s

app.py

@@ -1,7 +1,22 @@
+import os
+os.system("pip install gradio==2.4.6")
 import gradio as gr
+from PIL import Image
+import torch
+
 
 def greet(num):
     return num+69
 
 iface = gr.Interface(fn=greet, inputs="number", outputs="number")
-iface.launch(share=True)
+iface.launch(share=True)
+
+
+def inference(img):
+    out = face2paint(model1, img)
+    return out
+  
+title = "Pivotal Tuning for Latent Based Real Image Editing"
+description = "Gradio Demo for Pivotal Tuning Inversion. To use it, simply upload your image, or click one of the examples to load them. Read more at the links below. Please use a cropped portrait picture for best results similar to the examples below."
+article = "<p style='text-align: center'><a href='https://github.com/danielroich/PTI' target='_blank'>Github Repo Pytorch</a>"
+gr.Interface(inference, [gr.inputs.Image(type="pil")], gr.outputs.Image(type="pil"),title=title,description=description,article=article,allow_flagging=False,allow_screenshot=False,enable_queue=True).launch(share=True)

requirements.txt

@@ -0,0 +1,9 @@
+torch
+torchvision
+Pillow
+gdown
+numpy
+scipy
+cmake
+onnxruntime-gpu
+opencv-python-headless

tune.py

@@ -1,4 +1,3 @@
-import wandb
 import click
 import os
 import sys
@@ -11,7 +10,7 @@ from IPython.display import display
 import matplotlib.pyplot as plt
 from scripts.latent_editor_wrapper import LatentEditorWrapper
 
-image_dir_name = '/home/sayantan/processed_images'
+image_dir_name = 'images'
 use_multi_id_training = False
 global_config.device = 'cuda'
 paths_config.e4e = '/home/sayantan/PTI/pretrained_models/e4e_ffhq_encode.pt'

upload_wandb.py

@@ -1,9 +0,0 @@
-import wandb
-api = wandb.Api()
-run = api.run("masc/PTIseg/rhh4r09q")
-import os
-fils = os.listdir("/home/sayantan/processed_images")
-
-for i in fils:
-    run.upload_file("/home/sayantan/processed_images/"+i,root="/home/sayantan/")
-print("uploaded all")