Update app.py

app.py

@@ -426,14 +426,15 @@ def file_upload(file, net):
     
 help_text1 = """
             <b>Instructions</b>:
-            1. To get results faster without waiting in queue, you can duplicate into a private space with an A100 GPU.
-            2. To begin, you will have to get an identity-encoding model. You can either sample one from *weights2weights* space by clicking `Sample New Model` or by uploading an image and clicking `invert` to invert the identity into a model. You can optionally draw over the head to define a mask in the image for better results. Sampling a model takes around 10 seconds and inversion takes around 2 minutes. After this is done, you can optionally download this model for later use. A model can be uploaded in the \"Uploading a model\" tab in the `Advanced Options`.   
-            3. After getting a model, an image of the identity will be displayed on the right. You can sample from the model by changing seeds as well as prompts and then clicking `Generate`. Make sure to include \"sks person\" in your prompt to keep the same identity.
-            4. The identity in the model can be edited by changing the sliders for various attributes. After clicking `Generate`, you can see how the identity has changed and the effects are maintained across different seeds and prompts. 
+            1. To get results faster without waiting for a GPU, you can duplicate into a private space with an A100 GPU.
+            2. To begin, you will have to get an identity-encoding model. You can either sample one from *weights2weights* space by clicking `🎲 Sample new identity` or by uploading an image and clicking `⬆️ Insert identity` to insert the identity into a model. You can optionally draw over the head to define a mask in the image for better results. Sampling a model takes around 10 seconds and inserting an identity takes around 15 seconds per 100 epochs. After this is done, you can optionally download this model for later use. A model can be uploaded in the \"Uploading a model\" tab in the `Advanced Options`.   
+            3. After getting a model, an image of the identity will be displayed on the left as a reference. You can sample from the model by changing seeds as well as prompts and then clicking `🖼️ Generate` to generate images in the right column. Make sure to include \"sks person\" in your prompt to keep the same identity.
+            4. The identity in the model can be edited by changing the sliders for various attributes. After clicking `🖼️ Generate`, you can see how the identity has changed and the effects are maintained across different seeds and prompts. 
             """
 help_text2 = """<b>Tips</b>:
-            1. Editing and Identity Generation
-                * If you are interested in preserving more of the image during identity-editing (i.e., where the same seed and prompt results in the same image with only the identity changed), you can play with the "Injection Step" parameter in the \"Sampling\" tab in the `Advanced Options`. During the first *n* timesteps, the original model's weights will be used, and then the edited weights will be set during the remaining steps. Values closer to 1000 will set the edited weights early, having a more pronounced effect, which may disrupt some semantics and structure of the generated image. Lower values will set the edited weights later, better preserving image context. We notice that around 600-800 tends to produce the best results. Larger values in the range (700-1000) are helpful for more global attribute changes, while smaller (400-700) can be used for more finegrained edits. Although it is not always needed.
+            1. Identity Editing and Generation
+                * If you are interested in preserving more of the image during identity-editing (i.e., where the same seed and prompt results in the same image with only the identity changed), you can play with the "Injection Step" parameter in the \"Editing and Generation\" tab in the `Advanced Options`. 
+                    * During the first *n* timesteps, the original model's weights will be used, and then the edited weights will be set during the remaining steps. Values closer to 1000 will set the edited weights early, having a more pronounced effect, which may disrupt some semantics and structure of the generated image. Lower values will set the edited weights later, better preserving image context. We notice that around 600-800 tends to produce the best results. Larger values in the range (700-1000) are helpful for more global attribute changes, while smaller (400-700) can be used for more finegrained edits. Although it is not always needed.
                 * You can play around with negative prompts, number of inference steps, and CFG in the \"Sampling\" tab in the `Advanced Options` to affect the ultimate image quality.
                 * Sometimes the identity will not be perfectly consistent (e.g., there might be small variations of the face) when you use some seeds or prompts. This is a limitation of our method as well as an open-problem in personalized models. 
             2. Inversion 
@@ -469,7 +470,7 @@ with gr.Blocks(css="style.css") as demo:
     with gr.Column():
             with gr.Row():
                 with gr.Column(): 
-                    gr.Markdown(""" ❶ Either a) sample a random identity by clicking `🎲 Sample random identity` **or** b) upload an image (optional - draw a mask over the head) then click `⬆️ Insert identity`""")
+                    gr.Markdown("""❶ Either a) sample a random identity by clicking `🎲 Sample random identity` **or** b) upload an image (optional - draw a mask over the head) then click `⬆️ Insert identity`""")
                     input_image = gr.ImageEditor(elem_id="image_upload", type='pil', label="Reference Identity",
                                                width=512, height=512)    
 
@@ -482,9 +483,9 @@ with gr.Blocks(css="style.css") as demo:
     
     
                 with gr.Column():
-                    gr.Markdown("""❷ Generate new images of the identity from the model by entering different seeds and prompts and clicking `Generate`. Edit the encoded identity with the sliders and then visualize the edits with the generate button.""")
+                    gr.Markdown("""❷ Generate new images of the identity from the model by entering different seeds and prompts and clicking `🖼️ Generate`. Edit the encoded identity with the sliders and then visualize the edits with the generate button.""")
                     gallery = gr.Image(label="Generated Image",height=512, width=512, interactive=False)
-                    submit = gr.Button("Generate")
+                    submit = gr.Button("🖼️ Generate")
     
                         
             prompt = gr.Textbox(label="Prompt",
@@ -505,7 +506,7 @@ with gr.Blocks(css="style.css") as demo:
     
                 
             with gr.Accordion("Advanced Options ⬇️", open=False):
-                with gr.Tab("Generation"):
+                with gr.Tab("Editing and Generation"):
                     with gr.Row(): 
                         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)
@@ -513,7 +514,7 @@ with gr.Blocks(css="style.css") as demo:
                         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.Tab("Inserting Identity"):
                     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)