Muliple files updated

CodeFormer/basicsr/train.py

@@ -12,8 +12,7 @@ from basicsr.data import build_dataloader, build_dataset
 from basicsr.data.data_sampler import EnlargedSampler
 from basicsr.data.prefetch_dataloader import CPUPrefetcher, CUDAPrefetcher
 from basicsr.models import build_model
-from basicsr.utils import (MessageLogger, check_resume, get_env_info, get_root_logger, init_tb_logger,
-                           init_wandb_logger, make_exp_dirs, mkdir_and_rename, set_random_seed)
+from basicsr.utils import (MessageLogger, check_resume, get_env_info, get_root_logger, init_tb_logger,init_wandb_logger, make_exp_dirs, mkdir_and_rename, set_random_seed)
 from basicsr.utils.dist_util import get_dist_info, init_dist
 from basicsr.utils.options import dict2str, parse
 

_res/_custom.css

@@ -86,7 +86,7 @@ body>gradio-app.has-bg-image::before {
 gradio-app .gradio-container {
     max-width: 80% !important;
 
-    & div.main-row {
+    & div.row-main {
         background-color: var(--neutral-900) !important;
         border-right-width: 0px !important;
         border-bottom-width: 0px !important;

app.py

@@ -16,6 +16,8 @@ from basicsr.utils.realesrgan_utils import RealESRGANer
 
 from basicsr.utils.registry import ARCH_REGISTRY
 
+from modules import weights_downloads
+
 # Get torch device
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
@@ -38,41 +40,23 @@ theme = gr.themes.Soft(
 
 os.system("pip freeze")
 
-pretrain_model_url = {
-    'codeformer': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth',
-    'detection': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/detection_Resnet50_Final.pth',
-    'parsing': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/parsing_parsenet.pth',
-    'realesrgan': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/RealESRGAN_x2plus.pth'
-}
-# download weights
-if not os.path.exists('CodeFormer/weights/CodeFormer/codeformer.pth'):
-    load_file_from_url(url=pretrain_model_url['codeformer'], model_dir='CodeFormer/weights/CodeFormer', progress=True, file_name=None)
-if not os.path.exists('CodeFormer/weights/facelib/detection_Resnet50_Final.pth'):
-    load_file_from_url(url=pretrain_model_url['detection'], model_dir='CodeFormer/weights/facelib', progress=True, file_name=None)
-if not os.path.exists('CodeFormer/weights/facelib/parsing_parsenet.pth'):
-    load_file_from_url(url=pretrain_model_url['parsing'], model_dir='CodeFormer/weights/facelib', progress=True, file_name=None)
-if not os.path.exists('CodeFormer/weights/realesrgan/RealESRGAN_x2plus.pth'):
-    load_file_from_url(url=pretrain_model_url['realesrgan'], model_dir='CodeFormer/weights/realesrgan', progress=True, file_name=None)
-
-# download images
-torch.hub.download_url_to_file(
-    'https://replicate.com/api/models/sczhou/codeformer/files/fa3fe3d1-76b0-4ca8-ac0d-0a925cb0ff54/06.png',
-    '01.png')
-torch.hub.download_url_to_file(
-    'https://replicate.com/api/models/sczhou/codeformer/files/a1daba8e-af14-4b00-86a4-69cec9619b53/04.jpg',
-    '02.jpg')
-torch.hub.download_url_to_file(
-    'https://replicate.com/api/models/sczhou/codeformer/files/542d64f9-1712-4de7-85f7-3863009a7c3d/03.jpg',
-    '03.jpg')
-torch.hub.download_url_to_file(
-    'https://replicate.com/api/models/sczhou/codeformer/files/a11098b0-a18a-4c02-a19a-9a7045d68426/010.jpg',
-    '04.jpg')
-torch.hub.download_url_to_file(
-    'https://replicate.com/api/models/sczhou/codeformer/files/7cf19c2c-e0cf-4712-9af8-cf5bdbb8d0ee/012.jpg',
-    '05.jpg')
-torch.hub.download_url_to_file(
-    'https://raw.githubusercontent.com/sczhou/CodeFormer/master/inputs/cropped_faces/0729.png',
-    '06.png')
+# pretrain_model_url = {
+#     'codeformer': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth',
+#     'detection': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/detection_Resnet50_Final.pth',
+#     'parsing': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/parsing_parsenet.pth',
+#     'realesrgan': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/RealESRGAN_x2plus.pth'
+# }
+# # download weights
+# if not os.path.exists('CodeFormer/weights/CodeFormer/codeformer.pth'):
+#     load_file_from_url(url=pretrain_model_url['codeformer'], model_dir='CodeFormer/weights/CodeFormer', progress=True, file_name=None)
+# if not os.path.exists('CodeFormer/weights/facelib/detection_Resnet50_Final.pth'):
+#     load_file_from_url(url=pretrain_model_url['detection'], model_dir='CodeFormer/weights/facelib', progress=True, file_name=None)
+# if not os.path.exists('CodeFormer/weights/facelib/parsing_parsenet.pth'):
+#     load_file_from_url(url=pretrain_model_url['parsing'], model_dir='CodeFormer/weights/facelib', progress=True, file_name=None)
+# if not os.path.exists('CodeFormer/weights/realesrgan/RealESRGAN_x2plus.pth'):
+#     load_file_from_url(url=pretrain_model_url['realesrgan'], model_dir='CodeFormer/weights/realesrgan', progress=True, file_name=None)
+
+weights_downloads()
 
 def imread(img_path):
     img = cv2.imread(img_path)
@@ -117,18 +101,20 @@ codeformer_net.eval()
 
 os.makedirs('output', exist_ok=True)
 
-def inference(image, face_align, background_enhance, face_upsample, upscale, codeformer_fidelity):
+def inference(image, inf_options, upscale, codeformer_fidelity):
     """Run a single prediction on the model"""
     try: # global try
         # take the default setting for the demo
+        # face_align, background_enhance, face_upsample, 
         only_center_face = False
         draw_box = False
         detection_model = "retinaface_resnet50"
 
-        print('Inp:', image, background_enhance, face_upsample, upscale, codeformer_fidelity)
-        face_align = face_align if face_align is not None else True
-        background_enhance = background_enhance if background_enhance is not None else True
-        face_upsample = face_upsample if face_upsample is not None else True
+        # "Gesicht ausrichten", "Hintergrund verbessern", "Gesicht Hochskalieren"
+        print('Inp:', image, inf_options, upscale, codeformer_fidelity)
+        face_align = False if "Gesicht ausrichten" not in inf_options else True
+        background_enhance = False if "Hintergrund verbessern" not in inf_options else True
+        face_upsample = face_upsample if "Gesicht Hochskalieren" not in inf_options else True
         upscale = upscale if (upscale is not None and upscale > 0) else 2
 
         has_aligned = not face_align
@@ -240,22 +226,23 @@ title = "Photo restoration and enhancement by CodeFormer"
 description = ""
 article = ""
 
-demo = gr.Interface(
-    inference, [
-        gr.Image(type="filepath", label="Input"),
-        gr.Checkbox(value=True, label="Pre_Face_Align"),
-        gr.Checkbox(value=True, label="Background_Enhance"),
-        gr.Checkbox(value=True, label="Face_Upsample"),
-        gr.Number(value=2, label="Rescaling_Factor (up to 4)"),
-        gr.Slider(0, 1, value=0.5, step=0.01, label='Codeformer_Fidelity (0 for better quality, 1 for better identity)')
-    ], [
-        gr.Image(type="numpy", label="Output")
-    ],
-    title=title,
-    description=description,
-    concurrency_limit=2,
-    theme=theme
-    )
-
-DEBUG = os.getenv('DEBUG') == '1'
-demo.launch(debug=DEBUG)
+with gr.Blocks(theme=theme, title=title, css=custom_css, js=custom_js) as demo_photo_enhance:
+    with gr.Row(elem_classes="row-header"):
+        gr.Markdown("""""")
+    with gr.Row(elem_classes="row-main"):
+        with gr.Column(scale=1):
+            inp_image = gr.Image(type="filepath", label="Input")
+            inp_lang = gr.Dropdown(["English", "Deutsch"], value="Deutsch", label="Sprache", interactive=True)
+            inf_options = gr.CheckboxGroup(["Gesicht ausrichten", "Hintergrund verbessern", "Gesicht Hochskalieren",], label="Optionen", info="Where are they from?", interactive=True)
+            inp_scale = gr.Slider(0, 4, value=2, step=1, label="Foto Hochskalieren", info="Du kannst das Foto bis zum Faktor 4 hochskalieren")
+            inp_factor = gr.Slider(0, 1, value=0.5, step=0.01, label='Verbesserungsfaktor', info='zu 0 verstärkt die Ausgabe, zu 1 erhält die Identität')
+            run_btn = gr.Button("Los")
+        with gr.Column(scale=2):
+            output_image = gr.Image(type="numpy", label="Ergebnis")
+
+
+    run_btn.click(fn=inference, inputs=[inp_image, inp_lang, inp_scale], outputs=[out_audio])
+
+if __name__ == "__main__":
+    DEBUG = os.getenv('DEBUG') == '1'
+    demo_photo_enhance.launch(debug=DEBUG)

modules/weights_downloads.py

@@ -0,0 +1,20 @@
+
+def download_wights():
+    
+    # MARK: PRETRAINED MODEL URLS
+    pretrain_model_url = {
+        'codeformer': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth',
+        'detection': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/detection_Resnet50_Final.pth',
+        'parsing': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/parsing_parsenet.pth',
+        'realesrgan': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/RealESRGAN_x2plus.pth'
+    }
+    
+    # MARK: WEIGHT URLS
+    if not os.path.exists('CodeFormer/weights/CodeFormer/codeformer.pth'):
+        load_file_from_url(url=pretrain_model_url['codeformer'], model_dir='CodeFormer/weights/CodeFormer', progress=True, file_name=None)
+    if not os.path.exists('CodeFormer/weights/facelib/detection_Resnet50_Final.pth'):
+        load_file_from_url(url=pretrain_model_url['detection'], model_dir='CodeFormer/weights/facelib', progress=True, file_name=None)
+    if not os.path.exists('CodeFormer/weights/facelib/parsing_parsenet.pth'):
+        load_file_from_url(url=pretrain_model_url['parsing'], model_dir='CodeFormer/weights/facelib', progress=True, file_name=None)
+    if not os.path.exists('CodeFormer/weights/realesrgan/RealESRGAN_x2plus.pth'):
+        load_file_from_url(url=pretrain_model_url['realesrgan'], model_dir='CodeFormer/weights/realesrgan', progress=True, file_name=None)

requirements.txt

@@ -14,7 +14,10 @@ torchvision
 tqdm
 yapf
 lpips
-gdown # supports downloading the large file from Google Drive
+gdown
+gradio_imageslider
+gradio_modal
+# supports downloading the large file from Google Drive
 # cmake
 # dlib
 # conda install -c conda-forge dlib