Update app.py

app.py

@@ -1,119 +1,284 @@
-import gradio as gr
-import numpy as np
-from PIL import Image, ImageDraw, ImageFont
-import cv2
-from nudenet import NudeDetector
-
-# --- Konstanten ---
-DETECTION_MAX_DIM = 768
-PIXELS_PER_CM_ESTIMATE = 15
-MIN_CONFIDENCE = 0.45
-
-# --- NudeNet Detector ---
-detector = NudeDetector(inference_resolution=640)
-
-# --- Hilfsfunktionen ---
-def resize_for_detection(img_pil, max_dim):
-    if max(img_pil.width, img_pil.height) <= max_dim:
-        return img_pil, 1.0
-    ratio = max_dim / max(img_pil.width, img_pil.height)
-    new_size = (int(img_pil.width * ratio), int(img_pil.height * ratio))
-    resized = img_pil.resize(new_size, Image.Resampling.LANCZOS)
-    scale = 1 / ratio
-    return resized, scale
-
-def describe_breast_precise(crop_pil):
-    w,h = crop_pil.size
-    if w*h == 0:
-        return "Fehler: leeres Crop"
-    gray = cv2.cvtColor(np.array(crop_pil), cv2.COLOR_RGB2GRAY)
-    _, thresh = cv2.threshold(gray, 100, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
-    contours,_ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
-    nipple_detected = any(
-        40 < cv2.contourArea(c) < (w*h/4) and (p:=cv2.arcLength(c,True))>0 and
-        (4*np.pi*cv2.contourArea(c)/(p*p))>0.55
-        for c in contours
-    )
-    ratio = w/h
-    shape = "Breit" if ratio>1.15 else "Hoch" if ratio<0.85 else "Rund"
-    size = "klein" if w*h<28000 else "mittel" if w*h<75000 else "groß" if w*h<140000 else "sehr groß"
-    w_cm = round(w/PIXELS_PER_CM_ESTIMATE,1)
-    h_cm = round(h/PIXELS_PER_CM_ESTIMATE,1)
-    return f"Brust: {shape}, {size}, Nippel: {'Ja' if nipple_detected else 'Nein'}, {w_cm}x{h_cm}cm"
-
-def describe_vagina_precise(crop_pil):
-    w,h = crop_pil.size
-    if w*h == 0:
-        return "Fehler: leeres Crop"
-    gray = cv2.cvtColor(np.array(crop_pil), cv2.COLOR_RGB2GRAY)
-    hair_ratio = np.sum(cv2.inRange(gray, 35, 145) > 0) / (w*h)  # <--- korrigiert
-    shaved = "rasiert" if hair_ratio < 0.04 else "minimal" if hair_ratio < 0.13 else "Brazilian" if hair_ratio < 0.36 else "behaart"
-    ratio = w/h
-    area = w*h
-    if area < 18000:
-        form_desc = "Innie"
-    elif area > 65000 and ratio > 1.45:
-        form_desc = "Outie (Puff)"
-    elif ratio > 1.45:
-        form_desc = "Outie"
-    else:
-        form_desc = "Innie/Outie"
-    size = "winzig" if area<18000 else "klein" if area<38000 else "mittel" if area<65000 else "groß"
-    w_cm = round(w/PIXELS_PER_CM_ESTIMATE,1)
-    h_cm = round(h/PIXELS_PER_CM_ESTIMATE,1)
-    return f"Vagina: {form_desc}, {size}, {shaved}, {w_cm}x{h_cm}cm"
-
-# --- Bildverarbeitung ---
-def process_image(image):
+import streamlit as st
+from gradio_client import Client, handle_file
+import re
+import threading
+import time
+import requests
+import os
+import uuid
+import tempfile
+
+# ---------------------------
+# CONFIG
+# ---------------------------
+IMAGE_DIR = "data/images"
+os.makedirs(IMAGE_DIR, exist_ok=True)
+
+client_main = Client("selfit-camera/Omni-Image-Editor")
+client_process = Client("SLSLK/n8")
+
+# ---------------------------
+# SESSION
+# ---------------------------
+if "gallery" not in st.session_state:
+    st.session_state.gallery = []
+
+if "selected_image" not in st.session_state:
+    st.session_state.selected_image = None
+
+if "page" not in st.session_state:
+    st.session_state.page = "🖼️ Generieren"
+
+# ---------------------------
+# HELPERS
+# ---------------------------
+def extract_url(html):
+    match = re.search(r"src='([^']+)'", html)
+    return match.group(1) if match else None
+
+
+def save_image_from_url(url):
+    try:
+        r = requests.get(url)
+        if r.status_code != 200:
+            st.error(f"❌ Download Error HTTP {r.status_code}")
+            return None
+
+        path = os.path.join(IMAGE_DIR, f"{uuid.uuid4()}.png")
+        with open(path, "wb") as f:
+            f.write(r.content)
+
+        return path
+    except Exception as e:
+        st.error(f"❌ Save Error: {e}")
+        return None
+
+
+def prepare_image_for_api(input_image):
+    """
+    🔥 UNIVERSAL FIX:
+    - Upload → temp file
+    - Path → direkt
+    - URL → direkt
+    → immer handle_file(...)
+    """
+    try:
+        # 📥 Upload (Streamlit)
+        if hasattr(input_image, "getvalue"):
+            tmp = tempfile.NamedTemporaryFile(delete=False, suffix=".png")
+            tmp.write(input_image.getvalue())
+            tmp.close()
+            return handle_file(tmp.name)
+
+        # 📁 Lokaler Pfad oder URL
+        elif isinstance(input_image, str):
+            return handle_file(input_image)
+
+        else:
+            return None
+
+    except Exception as e:
+        st.error(f"❌ Prepare Error: {e}")
+        return None
+
+
+# ---------------------------
+# API FUNCTIONS
+# ---------------------------
+def generate_image(prompt):
+    try:
+        result = client_main.predict(
+            prompt=prompt,
+            aspect_ratio="16:9",
+            api_name="/text_to_image_interface"
+        )
+        return extract_url(result[0])
+    except Exception as e:
+        st.error(f"❌ Generate Error: {e}")
+        return None
+
+
+def edit_image(input_image, prompt):
+    try:
+        image_input = prepare_image_for_api(input_image)
+        if not image_input:
+            st.error("❌ Invalid image input")
+            return None
+
+        result = client_main.predict(
+            input_image=image_input,
+            prompt=prompt,
+            api_name="/edit_image_interface"
+        )
+
+        html = result[0]
+        return extract_url(html)
+
+    except Exception as e:
+        st.error(f"❌ Edit Error: {e}")
+        return None
+
+
+def process_image(input_image):
     try:
-        original_pil = Image.fromarray(image).convert("RGB") if isinstance(image,np.ndarray) else image.convert("RGB")
-        detection_pil, scale = resize_for_detection(original_pil, DETECTION_MAX_DIM)
-        detections = detector.detect(np.array(detection_pil))
-        draw = ImageDraw.Draw(original_pil)
-        font = ImageFont.load_default()
-        results_text = []
-
-        for det in detections:
-            label = det["class"]
-            score = det.get("score",0)
-            if score < MIN_CONFIDENCE:
-                continue
-            if label not in ["FEMALE_BREAST_EXPOSED","FEMALE_GENITALIA_EXPOSED"]:
-                continue
-            x,y,w,h = [int(v*scale) for v in det["box"]]
-            crop_pil = original_pil.crop((x,y,x+w,y+h))
-            if label=="FEMALE_BREAST_EXPOSED":
-                desc = describe_breast_precise(crop_pil)
-                color = (255,46,130)
-            else:
-                desc = describe_vagina_precise(crop_pil)
-                color = (138,43,226)
-            draw.rectangle([x,y,x+w,y+h],outline=color,width=4)
-            text_pos = (x,y-15 if y>15 else y+h)
-            draw.text(text_pos,desc,fill=color,font=font)
-            results_text.append(desc)
-
-        if not results_text:
-            draw.text((10,10),"Keine relevanten Bereiche erkannt.",fill=(255,0,0),font=font)
-
-        return np.array(original_pil)
+        image_input = prepare_image_for_api(input_image)
+        if not image_input:
+            st.error("❌ Invalid image input")
+            return None
+
+        result = client_process.predict(
+            image=image_input,
+            api_name="/process_image"
+        )
+
+        return result
 
     except Exception as e:
-        print(f"Fehler: {e}")
+        st.error(f"❌ Process Error: {e}")
         return None
 
-# --- Gradio App ---
-css = """
-body { background: #0f0f1a; color: #e0e0ff; }
-.gradio-container { max-width: 900px !important; margin: auto; }
-h1 { color: #ff2e82; text-align: center; }
-"""
-
-with gr.Blocks(css=css) as demo:
-    gr.Markdown("# 👙 Automatischer Nackt-Analyzer")
-    gr.Markdown("Lade ein Bild hoch und erhalte direkt das analysierte Bild mit Annotationen.")
-    input_image = gr.Image(type="numpy", label="Bild hochladen")
-    output_image = gr.Image(label="Analyse-Ergebnis")
-    input_image.change(fn=process_image, inputs=input_image, outputs=output_image)
-
-demo.launch()
+
+# ---------------------------
+# ASYNC
+# ---------------------------
+def run_async(func, *args):
+    result = {"done": False, "data": None}
+
+    def task():
+        result["data"] = func(*args)
+        result["done"] = True
+
+    threading.Thread(target=task).start()
+    return result
+
+
+def show_progress(job):
+    progress_bar = st.progress(0)
+    percent = 0
+
+    while not job["done"]:
+        percent += 5
+        if percent > 95:
+            percent = 95
+
+        progress_bar.progress(percent)
+        time.sleep(0.2)
+
+    progress_bar.progress(100)
+
+
+# ---------------------------
+# UI
+# ---------------------------
+st.set_page_config(layout="wide")
+st.title("🎨 Omni Image Studio")
+
+page = st.radio(
+    "Navigation",
+    ["🖼️ Generieren", "✨ Bearbeiten", "🧪 Analyse", "📚 Galerie"],
+    index=["🖼️ Generieren", "✨ Bearbeiten", "🧪 Analyse", "📚 Galerie"].index(st.session_state.page),
+    horizontal=True
+)
+
+st.session_state.page = page
+
+# ---------------------------
+# GENERATE
+# ---------------------------
+if page == "🖼️ Generieren":
+    prompt = st.text_area("Prompt")
+
+    if st.button("Generieren"):
+        job = run_async(generate_image, prompt)
+        show_progress(job)
+
+        url = job["data"]
+        if url:
+            path = save_image_from_url(url)
+            st.image(path)
+
+            st.session_state.gallery.append({
+                "path": path,
+                "prompt": prompt
+            })
+
+# ---------------------------
+# EDIT
+# ---------------------------
+elif page == "✨ Bearbeiten":
+    if st.session_state.selected_image:
+        st.image(st.session_state.selected_image)
+        input_image = st.session_state.selected_image
+    else:
+        input_image = st.file_uploader("Upload Image")
+
+    prompt = st.text_area("Edit Prompt")
+
+    if st.button("Bearbeiten"):
+        job = run_async(edit_image, input_image, prompt)
+        show_progress(job)
+
+        url = job["data"]
+        if url:
+            path = save_image_from_url(url)
+            st.image(path)
+
+            st.session_state.gallery.append({
+                "path": path,
+                "prompt": prompt
+            })
+
+# ---------------------------
+# ANALYSE
+# ---------------------------
+elif page == "🧪 Analyse":
+    if st.session_state.selected_image:
+        st.image(st.session_state.selected_image)
+        input_image = st.session_state.selected_image
+    else:
+        input_image = st.file_uploader("Upload Image")
+
+    if st.button("Analysieren"):
+        job = run_async(process_image, input_image)
+        show_progress(job)
+
+        result = job["data"]
+
+        if isinstance(result, str) and result.startswith("http"):
+            path = save_image_from_url(result)
+            st.image(path)
+
+            st.session_state.gallery.append({
+                "path": path,
+                "prompt": "Analyse"
+            })
+        else:
+            st.write(result)
+
+# ---------------------------
+# GALLERY
+# ---------------------------
+elif page == "📚 Galerie":
+    if not st.session_state.gallery:
+        st.info("Keine Bilder")
+    else:
+        cols = st.columns(3)
+
+        for i, item in enumerate(st.session_state.gallery):
+            with cols[i % 3]:
+                st.image(item["path"], caption=item["prompt"])
+
+                c1, c2 = st.columns(2)
+
+                if c1.button("✏️ Edit", key=f"e{i}"):
+                    st.session_state.selected_image = item["path"]
+                    st.session_state.page = "✨ Bearbeiten"
+                    st.rerun()
+
+                if c2.button("🧪 Analyse", key=f"a{i}"):
+                    st.session_state.selected_image = item["path"]
+                    st.session_state.page = "🧪 Analyse"
+                    st.rerun()
+
+        if st.button("🗑️ Clear"):
+            st.session_state.gallery = []