up

app.py

@@ -1,19 +1,6 @@
 import gradio as gr
 
-from io import BytesIO
-import requests
-import PIL
-from PIL import Image
-import numpy as np
-import os
-import uuid
-import torch
-from torch import autocast
-import cv2
-from matplotlib import pyplot as plt
-from torchvision import transforms
 from diffusers import DiffusionPipeline, UNet2DModel
-
 from share_btn import community_icon_html, loading_icon_html, share_js
 
 unet = UNet2DModel.from_pretrained("valhalla/sdxl-inpaint-ema")
@@ -27,7 +14,7 @@ def read_content(file_path: str) -> str:
 
     return content
 
-def predict(dict, prompt="", guidance_scale, steps, strength):
+def predict(dict, prompt="", guidance_scale=7.5, steps=20, strength=1.0):
     
     init_image = dict["image"].convert("RGB").resize((1024, 1024))
     mask = dict["mask"].convert("RGB").resize((1024, 1024))
@@ -88,7 +75,7 @@ with image_blocks as demo:
                         prompt = gr.Textbox(placeholder = 'Your prompt (what you want in place of what is erased)', show_label=False, elem_id="input-text")
                         guidance_scale = gradio.Number(value=7.5, minimum=1.0, maximum=20.0)
                         steps = gradio.Number(value=20, minimum=10, maximum=50)
-                        strength = gradio.Number(value=0.0, minimum=0.0, maximum=0.0)
+                        strength = gradio.Number(value=1.0, minimum=0.0, maximum=1.0)
                         
                         btn = gr.Button("Inpaint!").style(
                             margin=False,
@@ -123,4 +110,4 @@ with image_blocks as demo:
                 """
             )
 
-image_blocks.launch()
+image_blocks.launch(share=True)