit = gr.Button("Generate")
     
@@ -469,7 +471,6 @@ with gr.Blocks(css="style.css") as demo:
                                                 placeholder="sks person", 
                                                 value="sks person")
                 
-            seed = gr.Number(value=5, label="Seed", precision=0, interactive=True)
                     
             # Editing 
             with gr.Column():
@@ -482,21 +483,23 @@ with gr.Blocks(css="style.css") as demo:
     
                 
             with gr.Accordion("Advanced Options", open=False):
-                with gr.Tab("Inversion"):
-                    with gr.Row():     
-                        lr = gr.Number(value=1e-1, label="Learning Rate", interactive=True)
-                        pcs = gr.Slider(label="# Principal Components", value=10000, step=1, minimum=1, maximum=10000, interactive=True)
-                    with gr.Row():
-                        epochs = gr.Slider(label="Epochs", value=800, step=1, minimum=1, maximum=2000, interactive=True)
-                        weight_decay = gr.Number(value=1e-10, label="Weight Decay", interactive=True)
                 with gr.Tab("Sampling"):
-                    with gr.Row():     
+                    with gr.Row(): 
+                        seed = gr.Number(value=5, label="Seed", precision=0, interactive=True)
                         cfg= gr.Slider(label="CFG", value=3.0, step=0.1, minimum=0, maximum=10, interactive=True)
                         steps = gr.Slider(label="Inference Steps",  value=25, step=1, minimum=0, maximum=100, interactive=True)
                     with gr.Row():
                         negative_prompt = gr.Textbox(label="Negative Prompt", placeholder="low quality, blurry, unfinished, nudity, weapon", value="low quality, blurry, unfinished, nudity, weapon")
                         injection_step = gr.Slider(label="Injection Step",  value=800, step=1, minimum=0, maximum=1000, interactive=True)
                                 
+                with gr.Tab("Inversion"):
+                    with gr.Row():     
+                        lr = gr.Number(value=1e-1, label="Learning Rate", interactive=True)
+                        pcs = gr.Slider(label="# Principal Components", value=10000, step=1, minimum=1, maximum=10000, interactive=True)
+                    with gr.Row():
+                        epochs = gr.Slider(label="Epochs", value=800, step=1, minimum=1, maximum=2000, interactive=True)
+                        weight_decay = gr.Number(value=1e-10, label="Weight Decay", interactive=True)
+                
                 with gr.Tab("Uploading a model"):
                     gr.Markdown("""<div style="text-align: justify;">Upload a model below downloaded from this demo.""")
     
@@ -544,10 +547,10 @@ with gr.Blocks(css="style.css") as demo:
                 * For inverting a realistic photo of an identity, typically 800 epochs with lr=1e-1 and 10,000 principal components (PCs) works well. If the resulting generations have artifacted and unrealstic textures, there is probably overfitting and you may want to reduce the number of epochs or learning rate, or play with weight decay. If the generations do not look like the input photo, then you may want to increase the number of epochs.
                 * For inverting out-of-distribution identities, such as artistic renditions of people or non-humans (e.g. the ones shown in the paper), it is recommended to use 1000 PCs, lr=1, and train for 800 epochs.
                 * Note that if you change the number of PCs, you will probably need to change the learning rate. For less PCs, higher learning rates are typically required.""" 
-        
-            
-    gr.Markdown(help_text1)
-    gr.Markdown(help_text2)
+                
+    with gr.Accordion("💡Instructions & Tips⬇️", open=False):
+        gr.Markdown(help_text1)
+        gr.Markdown(help_text2)
         
 demo.queue().launch()