Files
facefusion/facefusion/uis/components/webcam.py
T
da0da3a4b4 Next (#945)
* Rename calcXXX to calculateXXX

* Add migraphx support

* Add migraphx support

* Add migraphx support

* Add migraphx support

* Add migraphx support

* Add migraphx support

* Use True for the flags

* Add migraphx support

* add face-swapper-weight

* add face-swapper-weight to facefusion.ini

* changes

* change choice

* Fix typing for xxxWeight

* Feat/log inference session (#906)

* Log inference session, Introduce time helper

* Log inference session, Introduce time helper

* Log inference session, Introduce time helper

* Log inference session, Introduce time helper

* Mark as NEXT

* Follow industry standard x1, x2, y1 and y2

* Follow industry standard x1, x2, y1 and y2

* Follow industry standard in terms of naming (#908)

* Follow industry standard in terms of naming

* Improve xxx_embedding naming

* Fix norm vs. norms

* Reduce timeout to 5

* Sort out voice_extractor once again

* changes

* Introduce many to the occlusion mask (#910)

* Introduce many to the occlusion mask

* Then we use minimum

* Add support for wmv

* Run platform tests before has_execution_provider (#911)

* Add support for wmv

* Introduce benchmark mode (#912)

* Honestly makes no difference to me

* Honestly makes no difference to me

* Fix wording

* Bring back YuNet (#922)

* Reintroduce YuNet without cv2 dependency

* Fix variable naming

* Avoid RGB to YUV colorshift using libx264rgb

* Avoid RGB to YUV colorshift using libx264rgb

* Make libx264 the default again

* Make libx264 the default again

* Fix types in ffmpeg builder

* Fix quality stuff in ffmpeg builder

* Fix quality stuff in ffmpeg builder

* Add libx264rgb to test

* Revamp Processors (#923)

* Introduce new concept of pure target frames

* Radical refactoring of process flow

* Introduce new concept of pure target frames

* Fix webcam

* Minor improvements

* Minor improvements

* Use deque for video processing

* Use deque for video processing

* Extend the video manager

* Polish deque

* Polish deque

* Deque is not even used

* Improve speed with multiple futures

* Fix temp frame mutation and

* Fix RAM usage

* Remove old types and manage method

* Remove execution_queue_count

* Use init_state for benchmarker to avoid issues

* add voice extractor option

* Change the order of voice extractor in code

* Use official download urls

* Use official download urls

* add gui

* fix preview

* Add remote updates for voice extractor

* fix crash on headless-run

* update test_job_helper.py

* Fix it for good

* Remove pointless method

* Fix types and unused imports

* Revamp reference (#925)

* Initial revamp of face references

* Initial revamp of face references

* Initial revamp of face references

* Terminate find_similar_faces

* Improve find mutant faces

* Improve find mutant faces

* Move sort where it belongs

* Forward reference vision frame

* Forward reference vision frame also in preview

* Fix reference selection

* Use static video frame

* Fix CI

* Remove reference type from frame processors

* Improve some naming

* Fix types and unused imports

* Fix find mutant faces

* Fix find mutant faces

* Fix imports

* Correct naming

* Correct naming

* simplify pad

* Improve webcam performance on highres

* Camera manager (#932)

* Introduce webcam manager

* Fix order

* Rename to camera manager, improve video manager

* Fix CI

* Remove optional

* Fix naming in webcam options

* Avoid using temp faces (#933)

* output video scale

* Fix imports

* output image scale

* upscale fix (not limiter)

* add unit test scale_resolution & remove unused methods

* fix and add test

* fix

* change pack_resolution

* fix tests

* Simplify output scale testing

* Fix benchmark UI

* Fix benchmark UI

* Update dependencies

* Introduce REAL multi gpu support using multi dimensional inference pool (#935)

* Introduce REAL multi gpu support using multi dimensional inference pool

* Remove the MULTI:GPU flag

* Restore "processing stop"

* Restore "processing stop"

* Remove old templates

* Go fill in with caching

* add expression restorer areas

* re-arrange

* rename method

* Fix stop for extract frames and merge video

* Replace arcface_converter models with latest crossface models

* Replace arcface_converter models with latest crossface models

* Move module logs to debug mode

* Refactor/streamer (#938)

* Introduce webcam manager

* Fix order

* Rename to camera manager, improve video manager

* Fix CI

* Fix naming in webcam options

* Move logic over to streamer

* Fix streamer, improve webcam experience

* Improve webcam experience

* Revert method

* Revert method

* Improve webcam again

* Use release on capture instead

* Only forward valid frames

* Fix resolution logging

* Add AVIF support

* Add AVIF support

* Limit avif to unix systems

* Drop avif

* Drop avif

* Drop avif

* Default to Documents in the UI if output path is not set

* Update wording.py (#939)

"succeed" is grammatically incorrect in the given context. To succeed is the infinitive form of the verb. Correct would be either "succeeded" or alternatively a form involving the noun "success".

* Fix more grammar issue

* Fix more grammar issue

* Sort out caching

* Move webcam choices back to UI

* Move preview options to own file (#940)

* Fix Migraphx execution provider

* Fix benchmark

* Reuse blend frame method

* Fix CI

* Fix CI

* Fix CI

* Hotfix missing check in face debugger, Enable logger for preview

* Fix reference selection (#942)

* Fix reference selection

* Fix reference selection

* Fix reference selection

* Fix reference selection

* Side by side preview (#941)

* Initial side by side preview

* More work on preview, remove UI only stuff from vision.py

* Improve more

* Use fit frame

* Add different fit methods for vision

* Improve preview part2

* Improve preview part3

* Improve preview part4

* Remove none as choice

* Remove useless methods

* Fix CI

* Fix naming

* use 1024 as preview resolution default

* Fix fit_cover_frame

* Uniform fit_xxx_frame methods

* Add back disabled logger

* Use ui choices alias

* Extract select face logic from processors (#943)

* Extract select face logic from processors to use it for face by face in preview

* Fix order

* Remove old code

* Merge methods

* Refactor face debugger (#944)

* Refactor huge method of face debugger

* Remove text metrics from face debugger

* Remove useless copy of temp frame

* Resort methods

* Fix spacing

* Remove old method

* Fix hard exit to work without signals

* Prevent upscaling for face-by-face

* Switch to version

* Improve exiting

---------

Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
Co-authored-by: Rafael Tappe Maestro <rafael@tappemaestro.com>
2025-09-08 10:43:58 +02:00

116 lines
4.2 KiB
Python

from typing import Generator, List, Optional, Tuple
import cv2
import gradio
from facefusion import state_manager, wording
from facefusion.camera_manager import clear_camera_pool, get_local_camera_capture
from facefusion.filesystem import has_image
from facefusion.streamer import multi_process_capture, open_stream
from facefusion.types import Fps, VisionFrame, WebcamMode
from facefusion.uis.core import get_ui_component
from facefusion.uis.types import File
from facefusion.vision import unpack_resolution
SOURCE_FILE : Optional[gradio.File] = None
WEBCAM_IMAGE : Optional[gradio.Image] = None
WEBCAM_START_BUTTON : Optional[gradio.Button] = None
WEBCAM_STOP_BUTTON : Optional[gradio.Button] = None
def render() -> None:
global SOURCE_FILE
global WEBCAM_IMAGE
global WEBCAM_START_BUTTON
global WEBCAM_STOP_BUTTON
has_source_image = has_image(state_manager.get_item('source_paths'))
SOURCE_FILE = gradio.File(
label = wording.get('uis.source_file'),
file_count = 'multiple',
value = state_manager.get_item('source_paths') if has_source_image else None
)
WEBCAM_IMAGE = gradio.Image(
label = wording.get('uis.webcam_image'),
format = 'jpeg',
visible = False
)
WEBCAM_START_BUTTON = gradio.Button(
value = wording.get('uis.start_button'),
variant = 'primary',
size = 'sm'
)
WEBCAM_STOP_BUTTON = gradio.Button(
value = wording.get('uis.stop_button'),
size = 'sm',
visible = False
)
def listen() -> None:
SOURCE_FILE.change(update_source, inputs = SOURCE_FILE, outputs = SOURCE_FILE)
webcam_device_id_dropdown = get_ui_component('webcam_device_id_dropdown')
webcam_mode_radio = get_ui_component('webcam_mode_radio')
webcam_resolution_dropdown = get_ui_component('webcam_resolution_dropdown')
webcam_fps_slider = get_ui_component('webcam_fps_slider')
if webcam_device_id_dropdown and webcam_mode_radio and webcam_resolution_dropdown and webcam_fps_slider:
WEBCAM_START_BUTTON.click(pre_start, outputs = [ SOURCE_FILE, WEBCAM_IMAGE, WEBCAM_START_BUTTON, WEBCAM_STOP_BUTTON ])
start_event = WEBCAM_START_BUTTON.click(start, inputs = [ webcam_device_id_dropdown, webcam_mode_radio, webcam_resolution_dropdown, webcam_fps_slider ], outputs = WEBCAM_IMAGE)
start_event.then(pre_stop)
WEBCAM_STOP_BUTTON.click(stop, cancels = start_event, outputs = WEBCAM_IMAGE)
WEBCAM_STOP_BUTTON.click(pre_stop, outputs = [ SOURCE_FILE, WEBCAM_IMAGE, WEBCAM_START_BUTTON, WEBCAM_STOP_BUTTON ])
def update_source(files : List[File]) -> gradio.File:
file_names = [ file.name for file in files ] if files else None
has_source_image = has_image(file_names)
if has_source_image:
state_manager.set_item('source_paths', file_names)
return gradio.File(value = file_names)
state_manager.clear_item('source_paths')
return gradio.File(value = None)
def pre_start() -> Tuple[gradio.File, gradio.Image, gradio.Button, gradio.Button]:
return gradio.File(visible = False), gradio.Image(visible = True), gradio.Button(visible = False), gradio.Button(visible = True)
def pre_stop() -> Tuple[gradio.File, gradio.Image, gradio.Button, gradio.Button]:
return gradio.File(visible = True), gradio.Image(visible = False), gradio.Button(visible = True), gradio.Button(visible = False)
def start(webcam_device_id : int, webcam_mode : WebcamMode, webcam_resolution : str, webcam_fps : Fps) -> Generator[VisionFrame, None, None]:
state_manager.init_item('face_selector_mode', 'one')
state_manager.sync_state()
camera_capture = get_local_camera_capture(webcam_device_id)
stream = None
if webcam_mode in [ 'udp', 'v4l2' ]:
stream = open_stream(webcam_mode, webcam_resolution, webcam_fps) # type:ignore[arg-type]
webcam_width, webcam_height = unpack_resolution(webcam_resolution)
if camera_capture and camera_capture.isOpened():
camera_capture.set(cv2.CAP_PROP_FRAME_WIDTH, webcam_width)
camera_capture.set(cv2.CAP_PROP_FRAME_HEIGHT, webcam_height)
camera_capture.set(cv2.CAP_PROP_FPS, webcam_fps)
for capture_frame in multi_process_capture(camera_capture, webcam_fps):
capture_frame = cv2.cvtColor(capture_frame, cv2.COLOR_BGR2RGB)
if webcam_mode == 'inline':
yield capture_frame
else:
try:
stream.stdin.write(capture_frame.tobytes())
except Exception:
pass
def stop() -> gradio.Image:
clear_camera_pool()
return gradio.Image(value = None)