Update app.py

app.py

@@ -1,37 +1,27 @@
 import streamlit as st
-import os
+import cv2
+import numpy as np
 from PIL import Image
-import subprocess
+import paddle
+from ppgan.apps import AnimeGANPredictor
 
-st.set_page_config(page_title="PaddleGAN Editor", layout="wide")
-st.title("🎨 PaddleGAN Image Editor")
+st.set_page_config(page_title="AnimeGAN", layout="centered")
+st.title("🎨 Convert Your Photo to Anime Style")
 
-task = st.selectbox("Choose a task", ["Photo2Cartoon", "GPEN Face Enhancement"])
+@st.cache_resource
+def load_model():
+    return AnimeGANPredictor()
 
-uploaded_file = st.file_uploader("Upload an image", type=["jpg", "png"])
+predictor = load_model()
 
+uploaded_file = st.file_uploader("Upload a photo", type=["jpg", "jpeg", "png"])
 if uploaded_file:
-    input_path = f"input.jpg"
-    with open(input_path, "wb") as f:
-        f.write(uploaded_file.read())
-    st.image(Image.open(input_path), caption="Uploaded Image", use_column_width=True)
+    image = Image.open(uploaded_file).convert("RGB")
+    st.image(image, caption="Original Image", use_column_width=True)
 
-    if st.button("Run PaddleGAN"):
-        if task == "Photo2Cartoon":
-            cmd = f"python tools/infer.py --config configs/photo2cartoon.yaml --input_dir {input_path} --output_dir output"
-        elif task == "GPEN Face Enhancement":
-            cmd = f"python tools/infer.py --config configs/gpen.yaml --input_dir {input_path} --output_dir output"
-        else:
-            st.error("Unsupported task.")
-            st.stop()
-
-        with st.spinner("Running PaddleGAN..."):
-            subprocess.run(cmd, shell=True)
-
-        result_path = "output/result.jpg"
-        if os.path.exists(result_path):
-            st.image(Image.open(result_path), caption="Result", use_column_width=True)
-            with open(result_path, "rb") as f:
-                st.download_button("📥 Download Result", f.read(), "edited.jpg", "image/jpeg")
-        else:
-            st.error("No result found.")
+    if st.button("Generate Anime"):
+        img_np = np.array(image)
+        img_bgr = cv2.cvtColor(img_np, cv2.COLOR_RGB2BGR)
+        result = predictor.run(img_bgr)
+        result_rgb = cv2.cvtColor(result, cv2.COLOR_BGR2RGB)
+        st.image(result_rgb, caption="Anime Style", use_column_width=True)