facefusion/tests/test_ffmpeg.py
Henry Ruhs 7609df6747
Next (#436)
* Rename landmark 5 variables

* Mark as NEXT

* Render tabs for multiple ui layout usage

* Allow many face detectors at once, Add face detector tweaks

* Remove face detector tweaks for now (kinda placebo)

* Fix lint issues

* Allow rendering the landmark-5 and landmark-5/68 via debugger

* Fix naming

* Convert face landmark based on confidence score

* Convert face landmark based on confidence score

* Add scrfd face detector model (#397)

* Add scrfd face detector model

* Switch to scrfd_2.5g.onnx model

* Just some renaming

* Downgrade OpenCV, Add SYSTEM_VERSION_COMPAT=0 for MacOS

* Improve naming

* prepare detect frame outside of semaphore

* Feat/process manager (#399)

* Minor naming

* Introduce process manager to start and stop

* Introduce process manager to start and stop

* Introduce process manager to start and stop

* Introduce process manager to start and stop

* Introduce process manager to start and stop

* Remove useless test for now

* Avoid useless variables

* Show stop once is_processing is True

* Allow to stop ffmpeg processing too

* Implement output image resolution (#403)

* Implement output image resolution

* Reorder code

* Simplify output logic and therefore fix bug

* Frame-enhancer-onnx (#404)

* changes

* changes

* changes

* changes

* add models

* update workflow

* Some cleanup

* Some cleanup

* Feat/frame enhancer polishing (#410)

* Some cleanup

* Polish the frame enhancer

* Frame Enhancer: Add more models, optimize processing

* Minor changes

* Improve readability of create_tile_frames and merge_tile_frames

* We don't have enough models yet

* Feat/face landmarker score (#413)

* Introduce face landmarker score

* Fix testing

* Fix testing

* Use release for score related sliders

* Reduce face landmark fallbacks

* Scores and landmarks in Face dict, Change color-theme in face debugger

* Scores and landmarks in Face dict, Change color-theme in face debugger

* Fix some naming

* Add 8K support (for whatever reasons)

* Fix testing

* Using get() for face.landmarks

* Introduce statistics

* More statistics

* Limit the histogram equalization

* Enable queue() for default layout

* Improve copy_image()

* Fix error when switching detector model

* Always set UI values with globals if possible

* Use different logic for output image and output video resolutions

* Enforce re-download if file size is off

* Remove unused method

* Remove unused method

* Remove unused warning filter

* Improved output path normalization (#419)

* Handle some exceptions

* Handle some exceptions

* Cleanup

* Prevent countless thread locks

* Listen to user feedback

* Fix webp edge case

* Feat/cuda device detection (#424)

* Introduce cuda device detection

* Introduce cuda device detection

* it's gtx

* Move logic to run_nvidia_smi()

* Finalize execution device naming

* Finalize execution device naming

* Merge execution_helper.py to execution.py

* Undo lowercase of values

* Undo lowercase of values

* Finalize naming

* Add missing entry to ini

* fix lip_syncer preview (#426)

* fix lip_syncer preview

* change

* Refresh preview on trim changes

* Cleanup frame enhancers and remove useless scale in merge_video() (#428)

* Keep lips over the whole video once lip syncer is enabled (#430)

* Keep lips over the whole video once lip syncer is enabled

* changes

* changes

* Fix spacing

* Use empty audio frame on silence

* Use empty audio frame on silence

* Fix ConfigParser encoding (#431)

facefusion.ini is UTF8 encoded but config.py doesn't specify encoding which results in corrupted entries when non english characters are used. 

Affected entries:
source_paths
target_path
output_path

* Adjust spacing

* Improve the GTX 16 series detection

* Use general exception to catch ParseError

* Use general exception to catch ParseError

* Host frame enhancer models4

* Use latest onnxruntime

* Minor changes in benchmark UI

* Different approach to cancel ffmpeg process

* Add support for amd amf encoders (#433)

* Add amd_amf encoders

* remove -rc cqp from amf encoder parameters

* Improve terminal output, move success messages to debug mode

* Improve terminal output, move success messages to debug mode

* Minor update

* Minor update

* onnxruntime 1.17.1 matches cuda 12.2

* Feat/improved scaling (#435)

* Prevent useless temp upscaling, Show resolution and fps in terminal output

* Remove temp frame quality

* Remove temp frame quality

* Tiny cleanup

* Default back to png for temp frames, Remove pix_fmt from frame extraction due mjpeg error

* Fix inswapper fallback by onnxruntime

* Fix inswapper fallback by major onnxruntime

* Fix inswapper fallback by major onnxruntime

* Add testing for vision restrict methods

* Fix left / right face mask regions, add left-ear and right-ear

* Flip right and left again

* Undo ears - does not work with box mask

* Prepare next release

* Fix spacing

* 100% quality when using jpg for temp frames

* Use span_kendata_x4 as default as of speed

* benchmark optimal tile and pad

* Undo commented out code

* Add real_esrgan_x4_fp16 model

* Be strict when using many face detectors

---------

Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
Co-authored-by: aldemoth <159712934+aldemoth@users.noreply.github.com>
2024-03-14 19:56:54 +01:00

114 lines
3.8 KiB
Python

import glob
import subprocess
import pytest
import facefusion.globals
from facefusion import process_manager
from facefusion.filesystem import get_temp_directory_path, create_temp, clear_temp
from facefusion.download import conditional_download
from facefusion.ffmpeg import extract_frames, read_audio_buffer
@pytest.fixture(scope = 'module', autouse = True)
def before_all() -> None:
process_manager.start()
conditional_download('.assets/examples',
[
'https://github.com/facefusion/facefusion-assets/releases/download/examples/source.jpg',
'https://github.com/facefusion/facefusion-assets/releases/download/examples/source.mp3',
'https://github.com/facefusion/facefusion-assets/releases/download/examples/target-240p.mp4'
])
subprocess.run([ 'ffmpeg', '-i', '.assets/examples/source.mp3', '.assets/examples/source.wav' ])
subprocess.run([ 'ffmpeg', '-i', '.assets/examples/target-240p.mp4', '-vf', 'fps=25', '.assets/examples/target-240p-25fps.mp4' ])
subprocess.run([ 'ffmpeg', '-i', '.assets/examples/target-240p.mp4', '-vf', 'fps=30', '.assets/examples/target-240p-30fps.mp4' ])
subprocess.run([ 'ffmpeg', '-i', '.assets/examples/target-240p.mp4', '-vf', 'fps=60', '.assets/examples/target-240p-60fps.mp4' ])
@pytest.fixture(scope = 'function', autouse = True)
def before_each() -> None:
facefusion.globals.trim_frame_start = None
facefusion.globals.trim_frame_end = None
facefusion.globals.temp_frame_format = 'jpg'
def test_extract_frames() -> None:
target_paths =\
[
'.assets/examples/target-240p-25fps.mp4',
'.assets/examples/target-240p-30fps.mp4',
'.assets/examples/target-240p-60fps.mp4'
]
for target_path in target_paths:
temp_directory_path = get_temp_directory_path(target_path)
create_temp(target_path)
assert extract_frames(target_path, '452x240', 30.0) is True
assert len(glob.glob1(temp_directory_path, '*.jpg')) == 324
clear_temp(target_path)
def test_extract_frames_with_trim_start() -> None:
facefusion.globals.trim_frame_start = 224
data_provider =\
[
('.assets/examples/target-240p-25fps.mp4', 55),
('.assets/examples/target-240p-30fps.mp4', 100),
('.assets/examples/target-240p-60fps.mp4', 212)
]
for target_path, frame_total in data_provider:
temp_directory_path = get_temp_directory_path(target_path)
create_temp(target_path)
assert extract_frames(target_path, '452x240', 30.0) is True
assert len(glob.glob1(temp_directory_path, '*.jpg')) == frame_total
clear_temp(target_path)
def test_extract_frames_with_trim_start_and_trim_end() -> None:
facefusion.globals.trim_frame_start = 124
facefusion.globals.trim_frame_end = 224
data_provider =\
[
('.assets/examples/target-240p-25fps.mp4', 120),
('.assets/examples/target-240p-30fps.mp4', 100),
('.assets/examples/target-240p-60fps.mp4', 50)
]
for target_path, frame_total in data_provider:
temp_directory_path = get_temp_directory_path(target_path)
create_temp(target_path)
assert extract_frames(target_path, '452x240', 30.0) is True
assert len(glob.glob1(temp_directory_path, '*.jpg')) == frame_total
clear_temp(target_path)
def test_extract_frames_with_trim_end() -> None:
facefusion.globals.trim_frame_end = 100
data_provider =\
[
('.assets/examples/target-240p-25fps.mp4', 120),
('.assets/examples/target-240p-30fps.mp4', 100),
('.assets/examples/target-240p-60fps.mp4', 50)
]
for target_path, frame_total in data_provider:
temp_directory_path = get_temp_directory_path(target_path)
create_temp(target_path)
assert extract_frames(target_path, '426x240', 30.0) is True
assert len(glob.glob1(temp_directory_path, '*.jpg')) == frame_total
clear_temp(target_path)
def test_read_audio_buffer() -> None:
assert isinstance(read_audio_buffer('.assets/examples/source.mp3', 1, 1), bytes)
assert isinstance(read_audio_buffer('.assets/examples/source.wav', 1, 1), bytes)
assert read_audio_buffer('.assets/examples/invalid.mp3', 1, 1) is None