updt

app.py

@@ -1,43 +1,3 @@
-"""import gradio as gr
-import PIL
-from PIL import Image
-
-
-
-def asis(img):
-    # Open an image
-    #img = Image.open("example.jpg")
-    # Get the original size of the image
-    original_size = img.size
-    # Calculate the new size of the image
-    new_size = (int(original_size[0]/2), int(original_size[1]/2))
-    # Resize the image
-    img1 = img.resize(new_size)
-    img2 = img.resize(new_size, resample=Image.LANCZOS)
-    # Save the resized image
-    #img.save("resized_example.jpg")
-    return img, img1, img2, 
-    
-with gr.Blocks() as demo:
-    img_in = gr.Image(type='pil') #, shape=(512,512))
-    with gr.Row():
-        img_out = gr.Image(type='pil', label='as is') # ,shape=(512,512))
-        img_out1 = gr.Image(type='pil', label='resizing to half') # ,shape=(512,512))
-        img_out2 = gr.Image(type='pil', label='resize with resample') # ,shape=(512,512))
-    #with gr.Row():
-    #  with gr.Column():
-    #    image_in = gr.Image(type='pil', label="Original Image")
-    #    text_in = gr.Textbox()
-    #    state_in = gr.State()
-    b1 = gr.Button('Run')
-    #  chatbot = gr.Chatbot() 
-    b1.click(asis,img_in,[img_out, img_out1, img_out2])
-
-#demo.queue(concurrency_count=10)
-demo.launch(debug=True) # width="80%", height=1500)
-"""
-
-
 import PIL
 import requests
 import torch
@@ -57,35 +17,40 @@ pipe.enable_attention_slicing()
 counter = 0
 
 
-help_text = """ """
+help_text = """ Some notes from the official [instruct-pix2pix](https://huggingface.co/spaces/timbrooks/instruct-pix2pix) Space by the authors and from the official [Diffusers docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/pix2pix) -
+If you're not getting what you want, there may be a few reasons:
+1. Is the image not changing enough? Your guidance_scale may be too low. It should be >1. Higher guidance scale encourages to generate images 
+that are closely linked to the text `prompt`, usually at the expense of lower image quality. This value dictates how similar the output should 
+be to the input. This pipeline requires a value of at least `1`. It's possible your edit requires larger changes from the original image. 
+                
+2. Alternatively, you can toggle image_guidance_scale. Image guidance scale is to push the generated image towards the inital image. Image guidance 
+                scale is enabled by setting `image_guidance_scale > 1`. Higher image guidance scale encourages to generate images that are closely 
+                linked to the source image `image`, usually at the expense of lower image quality.  
+3. I have observed that rephrasing the instruction sometimes improves results (e.g., "turn him into a dog" vs. "make him a dog" vs. "as a dog").
+4. Increasing the number of steps sometimes improves results.
+5. Do faces look weird? The Stable Diffusion autoencoder has a hard time with faces that are small in the image. Try:
+    * Cropping the image so the face takes up a larger portion of the frame.
+"""
 
 def previous(image):
     return image 
 
 def chat(image_in, in_steps, in_guidance_scale, in_img_guidance_scale, image_hid, img_name, counter_out, image_oneup, prompt, history, progress=gr.Progress(track_tqdm=True)):
     progress(0, desc="Starting...")
-    if prompt == 'reverse' : #--to add revert functionality later
+    if prompt.lower() == 'reverse' : #--to add revert functionality later
         history = history or []
-        #Resizing (or not) the image for better display and adding supportive sample text
-        #add_text_list = ["There you go", "Enjoy your image!", "Nice work! Wonder what you gonna do next!", "Way to go!", "Does this work for you?", "Something like this?"]
-        #if counter_out > 0:
         temp_img_name = img_name[:-4]+str(int(time.time()))+'.png' 
         image_oneup.save(temp_img_name)
         response = 'Reverted to the last image ' + '<img src="/file=' + temp_img_name + '">'  
         history.append((prompt, response))
         return history, history, image_oneup, temp_img_name, counter_out
-    if prompt == 'restart' : #--to add revert functionality later
+    if prompt.lower() == 'restart' : #--to add revert functionality later
         history = history or []
-        #Resizing (or not) the image for better display and adding supportive sample text
-        #add_text_list = ["There you go", "Enjoy your image!", "Nice work! Wonder what you gonna do next!", "Way to go!", "Does this work for you?", "Something like this?"]
-        #if counter_out > 0:
         temp_img_name = img_name[:-4]+str(int(time.time()))+'.png' 
         image_in.save(temp_img_name)
         response = 'Reverted to the last image ' + '<img src="/file=' + temp_img_name + '">'  
         history.append((prompt, response))
         return history, history, image_in, temp_img_name, counter_out
-    # Save the resized image
-    #img.save("resized_example.jpg", optimize=True, quality=95
     if counter_out > 0:
       edited_image = pipe(prompt, image=image_hid, num_inference_steps=int(in_steps), guidance_scale=float(in_guidance_scale), image_guidance_scale=float(in_img_guidance_scale)).images[0]
       if os.path.exists(img_name):
@@ -102,17 +67,11 @@ def chat(image_in, in_steps, in_guidance_scale, in_img_guidance_scale, image_hid
     else:
       seed = random.randint(0, 1000000)
       img_name = f"./edited_image_{seed}.png"
+      #Resizing the image
       basewidth = 512
       wpercent = (basewidth/float(image_in.size[0]))
       hsize = int((float(image_in.size[1])*float(wpercent)))
       image_in = image_in.resize((basewidth,hsize), Image.Resampling.LANCZOS)
-      # Get the original size of the image
-      #original_size = image_in.size
-      # Calculate the new size of the image
-      #new_size = (int(original_size[0]/2), int(original_size[1]/2))
-      # Resize the image
-      #img1 = img.resize(new_size)
-      #image_in = image_in.resize(new_size,Image.ANTIALIAS) # resample=Image.LANCZOS) 
       edited_image = pipe(prompt, image=image_in, num_inference_steps=int(in_steps), guidance_scale=float(in_guidance_scale), image_guidance_scale=float(in_img_guidance_scale)).images[0]
       if os.path.exists(img_name):
         os.remove(img_name)
@@ -134,17 +93,10 @@ def chat(image_in, in_steps, in_guidance_scale, in_img_guidance_scale, image_hid
         counter_out += 1
         return history, history, edited_image, img_name, counter_out
         
+        
 
 with gr.Blocks() as demo:
-    gr.Markdown("""<h1><center> Chat Interface with InstructPix2Pix: Give Image Editing Instructions</h1></center>
-    <p>For faster inference without waiting in the queue, you may duplicate the space and upgrade to GPU in settings.<br/>
-    <a href="https://huggingface.co/spaces/ysharma/InstructPix2Pix_Chatbot?duplicate=true">
-    <img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
-    **Note: Please be advised that a safety checker has been implemented in this public space. 
-    Any attempts to generate inappropriate or NSFW images will result in the display of a black screen 
-    as a precautionary measure for the protection of all users. We appreciate your cooperation in 
-    maintaining a safe and appropriate environment for all members of our community.**
-    <p/>""")
+    gr.Markdown("""<h1><center>dummy</h1></center> """)
     with gr.Row():
       with gr.Column():
         image_in = gr.Image(type='pil', label="Original Image")
@@ -158,8 +110,8 @@ with gr.Blocks() as demo:
           in_steps = gr.Number(label="Enter the number of Inference steps", value = 20)
           in_guidance_scale = gr.Slider(1,10, step=0.5, label="Set Guidance scale", value=7.5)
           in_img_guidance_scale = gr.Slider(1,10, step=0.5, label="Set Image Guidance scale", value=1.5)
-          image_hid = gr.Image(type='pil', visible=True)
-          image_oneup = gr.Image(type='pil', visible=True)
+          image_hid = gr.Image(type='pil', visible=False)
+          image_oneup = gr.Image(type='pil', visible=False)
           img_name_temp_out = gr.Textbox(visible=False)
           #img_revert = gr.Checkbox(visible=True, value=False,label=to track a revert message)
           counter_out = gr.Number(visible=False, value=0, precision=0)
@@ -170,5 +122,4 @@ with gr.Blocks() as demo:
     gr.Markdown(help_text)
     
 demo.queue(concurrency_count=10)
-demo.launch(debug=True, width="80%", height=2000)
-
+demo.launch(debug=True, width="80%", height=2000)