Files
facefusion/tests/test_vision.py
T
b60ea40d26 3.8.0 (#1212)
* mark as next

* unify the dependency checks in pre_check and add ffprobe (#1181)

* drop keep_temp and the common options component (#1180)

Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

* introduce ffprobe and ffprobe_builder (#1182)

* introduce ffprobe and ffprobe_builder

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* introduce ffprobe and ffprobe_builder

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

* probe video metadata via ffprobe in vision (#1184)

* probe video metadata via ffprobe in vision

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* probe video metadata via ffprobe in vision

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

* adopt the workflow task vocabulary from next major (#1185)

Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

* introduce workflow-mode and workflow-strategy like next major (#1187)

Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

* restrict hdr color transfer and tag the merge output as bt709 (#1188)

* restrict hdr color transfer and tag the merge output as bt709

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* restrict hdr color transfer and tag the merge output as bt709

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* full video migration

* compose the hdr fixture via the builder chain

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* compose the test fixtures via the builder and run_ffmpeg

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

* compose every test fixture via the builder and run_ffmpeg (#1189)

* compose every test fixture via the builder and run_ffmpeg

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* use loops in tests for ffmpeg stuff

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

* New Video Manager (#1191)

* tiny adjustment for tests

* address the review on the video manager

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* introduce the stream strategy for the video workflow (#1192)

* introduce the stream strategy for the video workflow

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* address the review on the stream strategy

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

* annotate the changes for review

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* annotate the new tests for review

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* match the temp pixel format help to the locale style

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* question the set_input_seek naming

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* question the reader and writer keys

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* drop the review annotations from the encoder mapping tests

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* drop the review annotations from the thread count tests

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* drop the review annotations from the ui files

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* capture the open review questions as annotations

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

* drop the settled annotations from the types

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbcd6VWCiU4BQP1gywPr2a

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

* switch to ffmpeg.style for audio.py

* remove todos that were never needed

* fix for ffmpeg7

* Add frame_store module (#1194)

* add frame_store module

* rename and change tests

* rename and update tests

* route window read through frame_store (#1196)

* route window read through frame_store

* update proper id

* restore todos

* restore todos

* go v4 style for workflow (#1197)

* go v4 style for workflow

* remove some todos

* route chunk read through frame_store (#1198)

* vision integration

* Deleted read_video_chunk + read_static_video_chunk

* margin decouple (#1199)

* fix windows CI fail (#1200)

* Cleanup Part1 (#1201)

* remove some todos, improve video manager, simplify ffmpeg commands and more

* do more

* remove thread count for filters

* Cleanup Part 2 (#1202)

* tons of renaming

* tons of renaming

* multi reader approach

* bring tests to an okay-ish state

* bring drain back

* improve read_video_frame speed

* rename method

* move variables

* seek video reader only when trim frame start is larger 0

* make stream the default

* Cleanup/part 3 (#1203)

* remove todo

* sort out workflow, to match upcoming v4

* remove look ahead

* remove core namespace again

* Revamp execution provider overrides/adjustments (#1206)

* Split provider hooks into override/adjust with cached CoreML base

Replace the single resolve_inference_providers processor hook with two:
override_inference_providers (full replacement) and adjust_inference_providers
(merge options onto the base providers built by create_inference_providers).
This lets CoreML processors inherit ModelCacheDirectory + SpecializationStrategy
from the base while layering ModelFormat/MLComputeUnits on top.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HTQCZiYjJyUX11bDpbRSiB

* fix caching for execution provider by having override and adjust ways

* fix caching for execution provider by having override and adjust ways

* fix lint

* use proper pytest fixtures

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix update preview bug (#1205)

* fix update preview bug

* fix update preview bug

* remove guard

* add is_vision_frame

* Restrict the preview frame slider and the reader seek to the last frame index (#1207)

* fix index bug

* fix rounding bug

* avoid tobytes copy (#1208)

* beautify tests

* hide ffmpeg warnings

* simplify process_stream_frame

* Use is vision frame everywhere (#1210)

* use is_vision_frame everywhere

* fix hash

* fix lint

* fix hash creation in face store

* that model does not exist

* update workflow ffmpeg

* guard workflow (#1211)

* bump version and dependencies

* Update preview

* switch workflow strategy to disk|memory

* update preview

* update preview

* fix wording

* last minute change workflow position

* adjust wording

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
2026-07-30 22:25:09 +02:00

254 lines
11 KiB
Python

import os
import numpy
import pytest
from facefusion import ffmpeg, ffmpeg_builder, process_manager
from facefusion.common_helper import is_linux
from facefusion.download import conditional_download
from facefusion.vision import calculate_histogram_difference, count_trim_frame_total, count_video_frame_total, detect_image_resolution, detect_video_duration, detect_video_fps, detect_video_resolution, match_frame_color, normalize_resolution, pack_resolution, predict_video_frame_total, read_image, read_video_frame, restrict_image_resolution, restrict_trim_frame, restrict_video_fps, restrict_video_resolution, scale_resolution, select_video_frames, unpack_resolution, write_image
from .helper import get_test_example_file, get_test_examples_directory, get_test_output_file, prepare_test_output_directory
@pytest.fixture(scope = 'module', autouse = True)
def before_all() -> None:
process_manager.start()
conditional_download(get_test_examples_directory(),
[
'https://github.com/facefusion/facefusion-assets/releases/download/examples-3.0.0/source.jpg',
'https://github.com/facefusion/facefusion-assets/releases/download/examples-3.0.0/target-240p.mp4',
'https://github.com/facefusion/facefusion-assets/releases/download/examples-3.0.0/target-1080p.mp4'
])
for target_name in [ 'target-240p', 'target-1080p' ]:
ffmpeg.run_ffmpeg(
ffmpeg_builder.chain(
ffmpeg_builder.set_input(get_test_example_file(target_name + '.mp4')),
[
'-vframes',
'1'
],
ffmpeg_builder.set_output(get_test_example_file(target_name + '.jpg'))
)
)
ffmpeg.run_ffmpeg(
ffmpeg_builder.chain(
ffmpeg_builder.set_input(get_test_example_file('target-240p.mp4')),
[
'-vframes',
'1'
],
ffmpeg_builder.set_output(get_test_example_file('目标-240p.webp'))
)
)
ffmpeg.run_ffmpeg(
ffmpeg_builder.chain(
ffmpeg_builder.set_input(get_test_example_file('target-240p.mp4')),
[
'-vframes',
'1'
],
[
'-vf',
'hue=s=0'
],
ffmpeg_builder.set_output(get_test_example_file('target-240p-0sat.jpg'))
)
)
for target_name in [ 'target-240p', 'target-1080p' ]:
ffmpeg.run_ffmpeg(
ffmpeg_builder.chain(
ffmpeg_builder.set_input(get_test_example_file(target_name + '.mp4')),
[
'-vframes',
'1'
],
[
'-vf',
'transpose=0'
],
ffmpeg_builder.set_output(get_test_example_file(target_name + '-90deg.jpg'))
)
)
for video_fps in [ 25, 30, 60 ]:
ffmpeg.run_ffmpeg(
ffmpeg_builder.chain(
ffmpeg_builder.set_input(get_test_example_file('target-240p.mp4')),
ffmpeg_builder.set_video_fps(video_fps),
ffmpeg_builder.set_output(get_test_example_file('target-240p-' + str(video_fps) + 'fps.mp4'))
)
)
for target_name in [ 'target-240p', 'target-1080p' ]:
ffmpeg.run_ffmpeg(
ffmpeg_builder.chain(
ffmpeg_builder.set_input(get_test_example_file(target_name + '.mp4')),
[
'-vf',
'transpose=0'
],
ffmpeg_builder.set_output(get_test_example_file(target_name + '-90deg.mp4'))
)
)
@pytest.fixture(scope = 'function', autouse = True)
def before_each() -> None:
prepare_test_output_directory()
def test_read_image() -> None:
assert read_image(get_test_example_file('target-240p.jpg')).shape == (226, 426, 3)
assert read_image(get_test_example_file('目标-240p.webp')).shape == (226, 426, 3)
assert read_image('invalid') is None
def test_write_image() -> None:
vision_frame = read_image(get_test_example_file('target-240p.jpg'))
assert write_image(get_test_output_file('target-240p.jpg'), vision_frame) is True
assert write_image(get_test_output_file('目标-240p.webp'), vision_frame) is True
def test_detect_image_resolution() -> None:
assert detect_image_resolution(get_test_example_file('target-240p.jpg')) == (426, 226)
assert detect_image_resolution(get_test_example_file('target-240p-90deg.jpg')) == (226, 426)
assert detect_image_resolution(get_test_example_file('target-1080p.jpg')) == (2048, 1080)
assert detect_image_resolution(get_test_example_file('target-1080p-90deg.jpg')) == (1080, 2048)
assert detect_image_resolution('invalid') is None
def test_restrict_image_resolution() -> None:
assert restrict_image_resolution(get_test_example_file('target-1080p.jpg'), (426, 226)) == (426, 226)
assert restrict_image_resolution(get_test_example_file('target-1080p.jpg'), (2048, 1080)) == (2048, 1080)
assert restrict_image_resolution(get_test_example_file('target-1080p.jpg'), (4096, 2160)) == (2048, 1080)
def test_read_video_frame() -> None:
target_path = get_test_example_file('target-240p-25fps.mp4')
assert read_video_frame(target_path).shape == (226, 426, 3)
assert numpy.array_equal(read_video_frame(target_path, 49), select_video_frames(target_path, 49, 5)[5])
assert numpy.array_equal(read_video_frame(target_path, 50), select_video_frames(target_path, 50, 5)[5])
assert numpy.array_equal(read_video_frame(target_path, 51), select_video_frames(target_path, 51, 5)[5])
assert read_video_frame('invalid') is None
def test_select_video_frames() -> None:
assert len(select_video_frames(get_test_example_file('target-240p-25fps.mp4'), 50, 5)) == 11
assert len(select_video_frames(get_test_example_file('target-240p-25fps.mp4'), 1, 5)) == 11
assert len(select_video_frames(get_test_example_file('target-240p-25fps.mp4'), 269, 5)) == 11
assert select_video_frames('invalid', 50, 5) == []
def test_count_video_frame_total() -> None:
assert count_video_frame_total(get_test_example_file('target-240p-25fps.mp4')) == 270
assert count_video_frame_total(get_test_example_file('target-240p-30fps.mp4')) == 324
assert count_video_frame_total(get_test_example_file('target-240p-60fps.mp4')) == 648
assert count_video_frame_total('invalid') == 0
def test_predict_video_frame_total() -> None:
assert predict_video_frame_total(get_test_example_file('target-240p-25fps.mp4'), 12.5, 0, 100) == 50
assert predict_video_frame_total(get_test_example_file('target-240p-25fps.mp4'), 25, 0, 100) == 100
assert predict_video_frame_total(get_test_example_file('target-240p-25fps.mp4'), 25, 0, 200) == 200
assert predict_video_frame_total('invalid', 25, 0, 100) == 0
def test_detect_video_fps() -> None:
assert detect_video_fps(get_test_example_file('target-240p-25fps.mp4')) == 25.0
assert detect_video_fps(get_test_example_file('target-240p-30fps.mp4')) == 30.0
assert detect_video_fps(get_test_example_file('target-240p-60fps.mp4')) == 60.0
assert detect_video_fps('invalid') is None
def test_restrict_video_fps() -> None:
assert restrict_video_fps(get_test_example_file('target-1080p.mp4'), 20.0) == 20.0
assert restrict_video_fps(get_test_example_file('target-1080p.mp4'), 25.0) == 25.0
assert restrict_video_fps(get_test_example_file('target-1080p.mp4'), 60.0) == 25.0
@pytest.mark.skipif(os.environ.get('CI') and is_linux(), reason = 'h264 codec not present')
def test_detect_video_duration() -> None:
assert detect_video_duration(get_test_example_file('target-240p.mp4')) == 10.8
assert detect_video_duration('invalid') == 0
@pytest.mark.skipif(os.environ.get('CI') and is_linux(), reason = 'h264 codec not present')
def test_count_trim_frame_total() -> None:
assert count_trim_frame_total(get_test_example_file('target-240p.mp4'), 0, 200) == 200
assert count_trim_frame_total(get_test_example_file('target-240p.mp4'), 70, 270) == 200
assert count_trim_frame_total(get_test_example_file('target-240p.mp4'), -10, None) == 270
assert count_trim_frame_total(get_test_example_file('target-240p.mp4'), None, -10) == 0
assert count_trim_frame_total(get_test_example_file('target-240p.mp4'), 280, None) == 0
assert count_trim_frame_total(get_test_example_file('target-240p.mp4'), None, 280) == 270
assert count_trim_frame_total(get_test_example_file('target-240p.mp4'), None, None) == 270
@pytest.mark.skipif(os.environ.get('CI') and is_linux(), reason = 'h264 codec not present')
def test_restrict_trim_frame() -> None:
assert restrict_trim_frame(get_test_example_file('target-240p.mp4'), 0, 200) == (0, 200)
assert restrict_trim_frame(get_test_example_file('target-240p.mp4'), 70, 270) == (70, 270)
assert restrict_trim_frame(get_test_example_file('target-240p.mp4'), -10, None) == (0, 270)
assert restrict_trim_frame(get_test_example_file('target-240p.mp4'), None, -10) == (0, 0)
assert restrict_trim_frame(get_test_example_file('target-240p.mp4'), 280, None) == (270, 270)
assert restrict_trim_frame(get_test_example_file('target-240p.mp4'), None, 280) == (0, 270)
assert restrict_trim_frame(get_test_example_file('target-240p.mp4'), None, None) == (0, 270)
@pytest.mark.skipif(os.environ.get('CI') and is_linux(), reason = 'h264 codec not present')
def test_detect_video_resolution() -> None:
assert detect_video_resolution(get_test_example_file('target-240p.mp4')) == (426, 226)
assert detect_video_resolution(get_test_example_file('target-240p-90deg.mp4')) == (226, 426)
assert detect_video_resolution(get_test_example_file('target-1080p.mp4')) == (2048, 1080)
assert detect_video_resolution(get_test_example_file('target-1080p-90deg.mp4')) == (1080, 2048)
assert detect_video_resolution('invalid') is None
def test_restrict_video_resolution() -> None:
assert restrict_video_resolution(get_test_example_file('target-1080p.mp4'), (426, 226)) == (426, 226)
assert restrict_video_resolution(get_test_example_file('target-1080p.mp4'), (2048, 1080)) == (2048, 1080)
assert restrict_video_resolution(get_test_example_file('target-1080p.mp4'), (4096, 2160)) == (2048, 1080)
def test_scale_resolution() -> None:
assert scale_resolution((426, 226), 0.5) == (212, 112)
assert scale_resolution((2048, 1080), 1.0) == (2048, 1080)
assert scale_resolution((4096, 2160), 2.0) == (8192, 4320)
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)
def test_calc_histogram_difference() -> None:
source_vision_frame = read_image(get_test_example_file('target-240p.jpg'))
target_vision_frame = read_image(get_test_example_file('target-240p-0sat.jpg'))
assert calculate_histogram_difference(source_vision_frame, source_vision_frame) == 1.0
assert calculate_histogram_difference(source_vision_frame, target_vision_frame) < 0.5
def test_match_frame_color() -> None:
source_vision_frame = read_image(get_test_example_file('target-240p.jpg'))
target_vision_frame = read_image(get_test_example_file('target-240p-0sat.jpg'))
output_vision_frame = match_frame_color(source_vision_frame, target_vision_frame)
assert calculate_histogram_difference(source_vision_frame, output_vision_frame) > 0.5