Update controlnet_module.py

controlnet_module.py

@@ -143,73 +143,67 @@ class ControlNetProcessor:
             return self.pipe_canny
 
     def generate_with_controlnet(
-        self, image, prompt, negative_prompt,
-        steps, guidance_scale, controlnet_strength,
-        progress=None, keep_environment=False
-    ):
-        """Generiert Bild mit ControlNet und Fortschrittsanzeige"""
-        try:
-            # --- KORREKTE LOGIK ---
-            if keep_environment:
-                # UMGEBUNG BEIBEHALTEN, PERSON ÄNDERN
-                controlnet_type = "canny"  # ✅ Canny behält Umgebung
-                print("🎯 ControlNet Modus: Umgebung beibehalten (Canny Edge)")
-                conditioning_image = self.extract_canny_edges(image)
-            else:
-                # PERSON BEIBEHALTEN, UMGEBUNG ÄNDERN  
-                controlnet_type = "openpose"  # ✅ OpenPose behält Person
-                print("🎯 ControlNet Modus: Person beibehalten (OpenPose)")
-                conditioning_image = self.extract_pose(image)
-
-            pipe = self.load_controlnet_pipeline(controlnet_type)
-
-            # Zufälliger Seed
-            seed = random.randint(0, 2**32 - 1)
-            generator = torch.Generator(device=self.device).manual_seed(seed)
-            print(f"ControlNet Seed: {seed}")
-
-            # Fortschritt-Callback
-            callback = ControlNetProgressCallback(progress, int(steps)) if progress is not None else None
-
-            print("🔄 ControlNet: Starte Pipeline...")
-
-            # ControlNet Generierung
-            result = pipe(
-                prompt=prompt,
-                image=conditioning_image,
-                negative_prompt=negative_prompt,
-                num_inference_steps=int(steps),
-                guidance_scale=guidance_scale,
-                generator=generator,
-                controlnet_conditioning_scale=controlnet_strength,
-                height=512,
-                width=512,
-                output_type="pil",
-                callback_on_step_end=callback,
-                callback_on_step_end_tensor_inputs=[],
-            )
-
-            # Debug-Ausgabe Scheduler Steps
-            try:
-                scheduler = pipe.scheduler
-                if hasattr(scheduler, "timesteps"):
-                    actual_steps = len(scheduler.timesteps)
-                    print(f"🎯 CONTROLNET TATSÄCHLICHE STEPS: {actual_steps} (von {steps} angefordert)")
-            except Exception as e:
-                print(f"⚠️ Konnte ControlNet Scheduler-Info nicht auslesen: {e}")
-
-            print("✅ ControlNet abgeschlossen!")
-            
-            # ZWEI Werte zurückgeben
-            return result.images[0], conditioning_image
-
-        except Exception as e:
-            print(f"❌ Fehler in ControlNet: {e}")
-            import traceback
-            traceback.print_exc()
-            error_image = image.convert("RGB").resize((512, 512))
-            return error_image, error_image
-
+    self, image, prompt, negative_prompt,
+    steps, guidance_scale, controlnet_strength,
+    progress=None, keep_environment=False
+):
+    """Generiert Bild mit ControlNet und Fortschrittsanzeige"""
+    try:
+        # --- KORREKTE LOGIK ---
+        if keep_environment:
+            # UMGEBUNG BEIBEHALTEN, PERSON ÄNDERN
+            controlnet_type = "canny"  # ✅ Canny behält Umgebung
+            print("🎯 ControlNet Modus: Umgebung beibehalten (Canny Edge)")
+            conditioning_image = self.extract_canny_edges(image)
+            inpaint_input = image  # ✅ ORIGINALBILD für Inpaint!
+        else:
+            # PERSON BEIBEHALTEN, UMGEBUNG ÄNDERN  
+            controlnet_type = "openpose"  # ✅ OpenPose behält Person
+            print("🎯 ControlNet Modus: Person beibehalten (OpenPose)")
+            conditioning_image = self.extract_pose(image)
+            inpaint_input = conditioning_image  # ✅ POSE-MAP für Inpaint
+
+        pipe = self.load_controlnet_pipeline(controlnet_type)
+
+        # Zufälliger Seed
+        seed = random.randint(0, 2**32 - 1)
+        generator = torch.Generator(device=self.device).manual_seed(seed)
+        print(f"ControlNet Seed: {seed}")
+
+        # Fortschritt-Callback
+        callback = ControlNetProgressCallback(progress, int(steps)) if progress is not None else None
+
+        print("🔄 ControlNet: Starte Pipeline...")
+
+        # ControlNet Generierung
+        result = pipe(
+            prompt=prompt,
+            image=conditioning_image,
+            negative_prompt=negative_prompt,
+            num_inference_steps=int(steps),
+            guidance_scale=guidance_scale,
+            generator=generator,
+            controlnet_conditioning_scale=controlnet_strength,
+            height=512,
+            width=512,
+            output_type="pil",
+            callback_on_step_end=callback,
+            callback_on_step_end_tensor_inputs=[],
+        )
+
+        print("✅ ControlNet abgeschlossen!")
+        
+        # DREI Werte zurückgeben
+        return result.images[0], conditioning_image, inpaint_input
+
+    except Exception as e:
+        print(f"❌ Fehler in ControlNet: {e}")
+        import traceback
+        traceback.print_exc()
+        error_image = image.convert("RGB").resize((512, 512))
+        return error_image, error_image, error_image        
+
+   
     def prepare_inpaint_input(self, image, keep_environment=False):
         """
         Bereitet das Input-Bild für Inpaint vor