Update app.py

app.py

@@ -1,42 +1,98 @@
 import streamlit as st
 from utils import transcribe_audio_segments, create_video_segments, generate_speech
-import tempfile
+from PIL import Image
 import os
+import cv2
+import numpy as np
+from io import BytesIO
+import tempfile
+from moviepy.editor import ImageSequenceClip
+from rembg import remove
+from basicsr.archs.rrdbnet_arch import RRDBNet
+from realesrgan import RealESRGANer
+
+# Helper function to apply cartoon effect
+def cartoonize(img):
+    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+    gray = cv2.medianBlur(gray, 5)
+    edges = cv2.adaptiveThreshold(
+        gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C,
+        cv2.THRESH_BINARY, 9, 9
+    )
+    color = cv2.bilateralFilter(img, 9, 300, 300)
+    cartoon = cv2.bitwise_and(color, color, mask=edges)
+    return cartoon
+
+# Helper function to apply edge detection
+def edge_detect(img):
+    return cv2.Canny(img, 100, 200)
+
+# Helper function to enhance face (upscale image)
+def enhance_image(img):
+    model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64,
+                   num_block=23, num_grow_ch=32, scale=4)
+    upsampler = RealESRGANer(
+        scale=4, model_path='realesrgan-x4plus.pth', model=model,
+        tile=0, tile_pad=10, pre_pad=0, half=False
+    )
+    _, _, output = upsampler.enhance(np.array(img), outscale=4)
+    return output
+
+# Save processed images
+def save_image(img, filename):
+    cv2.imwrite(filename, img)
+
+# Convert images to slideshow video
+def create_slideshow(images, out_path="slideshow.mp4"):
+    clip = ImageSequenceClip(images, fps=1)
+    clip.write_videofile(out_path, codec='libx264')
+
+# Streamlit UI
+st.set_page_config(layout="wide")
+st.title("🎨 Interactive Image Effects Studio")
+
+uploaded_files = st.file_uploader("Upload images", type=["jpg", "jpeg", "png"], accept_multiple_files=True)
+effects = st.multiselect("Select effects to apply", ["Cartoonize", "Edge Detection", "Background Removal", "Enhance/ Upscale"])
+
+effect_images = []
+
+if uploaded_files:
+    for uploaded_file in uploaded_files:
+        image = Image.open(uploaded_file).convert("RGB")
+        img_array = np.array(image)
+        original_img = cv2.cvtColor(img_array, cv2.COLOR_RGB2BGR)
+
+        processed_img = original_img.copy()
+        if "Cartoonize" in effects:
+            processed_img = cartoonize(processed_img)
+        if "Edge Detection" in effects:
+            processed_img = cv2.cvtColor(edge_detect(processed_img), cv2.COLOR_GRAY2BGR)
+        if "Background Removal" in effects:
+            processed_img = remove(Image.fromarray(cv2.cvtColor(processed_img, cv2.COLOR_BGR2RGB)))
+            processed_img = cv2.cvtColor(np.array(processed_img), cv2.COLOR_RGB2BGR)
+        if "Enhance/ Upscale" in effects:
+            processed_img = enhance_image(processed_img)
+
+        st.image(cv2.cvtColor(processed_img, cv2.COLOR_BGR2RGB), caption="Processed Image", use_column_width=True)
+
+        # Save processed
+        effect_images.append(cv2.cvtColor(processed_img, cv2.COLOR_BGR2RGB))
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as tmp_file:
+            save_image(processed_img, tmp_file.name)
+            with open(tmp_file.name, "rb") as file:
+                btn = st.download_button(
+                    label="Download Processed Image",
+                    data=file,
+                    file_name=os.path.basename(uploaded_file.name),
+                    mime="image/jpeg"
+                )
+
+    if st.button("Create Slideshow from Images"):
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".mp4") as tmp_video:
+            create_slideshow(effect_images, tmp_video.name)
+            with open(tmp_video.name, "rb") as file:
+                st.video(file)
+                st.download_button("Download Slideshow Video", file, file_name="slideshow.mp4")
+
 
-st.set_page_config(page_title="Voice Visualizer", layout="centered")
-st.title("🎥 Voice-to-Image Video Generator")
-st.markdown("Upload an audio file and images. The app transcribes the speech, matches keywords with images, and creates a video with images, audio, and translated subtitles.")
-
-audio_file = st.file_uploader("Upload audio (MP3/WAV)", type=["mp3", "wav"])
-images = st.file_uploader("Upload images", type=["jpg", "png", "jpeg"], accept_multiple_files=True)
-
-voice_to_voice = st.checkbox("🔁 Voice-to-Voice Response (AI replies in speech)")
-
-if st.button("Generate Video") and audio_file and images:
-    with tempfile.TemporaryDirectory() as tmpdir:
-        audio_path = os.path.join(tmpdir, audio_file.name)
-        with open(audio_path, "wb") as f:
-            f.write(audio_file.read())
-
-        image_paths = []
-        for img in images:
-            img_path = os.path.join(tmpdir, img.name)
-            with open(img_path, "wb") as f:
-                f.write(img.read())
-            image_paths.append(img_path)
-
-        st.info("Transcribing audio and splitting segments...")
-        segments = transcribe_audio_segments(audio_path)
-
-        st.info("Creating video...")
-        final_video = os.path.join(tmpdir, "video_output.mp4")
-        output = create_video_segments(segments, audio_path, image_paths, final_video)
-        st.success("🎉 Video created!")
-        st.video(output)
-
-        if voice_to_voice:
-            full_text = " ".join([s['text'] for s in segments])
-            st.info("Generating voice response...")
-            ai_response = f"Hello! Here's your visual story based on your audio: {full_text}"
-            speech_path = generate_speech(ai_response)
-            st.audio(speech_path)
+