Skip target audio (#656)

2025-12-06 18:08:29 +00:00 · 2023-06-29 12:43:05 +02:00 · 2023-06-29 12:43:05 +02:00 · eca4f0f127
commit eca4f0f127
parent c6a138701a
6 changed files with 20 additions and 19 deletions
--- a/README.md
+++ b/README.md
@ -36,14 +36,14 @@ options:
  -t TARGET_PATH, --target TARGET_PATH                     select an target image or video
  -o OUTPUT_PATH, --output OUTPUT_PATH                     select output file or directory
  --frame-processor FRAME_PROCESSOR [FRAME_PROCESSOR ...]  frame processors (choices: face_swapper, face_enhancer, ...)
-  --keep-fps                                               keep original fps
-  --keep-audio                                             keep original audio
+  --keep-fps                                               keep target fps
  --keep-frames                                            keep temporary frames
+  --skip-audio                                             skip target audio
  --many-faces                                             process every face
  --video-encoder {libx264,libx265,libvpx-vp9}             adjust output video encoder
  --video-quality [0-51]                                   adjust output video quality
  --max-memory MAX_MEMORY                                  maximum amount of RAM in GB
-  --execution-provider {cpu} [{cpu} ...]                   available execution provider (choices: cpu, ...)
+  --execution-provider {coreml,cpu} [{coreml,cpu} ...]     available execution provider (choices: cpu, ...)
  --execution-threads EXECUTION_THREADS                    number of execution threads
  -v, --version                                            show program's version number and exit
 ```
--- a/requirements-ci.txt
+++ b/requirements-ci.txt
@ -4,7 +4,7 @@ onnx==1.14.0
 insightface==0.7.3
 psutil==5.9.5
 tk==0.1.0
-customtkinter==5.1.3
+customtkinter==5.2.0
 torch==2.0.1
 torchvision==0.15.2
 onnxruntime==1.15.0
--- a/requirements.txt
+++ b/requirements.txt
@ -6,7 +6,7 @@ onnx==1.14.0
 insightface==0.7.3
 psutil==5.9.5
 tk==0.1.0
-customtkinter==5.1.3
+customtkinter==5.2.0
 pillow==9.5.0
 torch==2.0.1+cu118; sys_platform != 'darwin'
 torch==2.0.1; sys_platform == 'darwin'
--- a/roop/core.py
+++ b/roop/core.py
@ -38,10 +38,10 @@ def parse_args() -> None:
    program.add_argument('-t', '--target', help='select an target image or video', dest='target_path')
    program.add_argument('-o', '--output', help='select output file or directory', dest='output_path')
    program.add_argument('--frame-processor', help='frame processors (choices: face_swapper, face_enhancer, ...)', dest='frame_processor', default=['face_swapper'], nargs='+')
-    program.add_argument('--keep-fps', help='keep original fps', dest='keep_fps', action='store_true', default=False)
-    program.add_argument('--keep-audio', help='keep original audio', dest='keep_audio', action='store_true', default=True)
-    program.add_argument('--keep-frames', help='keep temporary frames', dest='keep_frames', action='store_true', default=False)
-    program.add_argument('--many-faces', help='process every face', dest='many_faces', action='store_true', default=False)
+    program.add_argument('--keep-fps', help='keep target fps', dest='keep_fps', action='store_true')
+    program.add_argument('--keep-frames', help='keep temporary frames', dest='keep_frames', action='store_true')
+    program.add_argument('--skip-audio', help='skip target audio', dest='skip_audio', action='store_true')
+    program.add_argument('--many-faces', help='process every face', dest='many_faces', action='store_true')
    program.add_argument('--video-encoder', help='adjust output video encoder', dest='video_encoder', default='libx264', choices=['libx264', 'libx265', 'libvpx-vp9'])
    program.add_argument('--video-quality', help='adjust output video quality', dest='video_quality', type=int, default=18, choices=range(52), metavar='[0-51]')
    program.add_argument('--max-memory', help='maximum amount of RAM in GB', dest='max_memory', type=int, default=suggest_max_memory())
@ -57,8 +57,8 @@ def parse_args() -> None:
    roop.globals.frame_processors = args.frame_processor
    roop.globals.headless = args.source_path or args.target_path or args.output_path
    roop.globals.keep_fps = args.keep_fps
-    roop.globals.keep_audio = args.keep_audio
    roop.globals.keep_frames = args.keep_frames
+    roop.globals.skip_audio = args.skip_audio
    roop.globals.many_faces = args.many_faces
    roop.globals.video_encoder = args.video_encoder
    roop.globals.video_quality = args.video_quality
@ -178,14 +178,15 @@ def start() -> None:
        update_status('Creating video with 30.0 fps...')
        create_video(roop.globals.target_path)
    # handle audio
-    if roop.globals.keep_audio:
+    if roop.globals.skip_audio:
+        move_temp(roop.globals.target_path, roop.globals.output_path)
+        update_status('Skipping audio...')
+    else:
        if roop.globals.keep_fps:
            update_status('Restoring audio...')
        else:
            update_status('Restoring audio might cause issues as fps are not kept...')
        restore_audio(roop.globals.target_path, roop.globals.output_path)
-    else:
-        move_temp(roop.globals.target_path, roop.globals.output_path)
    # clean and validate
    clean_temp(roop.globals.target_path)
    if is_video(roop.globals.target_path):
--- a/roop/globals.py
+++ b/roop/globals.py
@ -5,8 +5,8 @@ target_path = None
 output_path = None
 frame_processors: List[str] = []
 keep_fps = None
-keep_audio = None
 keep_frames = None
+skip_audio = None
 many_faces = None
 video_encoder = None
 video_quality = None
--- a/roop/ui.py
+++ b/roop/ui.py
@ -67,16 +67,16 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
    target_button.place(relx=0.6, rely=0.4, relwidth=0.3, relheight=0.1)

    keep_fps_value = ctk.BooleanVar(value=roop.globals.keep_fps)
-    keep_fps_checkbox = ctk.CTkSwitch(root, text='Keep fps', variable=keep_fps_value, cursor='hand2', command=lambda: setattr(roop.globals, 'keep_fps', not roop.globals.keep_fps))
+    keep_fps_checkbox = ctk.CTkSwitch(root, text='Keep target fps', variable=keep_fps_value, cursor='hand2', command=lambda: setattr(roop.globals, 'keep_fps', not roop.globals.keep_fps))
    keep_fps_checkbox.place(relx=0.1, rely=0.6)

    keep_frames_value = ctk.BooleanVar(value=roop.globals.keep_frames)
-    keep_frames_switch = ctk.CTkSwitch(root, text='Keep frames', variable=keep_frames_value, cursor='hand2', command=lambda: setattr(roop.globals, 'keep_frames', keep_frames_value.get()))
+    keep_frames_switch = ctk.CTkSwitch(root, text='Keep temporary frames', variable=keep_frames_value, cursor='hand2', command=lambda: setattr(roop.globals, 'keep_frames', keep_frames_value.get()))
    keep_frames_switch.place(relx=0.1, rely=0.65)

-    keep_audio_value = ctk.BooleanVar(value=roop.globals.keep_audio)
-    keep_audio_switch = ctk.CTkSwitch(root, text='Keep audio', variable=keep_audio_value, cursor='hand2', command=lambda: setattr(roop.globals, 'keep_audio', keep_audio_value.get()))
-    keep_audio_switch.place(relx=0.6, rely=0.6)
+    skip_audio_value = ctk.BooleanVar(value=roop.globals.skip_audio)
+    skip_audio_switch = ctk.CTkSwitch(root, text='Skip target audio', variable=skip_audio_value, cursor='hand2', command=lambda: setattr(roop.globals, 'skip_audio', skip_audio_value.get()))
+    skip_audio_switch.place(relx=0.6, rely=0.6)

    many_faces_value = ctk.BooleanVar(value=roop.globals.many_faces)
    many_faces_switch = ctk.CTkSwitch(root, text='Many faces', variable=many_faces_value, cursor='hand2', command=lambda: setattr(roop.globals, 'many_faces', many_faces_value.get()))