Files
DeepFaceLab/main.py

359 lines
23 KiB
Python
Raw Permalink Normal View History

2019-03-19 23:53:27 +04:00
if __name__ == "__main__":
2020-01-22 18:27:19 +04:00
# Fix for linux
import multiprocessing
2020-01-22 18:27:19 +04:00
multiprocessing.set_start_method("spawn")
from core.leras import nn
2020-01-21 18:43:39 +04:00
nn.initialize_main_env()
2019-12-24 14:07:06 +04:00
import os
import sys
import time
import argparse
2020-02-29 15:24:14 +04:00
from core import pathex
from core import osex
2019-12-24 14:07:06 +04:00
from pathlib import Path
2020-01-21 18:43:39 +04:00
from core.interact import interact as io
2019-12-24 14:07:06 +04:00
if sys.version_info[0] < 3 or (sys.version_info[0] == 3 and sys.version_info[1] < 6):
raise Exception("This program requires at least Python 3.6")
2019-03-19 23:53:27 +04:00
2019-12-24 14:07:06 +04:00
class fixPathAction(argparse.Action):
def __call__(self, parser, namespace, values, option_string=None):
setattr(namespace, self.dest, os.path.abspath(os.path.expanduser(values)))
exit_code = 0
2019-03-19 23:53:27 +04:00
parser = argparse.ArgumentParser()
2018-06-04 17:12:43 +04:00
subparsers = parser.add_subparsers()
2019-03-19 23:53:27 +04:00
2018-06-04 17:12:43 +04:00
def process_extract(arguments):
2020-01-21 18:43:39 +04:00
osex.set_process_lowest_prio()
2019-03-19 23:53:27 +04:00
from mainscripts import Extractor
2020-01-21 18:43:39 +04:00
Extractor.main( detector = arguments.detector,
input_path = Path(arguments.input_dir),
output_path = Path(arguments.output_dir),
output_debug = arguments.output_debug,
2020-01-21 18:43:39 +04:00
manual_fix = arguments.manual_fix,
manual_output_debug_fix = arguments.manual_output_debug_fix,
manual_window_size = arguments.manual_window_size,
face_type = arguments.face_type,
2020-06-27 19:07:55 +04:00
max_faces_from_image = arguments.max_faces_from_image,
image_size = arguments.image_size,
jpeg_quality = arguments.jpeg_quality,
2020-01-21 18:43:39 +04:00
cpu_only = arguments.cpu_only,
force_gpu_idxs = [ int(x) for x in arguments.force_gpu_idxs.split(',') ] if arguments.force_gpu_idxs is not None else None,
)
2019-03-19 23:53:27 +04:00
2019-03-14 10:50:53 +04:00
p = subparsers.add_parser( "extract", help="Extract the faces from a pictures.")
2020-01-21 18:43:39 +04:00
p.add_argument('--detector', dest="detector", choices=['s3fd','manual'], default=None, help="Type of detector.")
2019-03-14 10:50:53 +04:00
p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir", help="Input directory. A directory containing the files you wish to process.")
p.add_argument('--output-dir', required=True, action=fixPathAction, dest="output_dir", help="Output directory. This is where the extracted files will be stored.")
2020-01-21 18:43:39 +04:00
p.add_argument('--output-debug', action="store_true", dest="output_debug", default=None, help="Writes debug images to <output-dir>_debug\ directory.")
p.add_argument('--no-output-debug', action="store_false", dest="output_debug", default=None, help="Don't writes debug images to <output-dir>_debug\ directory.")
p.add_argument('--face-type', dest="face_type", choices=['half_face', 'full_face', 'whole_face', 'head', 'mark_only'], default=None)
2020-06-27 19:07:55 +04:00
p.add_argument('--max-faces-from-image', type=int, dest="max_faces_from_image", default=None, help="Max faces from image.")
p.add_argument('--image-size', type=int, dest="image_size", default=None, help="Output image size.")
p.add_argument('--jpeg-quality', type=int, dest="jpeg_quality", default=None, help="Jpeg quality.")
2019-03-14 10:50:53 +04:00
p.add_argument('--manual-fix', action="store_true", dest="manual_fix", default=False, help="Enables manual extract only frames where faces were not recognized.")
p.add_argument('--manual-output-debug-fix', action="store_true", dest="manual_output_debug_fix", default=False, help="Performs manual reextract input-dir frames which were deleted from [output_dir]_debug\ dir.")
2019-03-19 23:53:27 +04:00
p.add_argument('--manual-window-size', type=int, dest="manual_window_size", default=1368, help="Manual fix window size. Default: 1368.")
2020-01-21 18:43:39 +04:00
p.add_argument('--cpu-only', action="store_true", dest="cpu_only", default=False, help="Extract on CPU..")
p.add_argument('--force-gpu-idxs', dest="force_gpu_idxs", default=None, help="Force to choose GPU indexes separated by comma.")
2019-03-14 10:50:53 +04:00
p.set_defaults (func=process_extract)
2019-03-19 23:53:27 +04:00
def process_sort(arguments):
2020-01-21 18:43:39 +04:00
osex.set_process_lowest_prio()
2018-06-04 17:12:43 +04:00
from mainscripts import Sorter
2020-01-21 18:43:39 +04:00
Sorter.main (input_path=Path(arguments.input_dir), sort_by_method=arguments.sort_by_method)
2019-03-19 23:53:27 +04:00
p = subparsers.add_parser( "sort", help="Sort faces in a directory.")
2019-03-14 10:50:53 +04:00
p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir", help="Input directory. A directory containing the files you wish to process.")
2020-12-13 09:49:32 +04:00
p.add_argument('--by', dest="sort_by_method", default=None, choices=("blur", "motion-blur", "face-yaw", "face-pitch", "face-source-rect-size", "hist", "hist-dissim", "brightness", "hue", "black", "origname", "oneface", "final-by-blur", "final-by-size", "absdiff"), help="Method of sorting. 'origname' sort by original filename to recover original sequence." )
2019-03-14 10:50:53 +04:00
p.set_defaults (func=process_sort)
2019-03-19 23:53:27 +04:00
def process_util(arguments):
2020-01-21 18:43:39 +04:00
osex.set_process_lowest_prio()
from mainscripts import Util
2019-03-19 23:53:27 +04:00
if arguments.add_landmarks_debug_images:
Util.add_landmarks_debug_images (input_path=arguments.input_dir)
if arguments.recover_original_aligned_filename:
Util.recover_original_aligned_filename (input_path=arguments.input_dir)
if arguments.save_faceset_metadata:
Util.save_faceset_metadata_folder (input_path=arguments.input_dir)
if arguments.restore_faceset_metadata:
Util.restore_faceset_metadata_folder (input_path=arguments.input_dir)
if arguments.pack_faceset:
2019-12-23 14:57:47 +04:00
io.log_info ("Performing faceset packing...\r\n")
from samplelib import PackedFaceset
PackedFaceset.pack( Path(arguments.input_dir) )
if arguments.unpack_faceset:
2019-12-23 14:57:47 +04:00
io.log_info ("Performing faceset unpacking...\r\n")
from samplelib import PackedFaceset
PackedFaceset.unpack( Path(arguments.input_dir) )
if arguments.export_faceset_mask:
io.log_info ("Exporting faceset mask..\r\n")
Util.export_faceset_mask( Path(arguments.input_dir) )
2019-03-19 23:53:27 +04:00
p = subparsers.add_parser( "util", help="Utilities.")
2019-03-14 10:50:53 +04:00
p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir", help="Input directory. A directory containing the files you wish to process.")
p.add_argument('--add-landmarks-debug-images', action="store_true", dest="add_landmarks_debug_images", default=False, help="Add landmarks debug image for aligned faces.")
p.add_argument('--recover-original-aligned-filename', action="store_true", dest="recover_original_aligned_filename", default=False, help="Recover original aligned filename.")
p.add_argument('--save-faceset-metadata', action="store_true", dest="save_faceset_metadata", default=False, help="Save faceset metadata to file.")
p.add_argument('--restore-faceset-metadata', action="store_true", dest="restore_faceset_metadata", default=False, help="Restore faceset metadata to file. Image filenames must be the same as used with save.")
p.add_argument('--pack-faceset', action="store_true", dest="pack_faceset", default=False, help="")
p.add_argument('--unpack-faceset', action="store_true", dest="unpack_faceset", default=False, help="")
p.add_argument('--export-faceset-mask', action="store_true", dest="export_faceset_mask", default=False, help="")
2019-03-14 10:50:53 +04:00
p.set_defaults (func=process_util)
2019-03-19 23:53:27 +04:00
def process_train(arguments):
2020-01-21 18:43:39 +04:00
osex.set_process_lowest_prio()
2020-01-21 18:43:39 +04:00
kwargs = {'model_class_name' : arguments.model_name,
'saved_models_path' : Path(arguments.model_dir),
'training_data_src_path' : Path(arguments.training_data_src_dir),
'training_data_dst_path' : Path(arguments.training_data_dst_dir),
'pretraining_data_path' : Path(arguments.pretraining_data_dir) if arguments.pretraining_data_dir is not None else None,
'pretrained_model_path' : Path(arguments.pretrained_model_dir) if arguments.pretrained_model_dir is not None else None,
'no_preview' : arguments.no_preview,
'force_model_name' : arguments.force_model_name,
'force_gpu_idxs' : [ int(x) for x in arguments.force_gpu_idxs.split(',') ] if arguments.force_gpu_idxs is not None else None,
2020-01-21 18:43:39 +04:00
'cpu_only' : arguments.cpu_only,
'silent_start' : arguments.silent_start,
2020-01-21 18:43:39 +04:00
'execute_programs' : [ [int(x[0]), x[1] ] for x in arguments.execute_program ],
'debug' : arguments.debug,
2020-01-21 18:43:39 +04:00
}
2019-03-19 23:53:27 +04:00
from mainscripts import Trainer
2020-01-21 18:43:39 +04:00
Trainer.main(**kwargs)
2019-03-19 23:53:27 +04:00
p = subparsers.add_parser( "train", help="Trainer")
p.add_argument('--training-data-src-dir', required=True, action=fixPathAction, dest="training_data_src_dir", help="Dir of extracted SRC faceset.")
p.add_argument('--training-data-dst-dir', required=True, action=fixPathAction, dest="training_data_dst_dir", help="Dir of extracted DST faceset.")
2019-05-02 00:39:18 +04:00
p.add_argument('--pretraining-data-dir', action=fixPathAction, dest="pretraining_data_dir", default=None, help="Optional dir of extracted faceset that will be used in pretraining mode.")
p.add_argument('--pretrained-model-dir', action=fixPathAction, dest="pretrained_model_dir", default=None, help="Optional dir of pretrain model files. (Currently only for Quick96).")
2020-01-21 18:43:39 +04:00
p.add_argument('--model-dir', required=True, action=fixPathAction, dest="model_dir", help="Saved models dir.")
p.add_argument('--model', required=True, dest="model_name", choices=pathex.get_all_dir_names_startswith ( Path(__file__).parent / 'models' , 'Model_'), help="Model class name.")
2019-03-19 23:53:27 +04:00
p.add_argument('--debug', action="store_true", dest="debug", default=False, help="Debug samples.")
2020-01-21 18:43:39 +04:00
p.add_argument('--no-preview', action="store_true", dest="no_preview", default=False, help="Disable preview window.")
p.add_argument('--force-model-name', dest="force_model_name", default=None, help="Forcing to choose model name from model/ folder.")
2019-03-14 10:50:53 +04:00
p.add_argument('--cpu-only', action="store_true", dest="cpu_only", default=False, help="Train on CPU.")
2020-01-21 18:43:39 +04:00
p.add_argument('--force-gpu-idxs', dest="force_gpu_idxs", default=None, help="Force to choose GPU indexes separated by comma.")
p.add_argument('--silent-start', action="store_true", dest="silent_start", default=False, help="Silent start. Automatically chooses Best GPU and last used model.")
2019-03-26 19:15:20 +04:00
p.add_argument('--execute-program', dest="execute_program", default=[], action='append', nargs='+')
2019-03-14 10:50:53 +04:00
p.set_defaults (func=process_train)
2021-06-28 18:26:54 +04:00
def process_exportdfm(arguments):
osex.set_process_lowest_prio()
2021-06-28 18:26:54 +04:00
from mainscripts import ExportDFM
ExportDFM.main(model_class_name = arguments.model_name, saved_models_path = Path(arguments.model_dir))
2021-06-28 18:26:54 +04:00
p = subparsers.add_parser( "exportdfm", help="Export model to use in DeepFaceLive.")
p.add_argument('--model-dir', required=True, action=fixPathAction, dest="model_dir", help="Saved models dir.")
p.add_argument('--model', required=True, dest="model_name", choices=pathex.get_all_dir_names_startswith ( Path(__file__).parent / 'models' , 'Model_'), help="Model class name.")
2021-06-28 18:26:54 +04:00
p.set_defaults (func=process_exportdfm)
2019-03-19 23:53:27 +04:00
2020-01-21 18:43:39 +04:00
def process_merge(arguments):
osex.set_process_lowest_prio()
from mainscripts import Merger
Merger.main ( model_class_name = arguments.model_name,
saved_models_path = Path(arguments.model_dir),
force_model_name = arguments.force_model_name,
input_path = Path(arguments.input_dir),
output_path = Path(arguments.output_dir),
output_mask_path = Path(arguments.output_mask_dir),
aligned_path = Path(arguments.aligned_dir) if arguments.aligned_dir is not None else None,
force_gpu_idxs = arguments.force_gpu_idxs,
cpu_only = arguments.cpu_only)
2020-01-21 18:43:39 +04:00
p = subparsers.add_parser( "merge", help="Merger")
2019-03-14 10:50:53 +04:00
p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir", help="Input directory. A directory containing the files you wish to process.")
2020-01-21 18:43:39 +04:00
p.add_argument('--output-dir', required=True, action=fixPathAction, dest="output_dir", help="Output directory. This is where the merged files will be stored.")
p.add_argument('--output-mask-dir', required=True, action=fixPathAction, dest="output_mask_dir", help="Output mask directory. This is where the mask files will be stored.")
2020-01-21 18:43:39 +04:00
p.add_argument('--aligned-dir', action=fixPathAction, dest="aligned_dir", default=None, help="Aligned directory. This is where the extracted of dst faces stored.")
2019-03-14 10:50:53 +04:00
p.add_argument('--model-dir', required=True, action=fixPathAction, dest="model_dir", help="Model dir.")
2020-01-21 18:43:39 +04:00
p.add_argument('--model', required=True, dest="model_name", choices=pathex.get_all_dir_names_startswith ( Path(__file__).parent / 'models' , 'Model_'), help="Model class name.")
p.add_argument('--force-model-name', dest="force_model_name", default=None, help="Forcing to choose model name from model/ folder.")
2020-01-21 18:43:39 +04:00
p.add_argument('--cpu-only', action="store_true", dest="cpu_only", default=False, help="Merge on CPU.")
p.add_argument('--force-gpu-idxs', dest="force_gpu_idxs", default=None, help="Force to choose GPU indexes separated by comma.")
p.set_defaults(func=process_merge)
2019-03-19 23:53:27 +04:00
videoed_parser = subparsers.add_parser( "videoed", help="Video processing.").add_subparsers()
2019-03-19 23:53:27 +04:00
def process_videoed_extract_video(arguments):
2020-01-21 18:43:39 +04:00
osex.set_process_lowest_prio()
from mainscripts import VideoEd
VideoEd.extract_video (arguments.input_file, arguments.output_dir, arguments.output_ext, arguments.fps)
p = videoed_parser.add_parser( "extract-video", help="Extract images from video file.")
p.add_argument('--input-file', required=True, action=fixPathAction, dest="input_file", help="Input file to be processed. Specify .*-extension to find first file.")
p.add_argument('--output-dir', required=True, action=fixPathAction, dest="output_dir", help="Output directory. This is where the extracted images will be stored.")
2019-03-25 12:25:47 -05:00
p.add_argument('--output-ext', dest="output_ext", default=None, help="Image format (extension) of output files.")
p.add_argument('--fps', type=int, dest="fps", default=None, help="How many frames of every second of the video will be extracted. 0 - full fps.")
p.set_defaults(func=process_videoed_extract_video)
2019-03-19 23:53:27 +04:00
def process_videoed_cut_video(arguments):
2020-01-21 18:43:39 +04:00
osex.set_process_lowest_prio()
from mainscripts import VideoEd
2019-03-19 23:53:27 +04:00
VideoEd.cut_video (arguments.input_file,
arguments.from_time,
arguments.to_time,
arguments.audio_track_id,
arguments.bitrate)
p = videoed_parser.add_parser( "cut-video", help="Cut video file.")
p.add_argument('--input-file', required=True, action=fixPathAction, dest="input_file", help="Input file to be processed. Specify .*-extension to find first file.")
p.add_argument('--from-time', dest="from_time", default=None, help="From time, for example 00:00:00.000")
p.add_argument('--to-time', dest="to_time", default=None, help="To time, for example 00:00:00.000")
p.add_argument('--audio-track-id', type=int, dest="audio_track_id", default=None, help="Specify audio track id.")
2019-03-19 23:53:27 +04:00
p.add_argument('--bitrate', type=int, dest="bitrate", default=None, help="Bitrate of output file in Megabits.")
p.set_defaults(func=process_videoed_cut_video)
2019-03-19 23:53:27 +04:00
def process_videoed_denoise_image_sequence(arguments):
2020-01-21 18:43:39 +04:00
osex.set_process_lowest_prio()
from mainscripts import VideoEd
VideoEd.denoise_image_sequence (arguments.input_dir, arguments.factor)
p = videoed_parser.add_parser( "denoise-image-sequence", help="Denoise sequence of images, keeping sharp edges. Helps to remove pixel shake from the predicted face.")
p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir", help="Input directory to be processed.")
p.add_argument('--factor', type=int, dest="factor", default=None, help="Denoise factor (1-20).")
p.set_defaults(func=process_videoed_denoise_image_sequence)
2019-03-19 23:53:27 +04:00
def process_videoed_video_from_sequence(arguments):
2020-01-21 18:43:39 +04:00
osex.set_process_lowest_prio()
from mainscripts import VideoEd
VideoEd.video_from_sequence (input_dir = arguments.input_dir,
output_file = arguments.output_file,
reference_file = arguments.reference_file,
ext = arguments.ext,
fps = arguments.fps,
bitrate = arguments.bitrate,
include_audio = arguments.include_audio,
lossless = arguments.lossless)
2019-03-19 23:53:27 +04:00
p = videoed_parser.add_parser( "video-from-sequence", help="Make video from image sequence.")
p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir", help="Input file to be processed. Specify .*-extension to find first file.")
p.add_argument('--output-file', required=True, action=fixPathAction, dest="output_file", help="Input file to be processed. Specify .*-extension to find first file.")
p.add_argument('--reference-file', action=fixPathAction, dest="reference_file", help="Reference file used to determine proper FPS and transfer audio from it. Specify .*-extension to find first file.")
p.add_argument('--ext', dest="ext", default='png', help="Image format (extension) of input files.")
p.add_argument('--fps', type=int, dest="fps", default=None, help="FPS of output file. Overwritten by reference-file.")
2019-03-19 23:53:27 +04:00
p.add_argument('--bitrate', type=int, dest="bitrate", default=None, help="Bitrate of output file in Megabits.")
p.add_argument('--include-audio', action="store_true", dest="include_audio", default=False, help="Include audio from reference file.")
p.add_argument('--lossless', action="store_true", dest="lossless", default=False, help="PNG codec.")
p.set_defaults(func=process_videoed_video_from_sequence)
2019-03-19 23:53:27 +04:00
facesettool_parser = subparsers.add_parser( "facesettool", help="Faceset tools.").add_subparsers()
def process_faceset_enhancer(arguments):
2020-01-21 18:43:39 +04:00
osex.set_process_lowest_prio()
from mainscripts import FacesetEnhancer
FacesetEnhancer.process_folder ( Path(arguments.input_dir),
2020-01-21 18:43:39 +04:00
cpu_only=arguments.cpu_only,
force_gpu_idxs=arguments.force_gpu_idxs
)
p = facesettool_parser.add_parser ("enhance", help="Enhance details in DFL faceset.")
p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir", help="Input directory of aligned faces.")
p.add_argument('--cpu-only', action="store_true", dest="cpu_only", default=False, help="Process on CPU.")
2020-01-21 18:43:39 +04:00
p.add_argument('--force-gpu-idxs', dest="force_gpu_idxs", default=None, help="Force to choose GPU indexes separated by comma.")
p.set_defaults(func=process_faceset_enhancer)
added XSeg model. with XSeg model you can train your own mask segmentator of dst(and src) faces that will be used in merger for whole_face. Instead of using a pretrained model (which does not exist), you control which part of faces should be masked. Workflow is not easy, but at the moment it is the best solution for obtaining the best quality of whole_face's deepfakes using minimum effort without rotoscoping in AfterEffects. new scripts: XSeg) data_dst edit.bat XSeg) data_dst merge.bat XSeg) data_dst split.bat XSeg) data_src edit.bat XSeg) data_src merge.bat XSeg) data_src split.bat XSeg) train.bat Usage: unpack dst faceset if packed run XSeg) data_dst split.bat this scripts extracts (previously saved) .json data from jpg faces to use in label tool. run XSeg) data_dst edit.bat new tool 'labelme' is used use polygon (CTRL-N) to mask the face name polygon "1" (one symbol) as include polygon name polygon "0" (one symbol) as exclude polygon 'exclude polygons' will be applied after all 'include polygons' Hot keys: ctrl-N create polygon ctrl-J edit polygon A/D navigate between frames ctrl + mousewheel image zoom mousewheel vertical scroll alt+mousewheel horizontal scroll repeat for 10/50/100 faces, you don't need to mask every frame of dst, only frames where the face is different significantly, for example: closed eyes changed head direction changed light the more various faces you mask, the more quality you will get Start masking from the upper left area and follow the clockwise direction. Keep the same logic of masking for all frames, for example: the same approximated jaw line of the side faces, where the jaw is not visible the same hair line Mask the obstructions using polygon with name "0". run XSeg) data_dst merge.bat this script merges .json data of polygons into jpg faces, therefore faceset can be sorted or packed as usual. run XSeg) train.bat train the model Check the faces of 'XSeg dst faces' preview. if some faces have wrong or glitchy mask, then repeat steps: split run edit find these glitchy faces and mask them merge train further or restart training from scratch Restart training of XSeg model is only possible by deleting all 'model\XSeg_*' files. If you want to get the mask of the predicted face in merger, you should repeat the same steps for src faceset. New mask modes available in merger for whole_face: XSeg-prd - XSeg mask of predicted face -> faces from src faceset should be labeled XSeg-dst - XSeg mask of dst face -> faces from dst faceset should be labeled XSeg-prd*XSeg-dst - the smallest area of both if workspace\model folder contains trained XSeg model, then merger will use it, otherwise you will get transparent mask by using XSeg-* modes. Some screenshots: label tool: https://i.imgur.com/aY6QGw1.jpg trainer : https://i.imgur.com/NM1Kn3s.jpg merger : https://i.imgur.com/glUzFQ8.jpg example of the fake using 13 segmented dst faces : https://i.imgur.com/wmvyizU.gifv
2020-03-15 15:12:44 +04:00
p = facesettool_parser.add_parser ("resize", help="Resize DFL faceset.")
p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir", help="Input directory of aligned faces.")
def process_faceset_resizer(arguments):
osex.set_process_lowest_prio()
from mainscripts import FacesetResizer
FacesetResizer.process_folder ( Path(arguments.input_dir) )
p.set_defaults(func=process_faceset_resizer)
added XSeg model. with XSeg model you can train your own mask segmentator of dst(and src) faces that will be used in merger for whole_face. Instead of using a pretrained model (which does not exist), you control which part of faces should be masked. Workflow is not easy, but at the moment it is the best solution for obtaining the best quality of whole_face's deepfakes using minimum effort without rotoscoping in AfterEffects. new scripts: XSeg) data_dst edit.bat XSeg) data_dst merge.bat XSeg) data_dst split.bat XSeg) data_src edit.bat XSeg) data_src merge.bat XSeg) data_src split.bat XSeg) train.bat Usage: unpack dst faceset if packed run XSeg) data_dst split.bat this scripts extracts (previously saved) .json data from jpg faces to use in label tool. run XSeg) data_dst edit.bat new tool 'labelme' is used use polygon (CTRL-N) to mask the face name polygon "1" (one symbol) as include polygon name polygon "0" (one symbol) as exclude polygon 'exclude polygons' will be applied after all 'include polygons' Hot keys: ctrl-N create polygon ctrl-J edit polygon A/D navigate between frames ctrl + mousewheel image zoom mousewheel vertical scroll alt+mousewheel horizontal scroll repeat for 10/50/100 faces, you don't need to mask every frame of dst, only frames where the face is different significantly, for example: closed eyes changed head direction changed light the more various faces you mask, the more quality you will get Start masking from the upper left area and follow the clockwise direction. Keep the same logic of masking for all frames, for example: the same approximated jaw line of the side faces, where the jaw is not visible the same hair line Mask the obstructions using polygon with name "0". run XSeg) data_dst merge.bat this script merges .json data of polygons into jpg faces, therefore faceset can be sorted or packed as usual. run XSeg) train.bat train the model Check the faces of 'XSeg dst faces' preview. if some faces have wrong or glitchy mask, then repeat steps: split run edit find these glitchy faces and mask them merge train further or restart training from scratch Restart training of XSeg model is only possible by deleting all 'model\XSeg_*' files. If you want to get the mask of the predicted face in merger, you should repeat the same steps for src faceset. New mask modes available in merger for whole_face: XSeg-prd - XSeg mask of predicted face -> faces from src faceset should be labeled XSeg-dst - XSeg mask of dst face -> faces from dst faceset should be labeled XSeg-prd*XSeg-dst - the smallest area of both if workspace\model folder contains trained XSeg model, then merger will use it, otherwise you will get transparent mask by using XSeg-* modes. Some screenshots: label tool: https://i.imgur.com/aY6QGw1.jpg trainer : https://i.imgur.com/NM1Kn3s.jpg merger : https://i.imgur.com/glUzFQ8.jpg example of the fake using 13 segmented dst faces : https://i.imgur.com/wmvyizU.gifv
2020-03-15 15:12:44 +04:00
def process_dev_test(arguments):
osex.set_process_lowest_prio()
from mainscripts import dev_misc
dev_misc.dev_gen_mask_files( arguments.input_dir )
added XSeg model. with XSeg model you can train your own mask segmentator of dst(and src) faces that will be used in merger for whole_face. Instead of using a pretrained model (which does not exist), you control which part of faces should be masked. Workflow is not easy, but at the moment it is the best solution for obtaining the best quality of whole_face's deepfakes using minimum effort without rotoscoping in AfterEffects. new scripts: XSeg) data_dst edit.bat XSeg) data_dst merge.bat XSeg) data_dst split.bat XSeg) data_src edit.bat XSeg) data_src merge.bat XSeg) data_src split.bat XSeg) train.bat Usage: unpack dst faceset if packed run XSeg) data_dst split.bat this scripts extracts (previously saved) .json data from jpg faces to use in label tool. run XSeg) data_dst edit.bat new tool 'labelme' is used use polygon (CTRL-N) to mask the face name polygon "1" (one symbol) as include polygon name polygon "0" (one symbol) as exclude polygon 'exclude polygons' will be applied after all 'include polygons' Hot keys: ctrl-N create polygon ctrl-J edit polygon A/D navigate between frames ctrl + mousewheel image zoom mousewheel vertical scroll alt+mousewheel horizontal scroll repeat for 10/50/100 faces, you don't need to mask every frame of dst, only frames where the face is different significantly, for example: closed eyes changed head direction changed light the more various faces you mask, the more quality you will get Start masking from the upper left area and follow the clockwise direction. Keep the same logic of masking for all frames, for example: the same approximated jaw line of the side faces, where the jaw is not visible the same hair line Mask the obstructions using polygon with name "0". run XSeg) data_dst merge.bat this script merges .json data of polygons into jpg faces, therefore faceset can be sorted or packed as usual. run XSeg) train.bat train the model Check the faces of 'XSeg dst faces' preview. if some faces have wrong or glitchy mask, then repeat steps: split run edit find these glitchy faces and mask them merge train further or restart training from scratch Restart training of XSeg model is only possible by deleting all 'model\XSeg_*' files. If you want to get the mask of the predicted face in merger, you should repeat the same steps for src faceset. New mask modes available in merger for whole_face: XSeg-prd - XSeg mask of predicted face -> faces from src faceset should be labeled XSeg-dst - XSeg mask of dst face -> faces from dst faceset should be labeled XSeg-prd*XSeg-dst - the smallest area of both if workspace\model folder contains trained XSeg model, then merger will use it, otherwise you will get transparent mask by using XSeg-* modes. Some screenshots: label tool: https://i.imgur.com/aY6QGw1.jpg trainer : https://i.imgur.com/NM1Kn3s.jpg merger : https://i.imgur.com/glUzFQ8.jpg example of the fake using 13 segmented dst faces : https://i.imgur.com/wmvyizU.gifv
2020-03-15 15:12:44 +04:00
p = subparsers.add_parser( "dev_test", help="")
p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir")
p.set_defaults (func=process_dev_test)
# ========== XSeg
xseg_parser = subparsers.add_parser( "xseg", help="XSeg tools.").add_subparsers()
p = xseg_parser.add_parser( "editor", help="XSeg editor.")
added new XSegEditor ! here new whole_face + XSeg workflow: with XSeg model you can train your own mask segmentator for dst(and/or src) faces that will be used by the merger for whole_face. Instead of using a pretrained segmentator model (which does not exist), you control which part of faces should be masked. new scripts: 5.XSeg) data_dst edit masks.bat 5.XSeg) data_src edit masks.bat 5.XSeg) train.bat Usage: unpack dst faceset if packed run 5.XSeg) data_dst edit masks.bat Read tooltips on the buttons (en/ru/zn languages are supported) mask the face using include or exclude polygon mode. repeat for 50/100 faces, !!! you don't need to mask every frame of dst only frames where the face is different significantly, for example: closed eyes changed head direction changed light the more various faces you mask, the more quality you will get Start masking from the upper left area and follow the clockwise direction. Keep the same logic of masking for all frames, for example: the same approximated jaw line of the side faces, where the jaw is not visible the same hair line Mask the obstructions using exclude polygon mode. run XSeg) train.bat train the model Check the faces of 'XSeg dst faces' preview. if some faces have wrong or glitchy mask, then repeat steps: run edit find these glitchy faces and mask them train further or restart training from scratch Restart training of XSeg model is only possible by deleting all 'model\XSeg_*' files. If you want to get the mask of the predicted face (XSeg-prd mode) in merger, you should repeat the same steps for src faceset. New mask modes available in merger for whole_face: XSeg-prd - XSeg mask of predicted face -> faces from src faceset should be labeled XSeg-dst - XSeg mask of dst face -> faces from dst faceset should be labeled XSeg-prd*XSeg-dst - the smallest area of both if workspace\model folder contains trained XSeg model, then merger will use it, otherwise you will get transparent mask by using XSeg-* modes. Some screenshots: XSegEditor: https://i.imgur.com/7Bk4RRV.jpg trainer : https://i.imgur.com/NM1Kn3s.jpg merger : https://i.imgur.com/glUzFQ8.jpg example of the fake using 13 segmented dst faces : https://i.imgur.com/wmvyizU.gifv
2020-03-24 12:15:31 +04:00
def process_xsegeditor(arguments):
2020-01-21 18:43:39 +04:00
osex.set_process_lowest_prio()
added new XSegEditor ! here new whole_face + XSeg workflow: with XSeg model you can train your own mask segmentator for dst(and/or src) faces that will be used by the merger for whole_face. Instead of using a pretrained segmentator model (which does not exist), you control which part of faces should be masked. new scripts: 5.XSeg) data_dst edit masks.bat 5.XSeg) data_src edit masks.bat 5.XSeg) train.bat Usage: unpack dst faceset if packed run 5.XSeg) data_dst edit masks.bat Read tooltips on the buttons (en/ru/zn languages are supported) mask the face using include or exclude polygon mode. repeat for 50/100 faces, !!! you don't need to mask every frame of dst only frames where the face is different significantly, for example: closed eyes changed head direction changed light the more various faces you mask, the more quality you will get Start masking from the upper left area and follow the clockwise direction. Keep the same logic of masking for all frames, for example: the same approximated jaw line of the side faces, where the jaw is not visible the same hair line Mask the obstructions using exclude polygon mode. run XSeg) train.bat train the model Check the faces of 'XSeg dst faces' preview. if some faces have wrong or glitchy mask, then repeat steps: run edit find these glitchy faces and mask them train further or restart training from scratch Restart training of XSeg model is only possible by deleting all 'model\XSeg_*' files. If you want to get the mask of the predicted face (XSeg-prd mode) in merger, you should repeat the same steps for src faceset. New mask modes available in merger for whole_face: XSeg-prd - XSeg mask of predicted face -> faces from src faceset should be labeled XSeg-dst - XSeg mask of dst face -> faces from dst faceset should be labeled XSeg-prd*XSeg-dst - the smallest area of both if workspace\model folder contains trained XSeg model, then merger will use it, otherwise you will get transparent mask by using XSeg-* modes. Some screenshots: XSegEditor: https://i.imgur.com/7Bk4RRV.jpg trainer : https://i.imgur.com/NM1Kn3s.jpg merger : https://i.imgur.com/glUzFQ8.jpg example of the fake using 13 segmented dst faces : https://i.imgur.com/wmvyizU.gifv
2020-03-24 12:15:31 +04:00
from XSegEditor import XSegEditor
global exit_code
exit_code = XSegEditor.start (Path(arguments.input_dir))
added XSeg model. with XSeg model you can train your own mask segmentator of dst(and src) faces that will be used in merger for whole_face. Instead of using a pretrained model (which does not exist), you control which part of faces should be masked. Workflow is not easy, but at the moment it is the best solution for obtaining the best quality of whole_face's deepfakes using minimum effort without rotoscoping in AfterEffects. new scripts: XSeg) data_dst edit.bat XSeg) data_dst merge.bat XSeg) data_dst split.bat XSeg) data_src edit.bat XSeg) data_src merge.bat XSeg) data_src split.bat XSeg) train.bat Usage: unpack dst faceset if packed run XSeg) data_dst split.bat this scripts extracts (previously saved) .json data from jpg faces to use in label tool. run XSeg) data_dst edit.bat new tool 'labelme' is used use polygon (CTRL-N) to mask the face name polygon "1" (one symbol) as include polygon name polygon "0" (one symbol) as exclude polygon 'exclude polygons' will be applied after all 'include polygons' Hot keys: ctrl-N create polygon ctrl-J edit polygon A/D navigate between frames ctrl + mousewheel image zoom mousewheel vertical scroll alt+mousewheel horizontal scroll repeat for 10/50/100 faces, you don't need to mask every frame of dst, only frames where the face is different significantly, for example: closed eyes changed head direction changed light the more various faces you mask, the more quality you will get Start masking from the upper left area and follow the clockwise direction. Keep the same logic of masking for all frames, for example: the same approximated jaw line of the side faces, where the jaw is not visible the same hair line Mask the obstructions using polygon with name "0". run XSeg) data_dst merge.bat this script merges .json data of polygons into jpg faces, therefore faceset can be sorted or packed as usual. run XSeg) train.bat train the model Check the faces of 'XSeg dst faces' preview. if some faces have wrong or glitchy mask, then repeat steps: split run edit find these glitchy faces and mask them merge train further or restart training from scratch Restart training of XSeg model is only possible by deleting all 'model\XSeg_*' files. If you want to get the mask of the predicted face in merger, you should repeat the same steps for src faceset. New mask modes available in merger for whole_face: XSeg-prd - XSeg mask of predicted face -> faces from src faceset should be labeled XSeg-dst - XSeg mask of dst face -> faces from dst faceset should be labeled XSeg-prd*XSeg-dst - the smallest area of both if workspace\model folder contains trained XSeg model, then merger will use it, otherwise you will get transparent mask by using XSeg-* modes. Some screenshots: label tool: https://i.imgur.com/aY6QGw1.jpg trainer : https://i.imgur.com/NM1Kn3s.jpg merger : https://i.imgur.com/glUzFQ8.jpg example of the fake using 13 segmented dst faces : https://i.imgur.com/wmvyizU.gifv
2020-03-15 15:12:44 +04:00
p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir")
added new XSegEditor ! here new whole_face + XSeg workflow: with XSeg model you can train your own mask segmentator for dst(and/or src) faces that will be used by the merger for whole_face. Instead of using a pretrained segmentator model (which does not exist), you control which part of faces should be masked. new scripts: 5.XSeg) data_dst edit masks.bat 5.XSeg) data_src edit masks.bat 5.XSeg) train.bat Usage: unpack dst faceset if packed run 5.XSeg) data_dst edit masks.bat Read tooltips on the buttons (en/ru/zn languages are supported) mask the face using include or exclude polygon mode. repeat for 50/100 faces, !!! you don't need to mask every frame of dst only frames where the face is different significantly, for example: closed eyes changed head direction changed light the more various faces you mask, the more quality you will get Start masking from the upper left area and follow the clockwise direction. Keep the same logic of masking for all frames, for example: the same approximated jaw line of the side faces, where the jaw is not visible the same hair line Mask the obstructions using exclude polygon mode. run XSeg) train.bat train the model Check the faces of 'XSeg dst faces' preview. if some faces have wrong or glitchy mask, then repeat steps: run edit find these glitchy faces and mask them train further or restart training from scratch Restart training of XSeg model is only possible by deleting all 'model\XSeg_*' files. If you want to get the mask of the predicted face (XSeg-prd mode) in merger, you should repeat the same steps for src faceset. New mask modes available in merger for whole_face: XSeg-prd - XSeg mask of predicted face -> faces from src faceset should be labeled XSeg-dst - XSeg mask of dst face -> faces from dst faceset should be labeled XSeg-prd*XSeg-dst - the smallest area of both if workspace\model folder contains trained XSeg model, then merger will use it, otherwise you will get transparent mask by using XSeg-* modes. Some screenshots: XSegEditor: https://i.imgur.com/7Bk4RRV.jpg trainer : https://i.imgur.com/NM1Kn3s.jpg merger : https://i.imgur.com/glUzFQ8.jpg example of the fake using 13 segmented dst faces : https://i.imgur.com/wmvyizU.gifv
2020-03-24 12:15:31 +04:00
p.set_defaults (func=process_xsegeditor)
p = xseg_parser.add_parser( "apply", help="Apply trained XSeg model to the extracted faces.")
def process_xsegapply(arguments):
osex.set_process_lowest_prio()
from mainscripts import XSegUtil
XSegUtil.apply_xseg (Path(arguments.input_dir), Path(arguments.model_dir))
p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir")
p.add_argument('--model-dir', required=True, action=fixPathAction, dest="model_dir")
p.set_defaults (func=process_xsegapply)
p = xseg_parser.add_parser( "remove", help="Remove applied XSeg masks from the extracted faces.")
def process_xsegremove(arguments):
osex.set_process_lowest_prio()
from mainscripts import XSegUtil
XSegUtil.remove_xseg (Path(arguments.input_dir) )
p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir")
p.set_defaults (func=process_xsegremove)
p = xseg_parser.add_parser( "remove_labels", help="Remove XSeg labels from the extracted faces.")
def process_xsegremovelabels(arguments):
osex.set_process_lowest_prio()
from mainscripts import XSegUtil
XSegUtil.remove_xseg_labels (Path(arguments.input_dir) )
p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir")
p.set_defaults (func=process_xsegremovelabels)
p = xseg_parser.add_parser( "fetch", help="Copies faces containing XSeg polygons in <input_dir>_xseg dir.")
def process_xsegfetch(arguments):
osex.set_process_lowest_prio()
from mainscripts import XSegUtil
XSegUtil.fetch_xseg (Path(arguments.input_dir) )
p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir")
p.set_defaults (func=process_xsegfetch)
2018-06-04 17:12:43 +04:00
def bad_args(arguments):
parser.print_help()
exit(0)
parser.set_defaults(func=bad_args)
2019-03-19 23:53:27 +04:00
2018-06-04 17:12:43 +04:00
arguments = parser.parse_args()
arguments.func(arguments)
2018-06-04 17:12:43 +04:00
if exit_code == 0:
print ("Done.")
exit(exit_code)
2018-06-04 17:12:43 +04:00
'''
import code
code.interact(local=dict(globals(), **locals()))
2019-03-19 23:53:27 +04:00
'''