Update controlnet_facefix.py
Browse files- controlnet_facefix.py +138 -178
controlnet_facefix.py
CHANGED
|
@@ -1,13 +1,14 @@
|
|
| 1 |
-
# controlnet_facefix.py -
|
| 2 |
import torch
|
| 3 |
-
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
|
| 4 |
-
from PIL import Image
|
| 5 |
import time
|
| 6 |
import cv2
|
| 7 |
import numpy as np
|
|
|
|
| 8 |
|
| 9 |
print("="*60)
|
| 10 |
-
print("FACE-FIX: QUALITÄTSVERBESSERUNG
|
| 11 |
print("="*60)
|
| 12 |
|
| 13 |
_components_loaded = False
|
|
@@ -16,253 +17,212 @@ _controlnet_pose = None
|
|
| 16 |
_pipeline = None
|
| 17 |
|
| 18 |
def _initialize_components():
|
| 19 |
-
"""Lade
|
| 20 |
global _components_loaded, _controlnet_depth, _controlnet_pose
|
| 21 |
|
| 22 |
if _components_loaded:
|
| 23 |
return True
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
print("1. Lade ControlNet Depth (für 3D-Struktur)...")
|
| 27 |
-
_controlnet_depth = ControlNetModel.from_pretrained(
|
| 28 |
-
"lllyasviel/sd-controlnet-depth",
|
| 29 |
-
torch_dtype=torch.float16
|
| 30 |
-
)
|
| 31 |
-
print(" ✅ ControlNet Depth OK")
|
| 32 |
-
except Exception as e:
|
| 33 |
-
print(f" ❌ ControlNet Depth Fehler: {e}")
|
| 34 |
-
return False
|
| 35 |
|
| 36 |
try:
|
| 37 |
-
|
| 38 |
_controlnet_pose = ControlNetModel.from_pretrained(
|
| 39 |
"lllyasviel/sd-controlnet-openpose",
|
| 40 |
torch_dtype=torch.float16
|
| 41 |
)
|
| 42 |
-
print("
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
except Exception as e:
|
| 44 |
-
print(f"
|
| 45 |
return False
|
| 46 |
-
|
| 47 |
-
_components_loaded = True
|
| 48 |
-
print("✅ OPENPOSE + DEPTH GELADEN")
|
| 49 |
-
return True
|
| 50 |
|
| 51 |
-
def
|
| 52 |
-
"""
|
| 53 |
try:
|
| 54 |
img_array = np.array(image.convert("RGB"))
|
| 55 |
-
|
| 56 |
-
# Konvertiere zu Graustufen
|
| 57 |
gray = cv2.cvtColor(img_array, cv2.COLOR_RGB2GRAY)
|
| 58 |
|
| 59 |
-
#
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
# Adaptive Histogram Equalization für bessere Tiefenwahrnehmung
|
| 63 |
-
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
|
| 64 |
-
enhanced = clahe.apply(blurred)
|
| 65 |
-
|
| 66 |
-
# Invertiere für bessere Depth-Darstellung (helle = nah, dunkel = fern)
|
| 67 |
-
inverted = 255 - enhanced
|
| 68 |
|
| 69 |
-
#
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
#
|
| 79 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
|
| 81 |
-
def
|
| 82 |
-
"""
|
| 83 |
try:
|
| 84 |
img_array = np.array(image.convert("RGB"))
|
| 85 |
|
| 86 |
-
#
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
# 2.
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
# 3.
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
# Konvertiere zu RGB
|
| 107 |
-
pose_rgb = cv2.cvtColor(pose_edges, cv2.COLOR_GRAY2RGB)
|
| 108 |
-
|
| 109 |
-
return Image.fromarray(pose_rgb)
|
| 110 |
-
except Exception as e:
|
| 111 |
-
print(f"Pose Map Fehler: {e}")
|
| 112 |
-
# Fallback
|
| 113 |
-
edges = cv2.Canny(np.array(image.convert("RGB")), 50, 150)
|
| 114 |
-
return Image.fromarray(edges).convert("RGB")
|
| 115 |
|
| 116 |
def apply_facefix(image: Image.Image, prompt: str, negative_prompt: str, seed: int, model_id: str):
|
| 117 |
"""
|
| 118 |
-
QUALITÄTSVERBESSERUNG
|
| 119 |
|
| 120 |
-
|
| 121 |
-
1. OpenPose
|
| 122 |
-
2.
|
| 123 |
-
|
| 124 |
-
|
| 125 |
"""
|
| 126 |
-
print("\n" + "
|
| 127 |
-
print("
|
| 128 |
-
print(f"
|
| 129 |
-
print(
|
| 130 |
-
print("🔧"*50)
|
| 131 |
|
| 132 |
start_time = time.time()
|
| 133 |
|
| 134 |
-
# 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 135 |
if not _initialize_components():
|
| 136 |
-
|
| 137 |
-
return image
|
| 138 |
|
| 139 |
-
#
|
| 140 |
-
print("\n📐 Erstelle Control Maps...")
|
| 141 |
original_size = image.size
|
| 142 |
-
|
| 143 |
-
# Standardgröße für ControlNet
|
| 144 |
control_size = (512, 512)
|
| 145 |
resized_image = image.resize(control_size, Image.Resampling.LANCZOS)
|
| 146 |
|
| 147 |
-
#
|
| 148 |
-
|
| 149 |
-
|
| 150 |
-
# Pose Map (für Gesichts- und Körperstruktur)
|
| 151 |
-
pose_img = _extract_pose_map(resized_image)
|
| 152 |
-
|
| 153 |
-
# Optional: Debug speichern
|
| 154 |
-
depth_img.save("debug_depth_enhanced.png")
|
| 155 |
-
pose_img.save("debug_pose_enhanced.png")
|
| 156 |
|
| 157 |
-
#
|
| 158 |
global _pipeline
|
| 159 |
if _pipeline is None:
|
| 160 |
try:
|
| 161 |
-
print("🔄 Lade Pipeline
|
| 162 |
_pipeline = StableDiffusionControlNetPipeline.from_pretrained(
|
| 163 |
model_id,
|
| 164 |
-
controlnet=[_controlnet_pose
|
| 165 |
torch_dtype=torch.float16,
|
| 166 |
safety_checker=None,
|
| 167 |
requires_safety_checker=False,
|
| 168 |
)
|
| 169 |
|
| 170 |
-
# Optimierungen
|
| 171 |
_pipeline.enable_attention_slicing()
|
| 172 |
_pipeline.enable_vae_slicing()
|
| 173 |
|
| 174 |
-
print("✅ Pipeline
|
| 175 |
except Exception as e:
|
| 176 |
print(f"❌ Pipeline Fehler: {e}")
|
| 177 |
-
return
|
| 178 |
|
| 179 |
try:
|
| 180 |
-
# 4. Auf Device bewegen
|
| 181 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 182 |
print(f" Device: {device}")
|
| 183 |
pipeline = _pipeline.to(device)
|
| 184 |
|
| 185 |
-
#
|
| 186 |
-
#
|
|
|
|
|
|
|
| 187 |
|
| 188 |
-
|
| 189 |
-
|
| 190 |
-
|
| 191 |
-
|
| 192 |
-
|
| 193 |
-
|
| 194 |
-
# Negative Prompts für Qualitätsverbesserung
|
| 195 |
-
quality_negative = (
|
| 196 |
-
f"{negative_prompt}, "
|
| 197 |
-
"blurry, out of focus, lowres, low quality, jpeg artifacts, "
|
| 198 |
-
"compression artifacts, pixelated, grainy, noisy, "
|
| 199 |
-
"deformed, distorted, bad anatomy, mutation, ugly"
|
| 200 |
-
)
|
| 201 |
-
|
| 202 |
-
# 6. KRITISCHE PARAMETER FÜR INHALTSERHALTUNG:
|
| 203 |
-
# Hohe ControlNet-Stärken für maximale Kontrolle
|
| 204 |
-
# OpenPose: Hoch für Pose-Erhaltung
|
| 205 |
-
# Depth: Hoch für Strukturerhaltung
|
| 206 |
-
|
| 207 |
-
print("\n⚙️ Starte Qualitätsverbesserung mit Parametern:")
|
| 208 |
-
print(f" • OpenPose Strength: 0.95 (sehr hoch für Pose-Erhaltung)")
|
| 209 |
-
print(f" • Depth Strength: 0.85 (hoch für 3D-Struktur)")
|
| 210 |
-
print(f" • Steps: 25")
|
| 211 |
-
print(f" • CFG: 5.0 (niedrig für weniger 'Kreativität')")
|
| 212 |
|
| 213 |
result = pipeline(
|
| 214 |
-
prompt=
|
| 215 |
-
negative_prompt=
|
| 216 |
-
image=[pose_img
|
| 217 |
-
controlnet_conditioning_scale=[0.
|
| 218 |
-
num_inference_steps=
|
| 219 |
-
guidance_scale=
|
| 220 |
-
generator=torch.Generator(device).manual_seed(seed), #
|
| 221 |
height=512,
|
| 222 |
width=512,
|
| 223 |
).images[0]
|
| 224 |
|
| 225 |
-
#
|
| 226 |
if original_size != (512, 512):
|
| 227 |
result = result.resize(original_size, Image.Resampling.LANCZOS)
|
| 228 |
|
| 229 |
-
|
|
|
|
|
|
|
| 230 |
|
| 231 |
-
|
| 232 |
-
|
| 233 |
-
|
| 234 |
-
print(f"✅ Parameter: OpenPose=0.95, Depth=0.85")
|
| 235 |
-
print(f"✅ Gleicher Seed: {seed}")
|
| 236 |
-
print(f"✅ Größe: {original_size} → {result.size}")
|
| 237 |
-
print("✅"*50)
|
| 238 |
|
| 239 |
-
|
| 240 |
-
|
| 241 |
-
|
| 242 |
-
|
| 243 |
-
|
| 244 |
-
|
| 245 |
-
# Füge Beschriftung hinzu
|
| 246 |
-
from PIL import ImageDraw, ImageFont
|
| 247 |
-
draw = ImageDraw.Draw(comparison)
|
| 248 |
-
|
| 249 |
-
# Einfache Beschriftung
|
| 250 |
-
draw.text((10, 10), "Vorher", fill=(255, 255, 255))
|
| 251 |
-
draw.text((original_size[0] + 10, 10), "Nachher", fill=(255, 255, 255))
|
| 252 |
-
|
| 253 |
-
comparison.save("quality_improvement_comparison.png")
|
| 254 |
-
print(f"📊 Vergleich gespeichert: quality_improvement_comparison.png")
|
| 255 |
-
except Exception as e:
|
| 256 |
-
print(f"⚠️ Konnte Vergleich nicht speichern: {e}")
|
| 257 |
|
| 258 |
-
return
|
| 259 |
|
| 260 |
except Exception as e:
|
| 261 |
-
print(f"\n❌
|
| 262 |
-
|
| 263 |
-
traceback.print_exc()
|
| 264 |
-
return image
|
| 265 |
|
| 266 |
print("="*60)
|
| 267 |
-
print("FACE-FIX
|
| 268 |
print("="*60)
|
|
|
|
| 1 |
+
# controlnet_facefix.py - PURE QUALITY ENHANCEMENT WITH MINIMAL CHANGE
|
| 2 |
import torch
|
| 3 |
+
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, AutoencoderKL
|
| 4 |
+
from PIL import Image, ImageFilter, ImageEnhance
|
| 5 |
import time
|
| 6 |
import cv2
|
| 7 |
import numpy as np
|
| 8 |
+
from torchvision import transforms
|
| 9 |
|
| 10 |
print("="*60)
|
| 11 |
+
print("FACE-FIX: REINE QUALITÄTSVERBESSERUNG - MINIMALE ÄNDERUNG")
|
| 12 |
print("="*60)
|
| 13 |
|
| 14 |
_components_loaded = False
|
|
|
|
| 17 |
_pipeline = None
|
| 18 |
|
| 19 |
def _initialize_components():
|
| 20 |
+
"""Lade nur notwendige Komponenten"""
|
| 21 |
global _components_loaded, _controlnet_depth, _controlnet_pose
|
| 22 |
|
| 23 |
if _components_loaded:
|
| 24 |
return True
|
| 25 |
+
|
| 26 |
+
print("⚠️ Lade nur OpenPose (Depth wird deaktiviert)...")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
|
| 28 |
try:
|
| 29 |
+
# NUR OPENPOSE - Depth verändert zu viel
|
| 30 |
_controlnet_pose = ControlNetModel.from_pretrained(
|
| 31 |
"lllyasviel/sd-controlnet-openpose",
|
| 32 |
torch_dtype=torch.float16
|
| 33 |
)
|
| 34 |
+
print("✅ OpenPose geladen")
|
| 35 |
+
|
| 36 |
+
# Depth wird NICHT geladen - es verändert den Hintergrund zu stark
|
| 37 |
+
_controlnet_depth = None
|
| 38 |
+
|
| 39 |
+
_components_loaded = True
|
| 40 |
+
return True
|
| 41 |
except Exception as e:
|
| 42 |
+
print(f"❌ Fehler: {e}")
|
| 43 |
return False
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
|
| 45 |
+
def _extract_precise_pose(image):
|
| 46 |
+
"""SEHR PRÄZISE Pose-Extraktion nur für Gesicht"""
|
| 47 |
try:
|
| 48 |
img_array = np.array(image.convert("RGB"))
|
|
|
|
|
|
|
| 49 |
gray = cv2.cvtColor(img_array, cv2.COLOR_RGB2GRAY)
|
| 50 |
|
| 51 |
+
# EXTREM NIEDRIGE Thresholds für minimale Kanten
|
| 52 |
+
edges = cv2.Canny(gray, 15, 45) # Nur feinste Kanten
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
+
# Face detection für Fokus
|
| 55 |
+
face_cascade = cv2.CascadeClassifier(
|
| 56 |
+
cv2.data.haarcascades + 'haarcascade_frontalface_default.xml'
|
| 57 |
+
)
|
| 58 |
+
faces = face_cascade.detectMultiScale(gray, 1.1, 4)
|
| 59 |
+
|
| 60 |
+
# Erstelle leere Pose Map
|
| 61 |
+
pose_map = np.zeros_like(img_array)
|
| 62 |
+
|
| 63 |
+
# Nur Gesichtskanten einfügen
|
| 64 |
+
if len(faces) > 0:
|
| 65 |
+
for (x, y, w, h) in faces:
|
| 66 |
+
# Extrahiere Gesichtsregion
|
| 67 |
+
face_region = edges[y:y+h, x:x+w]
|
| 68 |
+
# Nur 10% der stärksten Kanten behalten
|
| 69 |
+
threshold = np.percentile(face_region[face_region > 0], 90)
|
| 70 |
+
face_region[face_region < threshold] = 0
|
| 71 |
+
pose_map[y:y+h, x:x+w, 0] = face_region
|
| 72 |
+
else:
|
| 73 |
+
# Falls kein Gesicht erkannt, minimale Kanten
|
| 74 |
+
pose_map[..., 0] = edges * 0.3 # Noch schwächer
|
| 75 |
+
|
| 76 |
+
return Image.fromarray(pose_map)
|
| 77 |
+
except:
|
| 78 |
+
# Fallback: minimale Kanten
|
| 79 |
+
gray = cv2.cvtColor(np.array(image.convert("RGB")), cv2.COLOR_RGB2GRAY)
|
| 80 |
+
edges = cv2.Canny(gray, 10, 30) * 0.2 # Sehr schwach
|
| 81 |
+
return Image.fromarray(edges).convert("RGB")
|
| 82 |
|
| 83 |
+
def _apply_face_enhancement(image):
|
| 84 |
+
"""EINFACHE Face Enhancement ohne AI"""
|
| 85 |
try:
|
| 86 |
img_array = np.array(image.convert("RGB"))
|
| 87 |
|
| 88 |
+
# 1. Scharfe Kanten (nur leicht)
|
| 89 |
+
sharpened = cv2.filter2D(img_array, -1,
|
| 90 |
+
np.array([[-0.5, -0.5, -0.5],
|
| 91 |
+
[-0.5, 5.0, -0.5],
|
| 92 |
+
[-0.5, -0.5, -0.5]]) / 3.0)
|
| 93 |
+
|
| 94 |
+
# 2. Leichter De-Noise
|
| 95 |
+
denoised = cv2.fastNlMeansDenoisingColored(sharpened, None, 3, 3, 7, 21)
|
| 96 |
+
|
| 97 |
+
# 3. Kontrast leicht erhöhen
|
| 98 |
+
lab = cv2.cvtColor(denoised, cv2.COLOR_RGB2LAB)
|
| 99 |
+
l, a, b = cv2.split(lab)
|
| 100 |
+
clahe = cv2.createCLAHE(clipLimit=1.0, tileGridSize=(8,8))
|
| 101 |
+
l = clahe.apply(l)
|
| 102 |
+
enhanced = cv2.merge([l, a, b])
|
| 103 |
+
enhanced = cv2.cvtColor(enhanced, cv2.COLOR_LAB2RGB)
|
| 104 |
+
|
| 105 |
+
return Image.fromarray(enhanced)
|
| 106 |
+
except:
|
| 107 |
+
return image
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
|
| 109 |
def apply_facefix(image: Image.Image, prompt: str, negative_prompt: str, seed: int, model_id: str):
|
| 110 |
"""
|
| 111 |
+
SUPER-SUBTILE QUALITÄTSVERBESSERUNG
|
| 112 |
|
| 113 |
+
Strategie:
|
| 114 |
+
1. NUR OpenPose (kein Depth - das verändert zu viel)
|
| 115 |
+
2. SEHR niedrige ControlNet-Stärke
|
| 116 |
+
3. Fast kein CFG Scale
|
| 117 |
+
4. Identischer Prompt
|
| 118 |
"""
|
| 119 |
+
print("\n" + "🎯"*50)
|
| 120 |
+
print("SUBTILE QUALITÄTSVERBESSERUNG")
|
| 121 |
+
print(f" Größe: {image.size}")
|
| 122 |
+
print("🎯"*50)
|
|
|
|
| 123 |
|
| 124 |
start_time = time.time()
|
| 125 |
|
| 126 |
+
# OPTION 1: Einfache non-AI Verbesserung (empfohlen)
|
| 127 |
+
print("\n⚡ OPTION 1: Einfache non-AI Verbesserung...")
|
| 128 |
+
enhanced = _apply_face_enhancement(image)
|
| 129 |
+
|
| 130 |
+
# Optional: AI-Verbesserung nur wenn nötig
|
| 131 |
+
use_ai_enhancement = False # Auf False setzen für minimale Änderung
|
| 132 |
+
|
| 133 |
+
if not use_ai_enhancement:
|
| 134 |
+
duration = time.time() - start_time
|
| 135 |
+
print(f"✅ Non-AI Verbesserung in {duration:.1f}s")
|
| 136 |
+
return enhanced
|
| 137 |
+
|
| 138 |
+
# OPTION 2: Minimale AI-Verbesserung (falls gewünscht)
|
| 139 |
+
print("⚠️ Starte MINIMALE AI-Verbesserung...")
|
| 140 |
+
|
| 141 |
if not _initialize_components():
|
| 142 |
+
return enhanced
|
|
|
|
| 143 |
|
| 144 |
+
# Control Map vorbereiten
|
|
|
|
| 145 |
original_size = image.size
|
|
|
|
|
|
|
| 146 |
control_size = (512, 512)
|
| 147 |
resized_image = image.resize(control_size, Image.Resampling.LANCZOS)
|
| 148 |
|
| 149 |
+
# MINIMALE Pose Map
|
| 150 |
+
pose_img = _extract_precise_pose(resized_image)
|
| 151 |
+
pose_img.save("debug_minimal_pose.png")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 152 |
|
| 153 |
+
# Pipeline (nur falls nicht geladen)
|
| 154 |
global _pipeline
|
| 155 |
if _pipeline is None:
|
| 156 |
try:
|
| 157 |
+
print("🔄 Lade Pipeline...")
|
| 158 |
_pipeline = StableDiffusionControlNetPipeline.from_pretrained(
|
| 159 |
model_id,
|
| 160 |
+
controlnet=[_controlnet_pose], # NUR OpenPose!
|
| 161 |
torch_dtype=torch.float16,
|
| 162 |
safety_checker=None,
|
| 163 |
requires_safety_checker=False,
|
| 164 |
)
|
| 165 |
|
|
|
|
| 166 |
_pipeline.enable_attention_slicing()
|
| 167 |
_pipeline.enable_vae_slicing()
|
| 168 |
|
| 169 |
+
print("✅ Pipeline geladen")
|
| 170 |
except Exception as e:
|
| 171 |
print(f"❌ Pipeline Fehler: {e}")
|
| 172 |
+
return enhanced
|
| 173 |
|
| 174 |
try:
|
|
|
|
| 175 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 176 |
print(f" Device: {device}")
|
| 177 |
pipeline = _pipeline.to(device)
|
| 178 |
|
| 179 |
+
# KRITISCHE ÄNDERUNGEN:
|
| 180 |
+
# 1. GLEICHER PROMPT wie ursprünglich
|
| 181 |
+
# 2. SEHR niedrige ControlNet-Stärke
|
| 182 |
+
# 3. FAST KEIN CFG
|
| 183 |
|
| 184 |
+
print("\n⚙️ EXTREM SUBTILE PARAMETER:")
|
| 185 |
+
print(" • OpenPose Strength: 0.3 (SEHR NIEDRIG)")
|
| 186 |
+
print(" • Steps: 15 (wenig)")
|
| 187 |
+
print(" • CFG: 2.0 (fast kein Guidance)")
|
| 188 |
+
print(" • Gleicher Seed")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 189 |
|
| 190 |
result = pipeline(
|
| 191 |
+
prompt=prompt, # WICHTIG: GLEICHER PROMPT!
|
| 192 |
+
negative_prompt=f"{negative_prompt}, deformed, blurry",
|
| 193 |
+
image=[pose_img], # Nur Pose
|
| 194 |
+
controlnet_conditioning_scale=[0.3], # EXTREM NIEDRIG
|
| 195 |
+
num_inference_steps=15, # WENIG Steps
|
| 196 |
+
guidance_scale=2.0, # FAST KEIN CFG
|
| 197 |
+
generator=torch.Generator(device).manual_seed(seed + 100), # Leicht anderer Seed
|
| 198 |
height=512,
|
| 199 |
width=512,
|
| 200 |
).images[0]
|
| 201 |
|
| 202 |
+
# Zurück auf Originalgröße
|
| 203 |
if original_size != (512, 512):
|
| 204 |
result = result.resize(original_size, Image.Resampling.LANCZOS)
|
| 205 |
|
| 206 |
+
# 50/50 Blend mit Original für noch weniger Änderung
|
| 207 |
+
result_array = np.array(result).astype(float)
|
| 208 |
+
original_array = np.array(image).astype(float)
|
| 209 |
|
| 210 |
+
# 70% Original, 30% AI-result
|
| 211 |
+
blended = (original_array * 0.7 + result_array * 0.3).astype(np.uint8)
|
| 212 |
+
final_result = Image.fromarray(blended)
|
|
|
|
|
|
|
|
|
|
|
|
|
| 213 |
|
| 214 |
+
duration = time.time() - start_time
|
| 215 |
+
print(f"\n✅ SUBTILE VERBESSERUNG in {duration:.1f}s")
|
| 216 |
+
print(f" • 70% Original, 30% AI")
|
| 217 |
+
print(f" • OpenPose: 0.3")
|
| 218 |
+
print(f" • CFG: 2.0")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 219 |
|
| 220 |
+
return final_result
|
| 221 |
|
| 222 |
except Exception as e:
|
| 223 |
+
print(f"\n❌ AI-Verbesserung fehlgeschlagen: {e}")
|
| 224 |
+
return enhanced
|
|
|
|
|
|
|
| 225 |
|
| 226 |
print("="*60)
|
| 227 |
+
print("FACE-FIX: REINE QUALITÄTSVERBESSERUNG")
|
| 228 |
print("="*60)
|