Next (#477)

* Add real_hatgan_x4 model

* Mark it as NEXT

* Force download to be executed and exit

* Fix frame per second interpolation

* 5 to 68 landmark (#456)

* changes

* changes

* Adjust model url

* Cleanup 5 to 68 landmark convertion

* Move everything to face analyser

* Introduce matrix only face helper

* Revert facefusion.ini

* Adjust limit due false positive analysis

* changes (#457)

* Use pixel format yuv422p to merge video

* Fix some code

* Minor cleanup

* Add gpen_bfr_1024 and gpen_bfr_2048

* Revert it back to yuv420p due compatibility issues

* Add debug back to ffmpeg

* Add debug back to ffmpeg

* Migrate to conda (#461)

* Migrate from venv to conda

* Migrate from venv to conda

* Message when conda is not activated

* Use release for every slider (#463)

* Use release event handler for every slider

* Move more sliders to release handler

* Move more sliders to release handler

* Add get_ui_components() to simplify code

* Revert some changes on frame slider

* Add the first iteration of a frame colorizer

* Support for the DDColor model

* Improve model file handling

* Improve model file handling part2

* Remove deoldify

* Remove deoldify

* Voice separator (#468)

* changes

* changes

* changes

* changes

* changes

* changes

* Rename audio extractor to voice extractor

* Cosmetic changes

* Cosmetic changes

* Fix fps lowering and boosting

* Fix fps lowering and boosting

* Fix fps lowering and boosting

* Some refactoring for audio.py and some astype() here and there (#470)

* Some refactoring for audio.py and some astype() here and there

* Fix lint

* Spacing

* Add mp3 to benchmark suite for lip syncer testing

* Improve naming

* Adjust chunk size

* Use higher quality

* Revert "Use higher quality"

This reverts commit d32f28757251ecc0f48214073adf54f3631b1289.

* Improve naming in ffmpeg.py

* Simplify code

* Better fps calculation

* Fix naming here and there

* Add back real esrgan x2

* Remove trailing comma

* Update wording and README

* Use semaphore to prevent frame colorizer memory issues

* Revert "Remove deoldify"

This reverts commit bd8034cbc71fe701f78dddec3057dc98593b2162.

* Remove unused type from frame colorizer

* Adjust naming

* Add missing clear of model initializer

* Change nvenc preset mappping to support old FFMPEG 4

* Update onnxruntime to 1.17.1

* Fix lint

* Prepare 2.5.0

* Fix Gradio overrides

* Add Deoldify Artistic back

* Feat/audio refactoring (#476)

* Improve audio naming and variables

* Improve audio naming and variables

* Refactor voice extractor like crazy

* Refactor voice extractor like crazy

* Remove spaces

* Update the usage

---------

Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>

facefusion/ffmpeg.py

@@ -1,20 +1,24 @@
 from typing import List, Optional
+import os
 import subprocess
 import filetype
 
 import facefusion.globals
-from facefusion import process_manager
+from facefusion import logger, process_manager
 from facefusion.typing import OutputVideoPreset, Fps, AudioBuffer
 from facefusion.filesystem import get_temp_frames_pattern, get_temp_output_video_path
+from facefusion.vision import restrict_video_fps
 
 
 def run_ffmpeg(args : List[str]) -> bool:
-	commands = [ 'ffmpeg', '-hide_banner', '-loglevel', 'quiet' ]
+	commands = [ 'ffmpeg', '-hide_banner', '-loglevel', 'error' ]
 	commands.extend(args)
-	process = subprocess.Popen(commands, stdout = subprocess.PIPE)
+	process = subprocess.Popen(commands, stderr = subprocess.PIPE, stdout = subprocess.PIPE)
 
 	while process_manager.is_processing():
 		try:
+			if facefusion.globals.log_level == 'debug':
+				log_debug(process)
 			return process.wait(timeout = 0.5) == 0
 		except subprocess.TimeoutExpired:
 			continue
@@ -27,6 +31,15 @@ def open_ffmpeg(args : List[str]) -> subprocess.Popen[bytes]:
 	return subprocess.Popen(commands, stdin = subprocess.PIPE, stdout = subprocess.PIPE)
 
 
+def log_debug(process : subprocess.Popen[bytes]) -> None:
+	_, stderr = process.communicate()
+	errors = stderr.decode().split(os.linesep)
+
+	for error in errors:
+		if error.strip():
+			logger.debug(error.strip(), __name__.upper())
+
+
 def extract_frames(target_path : str, temp_video_resolution : str, temp_video_fps : Fps) -> bool:
 	trim_frame_start = facefusion.globals.trim_frame_start
 	trim_frame_end = facefusion.globals.trim_frame_end
@@ -46,9 +59,10 @@ def extract_frames(target_path : str, temp_video_resolution : str, temp_video_fp
 
 
 def merge_video(target_path : str, output_video_resolution : str, output_video_fps : Fps) -> bool:
+	temp_video_fps = restrict_video_fps(target_path, output_video_fps)
 	temp_output_video_path = get_temp_output_video_path(target_path)
 	temp_frames_pattern = get_temp_frames_pattern(target_path, '%04d')
-	commands = [ '-hwaccel', 'auto', '-s', str(output_video_resolution), '-r', str(output_video_fps), '-i', temp_frames_pattern, '-c:v', facefusion.globals.output_video_encoder ]
+	commands = [ '-hwaccel', 'auto', '-s', str(output_video_resolution), '-r', str(temp_video_fps), '-i', temp_frames_pattern, '-c:v', facefusion.globals.output_video_encoder ]
 
 	if facefusion.globals.output_video_encoder in [ 'libx264', 'libx265' ]:
 		output_video_compression = round(51 - (facefusion.globals.output_video_quality * 0.51))
@@ -62,7 +76,7 @@ def merge_video(target_path : str, output_video_resolution : str, output_video_f
 	if facefusion.globals.output_video_encoder in [ 'h264_amf', 'hevc_amf' ]:
 		output_video_compression = round(51 - (facefusion.globals.output_video_quality * 0.51))
 		commands.extend([ '-qp_i', str(output_video_compression), '-qp_p', str(output_video_compression), '-quality', map_amf_preset(facefusion.globals.output_video_preset) ])
-	commands.extend([ '-pix_fmt', 'yuv420p', '-colorspace', 'bt709', '-y', temp_output_video_path ])
+	commands.extend([ '-vf', 'framerate=fps=' + str(output_video_fps), '-pix_fmt', 'yuv420p', '-colorspace', 'bt709', '-y', temp_output_video_path ])
 	return run_ffmpeg(commands)
 
 
@@ -79,8 +93,8 @@ def finalize_image(output_path : str, output_image_resolution : str) -> bool:
 	return run_ffmpeg(commands)
 
 
-def read_audio_buffer(target_path : str, sample_rate : int, total_channel : int) -> Optional[AudioBuffer]:
-	commands = [ '-i', target_path, '-vn', '-f', 's16le', '-acodec', 'pcm_s16le', '-ar', str(sample_rate), '-ac', str(total_channel), '-' ]
+def read_audio_buffer(target_path : str, sample_rate : int, channel_total : int) -> Optional[AudioBuffer]:
+	commands = [ '-i', target_path, '-vn', '-f', 's16le', '-acodec', 'pcm_s16le', '-ar', str(sample_rate), '-ac', str(channel_total), '-']
 	process = open_ffmpeg(commands)
 	audio_buffer, _ = process.communicate()
 	if process.returncode == 0:
@@ -106,25 +120,17 @@ def restore_audio(target_path : str, output_path : str, output_video_fps : Fps)
 
 def replace_audio(target_path : str, audio_path : str, output_path : str) -> bool:
 	temp_output_path = get_temp_output_video_path(target_path)
-	commands = [ '-hwaccel', 'auto', '-i', temp_output_path, '-i', audio_path, '-c:v', 'copy', '-af', 'apad', '-shortest', '-map', '0:v:0', '-map', '1:a:0', '-y', output_path ]
+	commands = [ '-hwaccel', 'auto', '-i', temp_output_path, '-i', audio_path, '-c:v', 'copy', '-af', 'apad', '-map', '0:v:0', '-map', '1:a:0', '-shortest', '-y', output_path ]
 	return run_ffmpeg(commands)
 
 
 def map_nvenc_preset(output_video_preset : OutputVideoPreset) -> Optional[str]:
-	if output_video_preset in [ 'ultrafast', 'superfast', 'veryfast' ]:
-		return 'p1'
-	if output_video_preset == 'faster':
-		return 'p2'
-	if output_video_preset == 'fast':
-		return 'p3'
+	if output_video_preset in [ 'ultrafast', 'superfast', 'veryfast', 'faster', 'fast' ]:
+		return 'fast'
 	if output_video_preset == 'medium':
-		return 'p4'
-	if output_video_preset == 'slow':
-		return 'p5'
-	if output_video_preset == 'slower':
-		return 'p6'
-	if output_video_preset == 'veryslow':
-		return 'p7'
+		return 'medium'
+	if output_video_preset in [ 'slow', 'slower', 'veryslow' ]:
+		return 'slow'
 	return None