facefusion/tests/test_vision.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

110 lines
6.5 KiB
Python

import subprocess
import pytest
from facefusion.download import conditional_download
from facefusion.vision import detect_image_resolution, restrict_image_resolution, create_image_resolutions, get_video_frame, count_video_frame_total, detect_video_fps, restrict_video_fps, detect_video_resolution, restrict_video_resolution, create_video_resolutions, normalize_resolution, pack_resolution, unpack_resolution
@pytest.fixture(scope = 'module', autouse = True)
def before_all() -> None:
conditional_download('.assets/examples',
[
'https://github.com/facefusion/facefusion-assets/releases/download/examples/source.jpg',
'https://github.com/facefusion/facefusion-assets/releases/download/examples/target-240p.mp4',
'https://github.com/facefusion/facefusion-assets/releases/download/examples/target-1080p.mp4'
])
subprocess.run([ 'ffmpeg', '-i', '.assets/examples/target-240p.mp4', '-vframes', '1', '.assets/examples/target-240p.jpg' ])
subprocess.run([ 'ffmpeg', '-i', '.assets/examples/target-1080p.mp4', '-vframes', '1', '.assets/examples/target-1080p.jpg' ])
subprocess.run([ 'ffmpeg', '-i', '.assets/examples/target-240p.mp4', '-vframes', '1', '-vf', 'transpose=0', '.assets/examples/target-240p-90deg.jpg' ])
subprocess.run([ 'ffmpeg', '-i', '.assets/examples/target-1080p.mp4', '-vframes', '1', '-vf', 'transpose=0', '.assets/examples/target-1080p-90deg.jpg' ])
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' ])
subprocess.run([ 'ffmpeg', '-i', '.assets/examples/target-240p.mp4', '-vf', 'transpose=0', '.assets/examples/target-240p-90deg.mp4' ])
subprocess.run([ 'ffmpeg', '-i', '.assets/examples/target-1080p.mp4', '-vf', 'transpose=0', '.assets/examples/target-1080p-90deg.mp4' ])
def test_detect_image_resolution() -> None:
assert detect_image_resolution('.assets/examples/target-240p.jpg') == (426, 226)
assert detect_image_resolution('.assets/examples/target-240p-90deg.jpg') == (226, 426)
assert detect_image_resolution('.assets/examples/target-1080p.jpg') == (2048, 1080)
assert detect_image_resolution('.assets/examples/target-1080p-90deg.jpg') == (1080, 2048)
assert detect_image_resolution('invalid') is None
def test_restrict_image_resolution() -> None:
assert restrict_image_resolution('.assets/examples/target-1080p.jpg', (426, 226)) == (426, 226)
assert restrict_image_resolution('.assets/examples/target-1080p.jpg', (2048, 1080)) == (2048, 1080)
assert restrict_image_resolution('.assets/examples/target-1080p.jpg', (4096, 2160)) == (2048, 1080)
def test_create_image_resolutions() -> None:
assert create_image_resolutions((426, 226)) == [ '106x56', '212x112', '320x170', '426x226', '640x340', '852x452', '1064x564', '1278x678', '1492x792', '1704x904' ]
assert create_image_resolutions((226, 426)) == [ '56x106', '112x212', '170x320', '226x426', '340x640', '452x852', '564x1064', '678x1278', '792x1492', '904x1704' ]
assert create_image_resolutions((2048, 1080)) == [ '512x270', '1024x540', '1536x810', '2048x1080', '3072x1620', '4096x2160', '5120x2700', '6144x3240', '7168x3780', '8192x4320' ]
assert create_image_resolutions((1080, 2048)) == [ '270x512', '540x1024', '810x1536', '1080x2048', '1620x3072', '2160x4096', '2700x5120', '3240x6144', '3780x7168', '4320x8192' ]
assert create_image_resolutions(None) == []
def test_get_video_frame() -> None:
assert get_video_frame('.assets/examples/target-240p-25fps.mp4') is not None
assert get_video_frame('invalid') is None
def test_count_video_frame_total() -> None:
assert count_video_frame_total('.assets/examples/target-240p-25fps.mp4') == 270
assert count_video_frame_total('.assets/examples/target-240p-30fps.mp4') == 324
assert count_video_frame_total('.assets/examples/target-240p-60fps.mp4') == 648
assert count_video_frame_total('invalid') == 0
def test_detect_video_fps() -> None:
assert detect_video_fps('.assets/examples/target-240p-25fps.mp4') == 25.0
assert detect_video_fps('.assets/examples/target-240p-30fps.mp4') == 30.0
assert detect_video_fps('.assets/examples/target-240p-60fps.mp4') == 60.0
assert detect_video_fps('invalid') is None
def test_restrict_video_fps() -> None:
assert restrict_video_fps('.assets/examples/target-1080p.mp4', 20.0) == 20.0
assert restrict_video_fps('.assets/examples/target-1080p.mp4', 25.0) == 25.0
assert restrict_video_fps('.assets/examples/target-1080p.mp4', 60.0) == 25.0
def test_detect_video_resolution() -> None:
assert detect_video_resolution('.assets/examples/target-240p.mp4') == (426, 226)
assert detect_video_resolution('.assets/examples/target-240p-90deg.mp4') == (226, 426)
assert detect_video_resolution('.assets/examples/target-1080p.mp4') == (2048, 1080)
assert detect_video_resolution('.assets/examples/target-1080p-90deg.mp4') == (1080, 2048)
assert detect_video_resolution('invalid') is None
def test_restrict_video_resolution() -> None:
assert restrict_video_resolution('.assets/examples/target-1080p.mp4', (426, 226)) == (426, 226)
assert restrict_video_resolution('.assets/examples/target-1080p.mp4', (2048, 1080)) == (2048, 1080)
assert restrict_video_resolution('.assets/examples/target-1080p.mp4', (4096, 2160)) == (2048, 1080)
def test_create_video_resolutions() -> None:
assert create_video_resolutions((426, 226)) == [ '426x226', '452x240', '678x360', '904x480', '1018x540', '1358x720', '2036x1080', '2714x1440', '4072x2160', '8144x4320' ]
assert create_video_resolutions((226, 426)) == [ '226x426', '240x452', '360x678', '480x904', '540x1018', '720x1358', '1080x2036', '1440x2714', '2160x4072', '4320x8144' ]
assert create_video_resolutions((2048, 1080)) == [ '456x240', '682x360', '910x480', '1024x540', '1366x720', '2048x1080', '2730x1440', '4096x2160', '8192x4320' ]
assert create_video_resolutions((1080, 2048)) == [ '240x456', '360x682', '480x910', '540x1024', '720x1366', '1080x2048', '1440x2730', '2160x4096', '4320x8192' ]
assert create_video_resolutions(None) == []
def test_normalize_resolution() -> None:
assert normalize_resolution((2.5, 2.5)) == (2, 2)
assert normalize_resolution((3.0, 3.0)) == (4, 4)
assert normalize_resolution((6.5, 6.5)) == (6, 6)
def test_pack_resolution() -> None:
assert pack_resolution((1, 1)) == '0x0'
assert pack_resolution((2, 2)) == '2x2'
def test_unpack_resolution() -> None:
assert unpack_resolution('0x0') == (0, 0)
assert unpack_resolution('2x2') == (2, 2)