jones/facefusion
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Feat/more audio settings (#849)

Browse Source 
* Add more audio settings, revamp some ffmpeg commands

* Add more audio settings, revamp some ffmpeg commands

* Add more audio settings, revamp some ffmpeg commands

* Add more audio settings, revamp some ffmpeg commands
This commit is contained in:
Henry Ruhs
2025-01-07 22:10:54 +01:00
committed by henryruhs
parent c5bc7c50a5
commit 5b76f54332
14 changed files with 144 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
facefusion/uis/choices.py
View File

@@ -5,7 +5,7 @@ from facefusion.uis.typing import JobManagerAction, JobRunnerAction, WebcamMode
job_manager_actions : List[JobManagerAction] = [ 'job-create', 'job-submit', 'job-delete', 'job-add-step', 'job-remix-step', 'job-insert-step', 'job-remove-step' ]
job_runner_actions : List[JobRunnerAction] = [ 'job-run', 'job-run-all', 'job-retry', 'job-retry-all' ]
common_options : List[str] = [ 'keep-temp', 'skip-audio' ]
common_options : List[str] = [ 'keep-temp' ]
webcam_modes : List[WebcamMode] = [ 'inline', 'udp', 'v4l2' ]
webcam_resolutions : List[str] = [ '320x240', '640x480', '800x600', '1024x768', '1280x720', '1280x960', '1920x1080', '2560x1440', '3840x2160' ]

2
facefusion/uis/components/benchmark.py
View File

@@ -81,8 +81,8 @@ def start(benchmark_runs : List[str], benchmark_cycles : int) -> Generator[List[
state_manager.init_item('source_paths', [ '.assets/examples/source.jpg', '.assets/examples/source.mp3' ])
state_manager.init_item('face_landmarker_score', 0)
state_manager.init_item('temp_frame_format', 'bmp')
state_manager.init_item('output_audio_volume', 0)
state_manager.init_item('output_video_preset', 'ultrafast')
state_manager.init_item('skip_audio', True)
state_manager.sync_item('execution_providers')
state_manager.sync_item('execution_thread_count')
state_manager.sync_item('execution_queue_count')

4
facefusion/uis/components/common_options.py
View File

@@ -15,8 +15,6 @@ def render() -> None:
if state_manager.get_item('keep_temp'):
common_options.append('keep-temp')
if state_manager.get_item('skip_audio'):
common_options.append('skip-audio')
COMMON_OPTIONS_CHECKBOX_GROUP = gradio.Checkboxgroup(
label = wording.get('uis.common_options_checkbox_group'),
@@ -31,6 +29,4 @@ def listen() -> None:
def update(common_options : List[str]) -> None:
keep_temp = 'keep-temp' in common_options
skip_audio = 'skip-audio' in common_options
state_manager.set_item('keep_temp', keep_temp)
state_manager.set_item('skip_audio', skip_audio)

40
facefusion/uis/components/output_options.py
View File

@@ -13,6 +13,8 @@ from facefusion.vision import create_image_resolutions, create_video_resolutions
OUTPUT_IMAGE_QUALITY_SLIDER : Optional[gradio.Slider] = None
OUTPUT_IMAGE_RESOLUTION_DROPDOWN : Optional[gradio.Dropdown] = None
OUTPUT_AUDIO_ENCODER_DROPDOWN : Optional[gradio.Dropdown] = None
OUTPUT_AUDIO_QUALITY_SLIDER : Optional[gradio.Slider] = None
OUTPUT_AUDIO_VOLUME_SLIDER : Optional[gradio.Slider] = None
OUTPUT_VIDEO_ENCODER_DROPDOWN : Optional[gradio.Dropdown] = None
OUTPUT_VIDEO_PRESET_DROPDOWN : Optional[gradio.Dropdown] = None
OUTPUT_VIDEO_RESOLUTION_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -24,6 +26,8 @@ def render() -> None:
global OUTPUT_IMAGE_QUALITY_SLIDER
global OUTPUT_IMAGE_RESOLUTION_DROPDOWN
global OUTPUT_AUDIO_ENCODER_DROPDOWN
global OUTPUT_AUDIO_QUALITY_SLIDER
global OUTPUT_AUDIO_VOLUME_SLIDER
global OUTPUT_VIDEO_ENCODER_DROPDOWN
global OUTPUT_VIDEO_PRESET_DROPDOWN
global OUTPUT_VIDEO_RESOLUTION_DROPDOWN
@@ -58,6 +62,22 @@ def render() -> None:
value = state_manager.get_item('output_audio_encoder'),
visible = is_video(state_manager.get_item('target_path'))
)
OUTPUT_AUDIO_QUALITY_SLIDER = gradio.Slider(
label = wording.get('uis.output_audio_quality_slider'),
value = state_manager.get_item('output_audio_quality'),
step = calc_int_step(facefusion.choices.output_audio_quality_range),
minimum = facefusion.choices.output_audio_quality_range[0],
maximum = facefusion.choices.output_audio_quality_range[-1],
visible = is_video(state_manager.get_item('target_path'))
)
OUTPUT_AUDIO_VOLUME_SLIDER = gradio.Slider(
label = wording.get('uis.output_audio_volume_slider'),
value = state_manager.get_item('output_audio_volume'),
step = calc_int_step(facefusion.choices.output_audio_volume_range),
minimum = facefusion.choices.output_audio_volume_range[0],
maximum = facefusion.choices.output_audio_volume_range[-1],
visible = is_video(state_manager.get_item('target_path'))
)
OUTPUT_VIDEO_ENCODER_DROPDOWN = gradio.Dropdown(
label = wording.get('uis.output_video_encoder_dropdown'),
choices = facefusion.choices.output_video_encoders,
@@ -99,6 +119,8 @@ def listen() -> None:
OUTPUT_IMAGE_QUALITY_SLIDER.release(update_output_image_quality, inputs = OUTPUT_IMAGE_QUALITY_SLIDER)
OUTPUT_IMAGE_RESOLUTION_DROPDOWN.change(update_output_image_resolution, inputs = OUTPUT_IMAGE_RESOLUTION_DROPDOWN)
OUTPUT_AUDIO_ENCODER_DROPDOWN.change(update_output_audio_encoder, inputs = OUTPUT_AUDIO_ENCODER_DROPDOWN)
OUTPUT_AUDIO_QUALITY_SLIDER.release(update_output_audio_quality, inputs = OUTPUT_AUDIO_QUALITY_SLIDER)
OUTPUT_AUDIO_VOLUME_SLIDER.release(update_output_audio_volume, inputs = OUTPUT_AUDIO_VOLUME_SLIDER)
OUTPUT_VIDEO_ENCODER_DROPDOWN.change(update_output_video_encoder, inputs = OUTPUT_VIDEO_ENCODER_DROPDOWN)
OUTPUT_VIDEO_PRESET_DROPDOWN.change(update_output_video_preset, inputs = OUTPUT_VIDEO_PRESET_DROPDOWN)
OUTPUT_VIDEO_QUALITY_SLIDER.release(update_output_video_quality, inputs = OUTPUT_VIDEO_QUALITY_SLIDER)
@@ -111,22 +133,22 @@ def listen() -> None:
'target_video'
]):
for method in [ 'upload', 'change', 'clear' ]:
getattr(ui_component, method)(remote_update, outputs = [ OUTPUT_IMAGE_QUALITY_SLIDER, OUTPUT_IMAGE_RESOLUTION_DROPDOWN, OUTPUT_AUDIO_ENCODER_DROPDOWN, OUTPUT_VIDEO_ENCODER_DROPDOWN, OUTPUT_VIDEO_PRESET_DROPDOWN, OUTPUT_VIDEO_QUALITY_SLIDER, OUTPUT_VIDEO_RESOLUTION_DROPDOWN, OUTPUT_VIDEO_FPS_SLIDER ])
getattr(ui_component, method)(remote_update, outputs = [ OUTPUT_IMAGE_QUALITY_SLIDER, OUTPUT_IMAGE_RESOLUTION_DROPDOWN, OUTPUT_AUDIO_ENCODER_DROPDOWN, OUTPUT_AUDIO_QUALITY_SLIDER, OUTPUT_AUDIO_VOLUME_SLIDER, OUTPUT_VIDEO_ENCODER_DROPDOWN, OUTPUT_VIDEO_PRESET_DROPDOWN, OUTPUT_VIDEO_QUALITY_SLIDER, OUTPUT_VIDEO_RESOLUTION_DROPDOWN, OUTPUT_VIDEO_FPS_SLIDER ])
def remote_update() -> Tuple[gradio.Slider, gradio.Dropdown, gradio.Dropdown, gradio.Dropdown, gradio.Dropdown, gradio.Slider, gradio.Dropdown, gradio.Slider]:
def remote_update() -> Tuple[gradio.Slider, gradio.Dropdown, gradio.Dropdown, gradio.Slider, gradio.Slider, gradio.Dropdown, gradio.Dropdown, gradio.Slider, gradio.Dropdown, gradio.Slider]:
if is_image(state_manager.get_item('target_path')):
output_image_resolution = detect_image_resolution(state_manager.get_item('target_path'))
output_image_resolutions = create_image_resolutions(output_image_resolution)
state_manager.set_item('output_image_resolution', pack_resolution(output_image_resolution))
return gradio.Slider(visible = True), gradio.Dropdown(value = state_manager.get_item('output_image_resolution'), choices = output_image_resolutions, visible = True), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False)
return gradio.Slider(visible = True), gradio.Dropdown(value = state_manager.get_item('output_image_resolution'), choices = output_image_resolutions, visible = True), gradio.Dropdown(visible = False), gradio.Slider(visible = False), gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False)
if is_video(state_manager.get_item('target_path')):
output_video_resolution = detect_video_resolution(state_manager.get_item('target_path'))
output_video_resolutions = create_video_resolutions(output_video_resolution)
state_manager.set_item('output_video_resolution', pack_resolution(output_video_resolution))
state_manager.set_item('output_video_fps', detect_video_fps(state_manager.get_item('target_path')))
return gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = True), gradio.Dropdown(visible = True), gradio.Dropdown(visible = True), gradio.Slider(visible = True), gradio.Dropdown(value = state_manager.get_item('output_video_resolution'), choices = output_video_resolutions, visible = True), gradio.Slider(value = state_manager.get_item('output_video_fps'), visible = True)
return gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False)
return gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = True), gradio.Slider(visible = True), gradio.Slider(visible = True), gradio.Dropdown(visible = True), gradio.Dropdown(visible = True), gradio.Slider(visible = True), gradio.Dropdown(value = state_manager.get_item('output_video_resolution'), choices = output_video_resolutions, visible = True), gradio.Slider(value = state_manager.get_item('output_video_fps'), visible = True)
return gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False), gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False)
def update_output_image_quality(output_image_quality : float) -> None:
@@ -141,6 +163,14 @@ def update_output_audio_encoder(output_audio_encoder : OutputAudioEncoder) -> No
state_manager.set_item('output_audio_encoder', output_audio_encoder)
def update_output_audio_quality(output_audio_quality : float) -> None:
state_manager.set_item('output_audio_quality', int(output_audio_quality))
def update_output_audio_volume(output_audio_volume: float) -> None:
state_manager.set_item('output_audio_volume', int(output_audio_volume))
def update_output_video_encoder(output_video_encoder : OutputVideoEncoder) -> None:
state_manager.set_item('output_video_encoder', output_video_encoder)