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

Introduce lip syncer weight

Browse Source
This commit is contained in:
henryruhs
2025-06-09 15:02:28 +02:00
parent 076c313842
commit f05f74f5a1
7 changed files with 32 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
facefusion/processors/choices.py
View File

@@ -218,3 +218,4 @@ face_enhancer_blend_range : Sequence[int] = create_int_range(0, 100, 1)
face_enhancer_weight_range : Sequence[float] = create_float_range(0.0, 1.0, 0.05) face_enhancer_weight_range : Sequence[float] = create_float_range(0.0, 1.0, 0.05)
frame_colorizer_blend_range : Sequence[int] = create_int_range(0, 100, 1) frame_colorizer_blend_range : Sequence[int] = create_int_range(0, 100, 1)
frame_enhancer_blend_range : Sequence[int] = create_int_range(0, 100, 1) frame_enhancer_blend_range : Sequence[int] = create_int_range(0, 100, 1)
lip_syncer_weight_range : Sequence[float] = create_float_range(0.0, 1.0, 0.05)

6
facefusion/processors/modules/lip_syncer.py
View File

@@ -9,6 +9,7 @@ import facefusion.jobs.job_manager
import facefusion.jobs.job_store import facefusion.jobs.job_store
import facefusion.processors.core as processors import facefusion.processors.core as processors
from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, video_manager, voice_extractor, wording from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, video_manager, voice_extractor, wording
from facefusion.common_helper import create_float_metavar
from facefusion.audio import create_empty_audio_frame, get_voice_frame, read_static_voice from facefusion.audio import create_empty_audio_frame, get_voice_frame, read_static_voice
from facefusion.common_helper import get_first from facefusion.common_helper import get_first
from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
@@ -94,11 +95,13 @@ def register_args(program : ArgumentParser) -> None:
group_processors = find_argument_group(program, 'processors') group_processors = find_argument_group(program, 'processors')
if group_processors: if group_processors:
group_processors.add_argument('--lip-syncer-model', help = wording.get('help.lip_syncer_model'), default = config.get_str_value('processors', 'lip_syncer_model', 'wav2lip_gan_96'), choices = processors_choices.lip_syncer_models) group_processors.add_argument('--lip-syncer-model', help = wording.get('help.lip_syncer_model'), default = config.get_str_value('processors', 'lip_syncer_model', 'wav2lip_gan_96'), choices = processors_choices.lip_syncer_models)
facefusion.jobs.job_store.register_step_keys([ 'lip_syncer_model' ]) group_processors.add_argument('--lip-syncer-weight', help = wording.get('help.lip_syncer_weight'), type = float, default = config.get_float_value('processors', 'lip_syncer_weight', '0.5'), choices = processors_choices.lip_syncer_weight_range, metavar = create_float_metavar(processors_choices.lip_syncer_weight_range))
facefusion.jobs.job_store.register_step_keys([ 'lip_syncer_model', 'lip_syncer_weight' ])
def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None: def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
apply_state_item('lip_syncer_model', args.get('lip_syncer_model')) apply_state_item('lip_syncer_model', args.get('lip_syncer_model'))
apply_state_item('lip_syncer_weight', args.get('lip_syncer_weight'))
def pre_check() -> bool: def pre_check() -> bool:
@@ -186,6 +189,7 @@ def prepare_audio_frame(temp_audio_frame : AudioFrame) -> AudioFrame:
temp_audio_frame = numpy.maximum(numpy.exp(-5 * numpy.log(10)), temp_audio_frame) temp_audio_frame = numpy.maximum(numpy.exp(-5 * numpy.log(10)), temp_audio_frame)
temp_audio_frame = numpy.log10(temp_audio_frame) * 1.6 + 3.2 temp_audio_frame = numpy.log10(temp_audio_frame) * 1.6 + 3.2
temp_audio_frame = temp_audio_frame.clip(-4, 4).astype(numpy.float32) temp_audio_frame = temp_audio_frame.clip(-4, 4).astype(numpy.float32)
temp_audio_frame = temp_audio_frame * (state_manager.get_item('lip_syncer_weight') * 2.0)
temp_audio_frame = numpy.expand_dims(temp_audio_frame, axis = (0, 1)) temp_audio_frame = numpy.expand_dims(temp_audio_frame, axis = (0, 1))
return temp_audio_frame return temp_audio_frame

3
facefusion/processors/types.py
View File

@@ -103,7 +103,8 @@ ProcessorStateKey = Literal\
'frame_colorizer_blend', 'frame_colorizer_blend',
'frame_enhancer_model', 'frame_enhancer_model',
'frame_enhancer_blend', 'frame_enhancer_blend',
'lip_syncer_model' 'lip_syncer_model',
'lip_syncer_weight'
] ]
ProcessorState = TypedDict('ProcessorState', ProcessorState = TypedDict('ProcessorState',
{ {

25
facefusion/uis/components/lip_syncer_options.py
View File

@@ -1,18 +1,21 @@
from typing import List, Optional from typing import List, Optional, Tuple
import gradio import gradio
from facefusion import state_manager, wording from facefusion import state_manager, wording
from facefusion.common_helper import calc_float_step
from facefusion.processors import choices as processors_choices from facefusion.processors import choices as processors_choices
from facefusion.processors.core import load_processor_module from facefusion.processors.core import load_processor_module
from facefusion.processors.types import LipSyncerModel from facefusion.processors.types import LipSyncerModel
from facefusion.uis.core import get_ui_component, register_ui_component from facefusion.uis.core import get_ui_component, register_ui_component
LIP_SYNCER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None LIP_SYNCER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
LIP_SYNCER_WEIGHT_SLIDER : Optional[gradio.Slider] = None
def render() -> None: def render() -> None:
global LIP_SYNCER_MODEL_DROPDOWN global LIP_SYNCER_MODEL_DROPDOWN
global LIP_SYNCER_WEIGHT_SLIDER
has_lip_syncer = 'lip_syncer' in state_manager.get_item('processors') has_lip_syncer = 'lip_syncer' in state_manager.get_item('processors')
LIP_SYNCER_MODEL_DROPDOWN = gradio.Dropdown( LIP_SYNCER_MODEL_DROPDOWN = gradio.Dropdown(
@@ -21,20 +24,30 @@ def render() -> None:
value = state_manager.get_item('lip_syncer_model'), value = state_manager.get_item('lip_syncer_model'),
visible = has_lip_syncer visible = has_lip_syncer
) )
LIP_SYNCER_WEIGHT_SLIDER = gradio.Slider(
label = wording.get('uis.lip_syncer_weight_slider'),
value = state_manager.get_item('lip_syncer_weight'),
step = calc_float_step(processors_choices.lip_syncer_weight_range),
minimum = processors_choices.lip_syncer_weight_range[0],
maximum = processors_choices.lip_syncer_weight_range[-1],
visible = has_lip_syncer
)
register_ui_component('lip_syncer_model_dropdown', LIP_SYNCER_MODEL_DROPDOWN) register_ui_component('lip_syncer_model_dropdown', LIP_SYNCER_MODEL_DROPDOWN)
register_ui_component('lip_syncer_weight_slider', LIP_SYNCER_WEIGHT_SLIDER)
def listen() -> None: def listen() -> None:
LIP_SYNCER_MODEL_DROPDOWN.change(update_lip_syncer_model, inputs = LIP_SYNCER_MODEL_DROPDOWN, outputs = LIP_SYNCER_MODEL_DROPDOWN) LIP_SYNCER_MODEL_DROPDOWN.change(update_lip_syncer_model, inputs = LIP_SYNCER_MODEL_DROPDOWN, outputs = LIP_SYNCER_MODEL_DROPDOWN)
LIP_SYNCER_WEIGHT_SLIDER.release(update_lip_syncer_weight, inputs = LIP_SYNCER_WEIGHT_SLIDER)
processors_checkbox_group = get_ui_component('processors_checkbox_group') processors_checkbox_group = get_ui_component('processors_checkbox_group')
if processors_checkbox_group: if processors_checkbox_group:
processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = LIP_SYNCER_MODEL_DROPDOWN) processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [ LIP_SYNCER_MODEL_DROPDOWN, LIP_SYNCER_WEIGHT_SLIDER ])
def remote_update(processors : List[str]) -> gradio.Dropdown: def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Slider]:
has_lip_syncer = 'lip_syncer' in processors has_lip_syncer = 'lip_syncer' in processors
return gradio.Dropdown(visible = has_lip_syncer) return gradio.Dropdown(visible = has_lip_syncer), gradio.Slider(visible = has_lip_syncer)
def update_lip_syncer_model(lip_syncer_model : LipSyncerModel) -> gradio.Dropdown: def update_lip_syncer_model(lip_syncer_model : LipSyncerModel) -> gradio.Dropdown:
@@ -45,3 +58,7 @@ def update_lip_syncer_model(lip_syncer_model : LipSyncerModel) -> gradio.Dropdow
if lip_syncer_module.pre_check(): if lip_syncer_module.pre_check():
return gradio.Dropdown(value = state_manager.get_item('lip_syncer_model')) return gradio.Dropdown(value = state_manager.get_item('lip_syncer_model'))
return gradio.Dropdown() return gradio.Dropdown()
def update_lip_syncer_weight(lip_syncer_weight : float) -> None:
state_manager.set_item('lip_syncer_weight', lip_syncer_weight)

1
facefusion/uis/components/preview.py
View File

@@ -131,6 +131,7 @@ def listen() -> None:
'face_enhancer_weight_slider', 'face_enhancer_weight_slider',
'frame_colorizer_blend_slider', 'frame_colorizer_blend_slider',
'frame_enhancer_blend_slider', 'frame_enhancer_blend_slider',
'lip_syncer_weight_slider',
'reference_face_distance_slider', 'reference_face_distance_slider',
'face_selector_age_range_slider', 'face_selector_age_range_slider',
'face_mask_blur_slider', 'face_mask_blur_slider',

1
facefusion/uis/types.py
View File

@@ -61,6 +61,7 @@ ComponentName = Literal\
'frame_enhancer_model_dropdown', 'frame_enhancer_model_dropdown',
'job_list_job_status_checkbox_group', 'job_list_job_status_checkbox_group',
'lip_syncer_model_dropdown', 'lip_syncer_model_dropdown',
'lip_syncer_weight_slider',
'output_image', 'output_image',
'output_video', 'output_video',
'output_video_fps_slider', 'output_video_fps_slider',

1
facefusion/wording.py
View File

@@ -303,6 +303,7 @@ WORDING : Dict[str, Any] =\
'job_runner_job_action_dropdown': 'JOB ACTION', 'job_runner_job_action_dropdown': 'JOB ACTION',
'job_runner_job_id_dropdown': 'JOB ID', 'job_runner_job_id_dropdown': 'JOB ID',
'lip_syncer_model_dropdown': 'LIP SYNCER MODEL', 'lip_syncer_model_dropdown': 'LIP SYNCER MODEL',
'lip_syncer_weight_slider': 'LIP SYNCER WEIGHT',
'log_level_dropdown': 'LOG LEVEL', 'log_level_dropdown': 'LOG LEVEL',
'output_audio_encoder_dropdown': 'OUTPUT AUDIO ENCODER', 'output_audio_encoder_dropdown': 'OUTPUT AUDIO ENCODER',
'output_audio_quality_slider': 'OUTPUT AUDIO QUALITY', 'output_audio_quality_slider': 'OUTPUT AUDIO QUALITY',