Update roop/core.py

roop/core.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+
 import os
 import sys
 # single thread doubles cuda performance - needs to be set before torch import
@@ -12,10 +13,8 @@ import platform
 import signal
 import shutil
 import argparse
-import torch
 import onnxruntime
 import tensorflow
-
 import roop.globals
 import roop.metadata
 import roop.ui as ui
@@ -23,9 +22,6 @@ from roop.predictor import predict_image, predict_video
 from roop.processors.frame.core import get_frame_processors_modules
 from roop.utilities import has_image_extension, is_image, is_video, detect_fps, create_video, extract_frames, get_temp_frame_paths, restore_audio, create_temp, move_temp, clean_temp, normalize_output_path
 
-if 'ROCMExecutionProvider' in roop.globals.execution_providers:
-    del torch
-
 warnings.filterwarnings('ignore', category=FutureWarning, module='insightface')
 warnings.filterwarnings('ignore', category=UserWarning, module='torchvision')
 
@@ -37,13 +33,18 @@ 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('--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())
+    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('--reference-face-position', help='position of the reference face', dest='reference_face_position', type=int, default=0)
+    program.add_argument('--reference-frame-number', help='number of the reference frame', dest='reference_frame_number', type=int, default=0)
+    program.add_argument('--similar-face-distance', help='face distance used for recognition', dest='similar_face_distance', type=float, default=0.85)
+    program.add_argument('--temp-frame-format', help='image format used for frame extraction', dest='temp_frame_format', default='png', choices=['jpg', 'png'])
+    program.add_argument('--temp-frame-quality', help='image quality used for frame extraction', dest='temp_frame_quality', type=int, default=0, choices=range(101), metavar='[0-100]')
+    program.add_argument('--output-video-encoder', help='encoder used for the output video', dest='output_video_encoder', default='libx264', choices=['libx264', 'libx265', 'libvpx-vp9', 'h264_nvenc', 'hevc_nvenc'])
+    program.add_argument('--output-video-quality', help='quality used for the output video', dest='output_video_quality', type=int, default=35, choices=range(101), metavar='[0-100]')
+    program.add_argument('--max-memory', help='maximum amount of RAM in GB', dest='max_memory', type=int)
     program.add_argument('--execution-provider', help='available execution provider (choices: cpu, ...)', dest='execution_provider', default=['cpu'], choices=suggest_execution_providers(), nargs='+')
     program.add_argument('--execution-threads', help='number of execution threads', dest='execution_threads', type=int, default=suggest_execution_threads())
     program.add_argument('-v', '--version', action='version', version=f'{roop.metadata.name} {roop.metadata.version}')
@@ -53,14 +54,19 @@ def parse_args() -> None:
     roop.globals.source_path = args.source_path
     roop.globals.target_path = args.target_path
     roop.globals.output_path = normalize_output_path(roop.globals.source_path, roop.globals.target_path, args.output_path)
+    roop.globals.headless = roop.globals.source_path is not None and roop.globals.target_path is not None and roop.globals.output_path is not 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
+    roop.globals.reference_face_position = args.reference_face_position
+    roop.globals.reference_frame_number = args.reference_frame_number
+    roop.globals.similar_face_distance = args.similar_face_distance
+    roop.globals.temp_frame_format = args.temp_frame_format
+    roop.globals.temp_frame_quality = args.temp_frame_quality
+    roop.globals.output_video_encoder = args.output_video_encoder
+    roop.globals.output_video_quality = args.output_video_quality
     roop.globals.max_memory = args.max_memory
     roop.globals.execution_providers = decode_execution_providers(args.execution_provider)
     roop.globals.execution_threads = args.execution_threads
@@ -75,22 +81,14 @@ def decode_execution_providers(execution_providers: List[str]) -> List[str]:
             if any(execution_provider in encoded_execution_provider for execution_provider in execution_providers)]
 
 
-def suggest_max_memory() -> int:
-    if platform.system().lower() == 'darwin':
-        return 4
-    return 16
-
-
 def suggest_execution_providers() -> List[str]:
     return encode_execution_providers(onnxruntime.get_available_providers())
 
 
 def suggest_execution_threads() -> int:
-    if 'DmlExecutionProvider' in roop.globals.execution_providers:
-        return 1
-    if 'ROCMExecutionProvider' in roop.globals.execution_providers:
-        return 1
-    return 8
+    if 'CUDAExecutionProvider' in onnxruntime.get_available_providers():
+        return 8
+    return 1
 
 
 def limit_resources() -> None:
@@ -107,18 +105,13 @@ def limit_resources() -> None:
             memory = roop.globals.max_memory * 1024 ** 6
         if platform.system().lower() == 'windows':
             import ctypes
-            kernel32 = ctypes.windll.kernel32
+            kernel32 = ctypes.windll.kernel32  # type: ignore[attr-defined]
             kernel32.SetProcessWorkingSetSize(-1, ctypes.c_size_t(memory), ctypes.c_size_t(memory))
         else:
             import resource
             resource.setrlimit(resource.RLIMIT_DATA, (memory, memory))
 
 
-def release_resources() -> None:
-    if 'CUDAExecutionProvider' in roop.globals.execution_providers:
-        torch.cuda.empty_cache()
-
-
 def pre_check() -> bool:
     if sys.version_info < (3, 9):
         update_status('Python version is not supported - please upgrade to 3.9 or higher.')
@@ -144,11 +137,12 @@ def start() -> None:
         if predict_image(roop.globals.target_path):
             destroy()
         shutil.copy2(roop.globals.target_path, roop.globals.output_path)
+        # process frame
         for frame_processor in get_frame_processors_modules(roop.globals.frame_processors):
             update_status('Progressing...', frame_processor.NAME)
             frame_processor.process_image(roop.globals.source_path, roop.globals.output_path, roop.globals.output_path)
             frame_processor.post_process()
-            release_resources()
+        # validate image
         if is_image(roop.globals.target_path):
             update_status('Processing to image succeed!')
         else:
@@ -157,36 +151,48 @@ def start() -> None:
     # process image to videos
     if predict_video(roop.globals.target_path):
         destroy()
-    update_status('Creating temp resources...')
+    update_status('Creating temporary resources...')
     create_temp(roop.globals.target_path)
-    update_status('Extracting frames...')
-    extract_frames(roop.globals.target_path)
+    # extract frames
+    if roop.globals.keep_fps:
+        fps = detect_fps(roop.globals.target_path)
+        update_status(f'Extracting frames with {fps} FPS...')
+        extract_frames(roop.globals.target_path, fps)
+    else:
+        update_status('Extracting frames with 30 FPS...')
+        extract_frames(roop.globals.target_path)
+    # process frame
     temp_frame_paths = get_temp_frame_paths(roop.globals.target_path)
-    for frame_processor in get_frame_processors_modules(roop.globals.frame_processors):
-        update_status('Progressing...', frame_processor.NAME)
-        frame_processor.process_video(roop.globals.source_path, temp_frame_paths)
-        frame_processor.post_process()
-        release_resources()
-    # handles fps
+    if temp_frame_paths:
+        for frame_processor in get_frame_processors_modules(roop.globals.frame_processors):
+            update_status('Progressing...', frame_processor.NAME)
+            frame_processor.process_video(roop.globals.source_path, temp_frame_paths)
+            frame_processor.post_process()
+    else:
+        update_status('Frames not found...')
+        return
+    # create video
     if roop.globals.keep_fps:
-        update_status('Detecting fps...')
         fps = detect_fps(roop.globals.target_path)
-        update_status(f'Creating video with {fps} fps...')
+        update_status(f'Creating video with {fps} FPS...')
         create_video(roop.globals.target_path, fps)
     else:
-        update_status('Creating video with 30.0 fps...')
+        update_status('Creating video with 30 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
+    update_status('Cleaning temporary resources...')
     clean_temp(roop.globals.target_path)
+    # validate video
     if is_video(roop.globals.target_path):
         update_status('Processing to video succeed!')
     else:
@@ -196,7 +202,7 @@ def start() -> None:
 def destroy() -> None:
     if roop.globals.target_path:
         clean_temp(roop.globals.target_path)
-    quit()
+    sys.exit()
 
 
 def run() -> None:
@@ -211,4 +217,4 @@ def run() -> None:
         start()
     else:
         window = ui.init(start, destroy)
-        window.mainloop()
+        window.mainloop()