1
0
Fork 0
mirror of https://github.com/deepfakes/faceswap synced 2025-06-07 10:43:27 -04:00

Compare commits

...

6 commits

Author SHA1 Message Date
Mike Heavers
4505a2209d
Merge 449813c277 into acd0f11749 2025-06-01 00:15:20 -07:00
torzdf
acd0f11749 Merge branch 'staging' 2025-05-21 17:58:33 +01:00
torzdf
92ef5aa92d bugfix: setup.py fix badly escaped delimiters for Windows 2025-05-21 17:57:00 +01:00
torzdf
6c947c44f9 Merge branch 'staging' 2025-05-19 16:51:17 +01:00
torzdf
5212589242 Pin imageio-ffmpeg to <0.6.0 2025-05-19 16:48:50 +01:00
Mike Heavers
449813c277
Update USAGE.md
proper anchor to extracting video frames
2022-10-08 13:29:53 -07:00
3 changed files with 9 additions and 5 deletions

View file

@ -37,7 +37,7 @@ So here's our plan. We want to create a reality where Donald Trump lost the pres
## Gathering raw data
In order to accomplish this, the bot needs to learn to recognize both face A (Trump) and face B (Nic Cage). By default, the bot doesn't know what a Trump or a Nic Cage looks like. So we need to show it lots of pictures and let it guess which is which. So we need pictures of both of these faces first.
A possible source is Google, DuckDuckGo or Bing image search. There are scripts to download large amounts of images. A better source of images are videos (from interviews, public speeches, or movies) as these will capture many more natural poses and expressions. Fortunately FaceSwap has you covered and can extract faces from both still images and video files. See [Extracting video frames](#Extracting_video_frames) for more information.
A possible source is Google, DuckDuckGo or Bing image search. There are scripts to download large amounts of images. A better source of images are videos (from interviews, public speeches, or movies) as these will capture many more natural poses and expressions. Fortunately FaceSwap has you covered and can extract faces from both still images and video files. See [Extracting video frames](#videos) for more information.
Feel free to list your image sets in the [faceswap Forum](https://faceswap.dev/forum), or add more methods to this file.

View file

@ -8,6 +8,8 @@ scikit-learn>=1.3.0
fastcluster>=1.2.6
matplotlib>=3.8.0
imageio>=2.33.1
imageio-ffmpeg>=0.4.9
# ffmpeg binary >=0.6.0 breaks convert.
# TODO fix convert to use latest binary
imageio-ffmpeg>=0.4.9,<0.6.0
ffmpy>=0.3.0
pywin32>=305 ; sys_platform == "win32"

View file

@ -13,7 +13,7 @@ import re
import sys
import typing as T
from shutil import which
from subprocess import list2cmdline, PIPE, Popen, run, STDOUT
from subprocess import PIPE, Popen, run, STDOUT
from pkg_resources import parse_requirements
@ -1076,7 +1076,9 @@ class Install(): # pylint:disable=too-few-public-methods
str
The formatted full package and version string
"""
return f"{package}{','.join(''.join(spec) for spec in version)}"
retval = f"{package}{','.join(''.join(spec) for spec in version)}"
logger.debug("Formatted package \"%s\" version \"%s\" to \"%s'", package, version, retval)
return retval
def _install_setup_packages(self) -> None:
""" Install any packages that are required for the setup.py installer to work. This
@ -1493,7 +1495,7 @@ class WinPTYInstaller(Installer): # pylint:disable=too-few-public-methods
is_gui: bool) -> None:
super().__init__(environment, package, command, is_gui)
self._cmd = which(command[0], path=os.environ.get('PATH', os.defpath))
self._cmdline = list2cmdline(command)
self._cmdline = " ".join(command)
logger.debug("cmd: '%s', cmdline: '%s'", self._cmd, self._cmdline)
self._pbar = re.compile(r"(?:eta\s[\d\W]+)|(?:\s+\|\s+\d+%)\Z")