* feat/yoloface (#334)
* added yolov8 to face_detector (#323)
* added yolov8 to face_detector
* added yolov8 to face_detector
* Initial cleanup and renaming
* Update README
* refactored detect_with_yoloface (#329)
* refactored detect_with_yoloface
* apply review
* Change order again
* Restore working code
* modified code (#330)
* refactored detect_with_yoloface
* apply review
* use temp_frame in detect_with_yoloface
* reorder
* modified
* reorder models
* Tiny cleanup
---------
Co-authored-by: tamoharu <133945583+tamoharu@users.noreply.github.com>
* include audio file functions (#336)
* Add testing for audio handlers
* Change order
* Fix naming
* Use correct typing in choices
* Update help message for arguments, Notation based wording approach (#347)
* Update help message for arguments, Notation based wording approach
* Fix installer
* Audio functions (#345)
* Update ffmpeg.py
* Create audio.py
* Update ffmpeg.py
* Update audio.py
* Update audio.py
* Update typing.py
* Update ffmpeg.py
* Update audio.py
* Rename Frame to VisionFrame (#346)
* Minor tidy up
* Introduce audio testing
* Add more todo for testing
* Add more todo for testing
* Fix indent
* Enable venv on the fly
* Enable venv on the fly
* Revert venv on the fly
* Revert venv on the fly
* Force Gradio to shut up
* Force Gradio to shut up
* Clear temp before processing
* Reduce terminal output
* include audio file functions
* Enforce output resolution on merge video
* Minor cleanups
* Add age and gender to face debugger items (#353)
* Add age and gender to face debugger items
* Rename like suggested in the code review
* Fix the output framerate vs. time
* Lip Sync (#356)
* Cli implementation of wav2lip
* - create get_first_item()
- remove non gan wav2lip model
- implement video memory strategy
- implement get_reference_frame()
- implement process_image()
- rearrange crop_mask_list
- implement test_cli
* Simplify testing
* Rename to lip syncer
* Fix testing
* Fix testing
* Minor cleanup
* Cuda 12 installer (#362)
* Make cuda nightly (12) the default
* Better keep legacy cuda just in case
* Use CUDA and ROCM versions
* Remove MacOS options from installer (CoreML include in default package)
* Add lip-syncer support to source component
* Add lip-syncer support to source component
* Fix the check in the source component
* Add target image check
* Introduce more helpers to suite the lip-syncer needs
* Downgrade onnxruntime as of buggy 1.17.0 release
* Revert "Downgrade onnxruntime as of buggy 1.17.0 release"
This reverts commit f4a7ae6824.
* More testing and add todos
* Fix the frame processor API to at least not throw errors
* Introduce dict based frame processor inputs (#364)
* Introduce dict based frame processor inputs
* Forgot to adjust webcam
* create path payloads (#365)
* create index payload to paths for process_frames
* rename to payload_paths
* This code now is poetry
* Fix the terminal output
* Make lip-syncer work in the preview
* Remove face debugger test for now
* Reoder reference_faces, Fix testing
* Use inswapper_128 on buggy onnxruntime 1.17.0
* Undo inswapper_128_fp16 duo broken onnxruntime 1.17.0
* Undo inswapper_128_fp16 duo broken onnxruntime 1.17.0
* Fix lip_syncer occluder & region mask issue
* Fix preview once in case there was no output video fps
* fix lip_syncer custom fps
* remove unused import
* Add 68 landmark functions (#367)
* Add 68 landmark model
* Add landmark to face object
* Re-arrange and modify typing
* Rename function
* Rearrange
* Rearrange
* ignore type
* ignore type
* change type
* ignore
* name
* Some cleanup
* Some cleanup
* Opps, I broke something
* Feat/face analyser refactoring (#369)
* Restructure face analyser and start TDD
* YoloFace and Yunet testing are passing
* Remove offset from yoloface detection
* Cleanup code
* Tiny fix
* Fix get_many_faces()
* Tiny fix (again)
* Use 320x320 fallback for retinaface
* Fix merging mashup
* Upload wave2lip model
* Upload 2dfan2 model and rename internal to face_predictor
* Downgrade onnxruntime for most cases
* Update for the face debugger to render landmark 68
* Try to make detect_face_landmark_68() and detect_gender_age() more uniform
* Enable retinaface testing for 320x320
* Make detect_face_landmark_68() and detect_gender_age() as uniform as … (#370)
* Make detect_face_landmark_68() and detect_gender_age() as uniform as possible
* Revert landmark scale and translation
* Make box-mask for lip-syncer adjustable
* Add create_bbox_from_landmark()
* Remove currently unused code
* Feat/uniface (#375)
* add uniface (#373)
* Finalize UniFace implementation
---------
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
* My approach how todo it
* edit
* edit
* replace vertical blur with gaussian
* remove region mask
* Rebase against next and restore method
* Minor improvements
* Minor improvements
* rename & add forehead padding
* Adjust and host uniface model
* Use 2dfan4 model
* Rename to face landmarker
* Feat/replace bbox with bounding box (#380)
* Add landmark 68 to 5 convertion
* Add landmark 68 to 5 convertion
* Keep 5, 5/68 and 68 landmarks
* Replace kps with landmark
* Replace bbox with bounding box
* Reshape face_landmark5_list different
* Make yoloface the default
* Move convert_face_landmark_68_to_5 to face_helper
* Minor spacing issue
* Dynamic detector sizes according to model (#382)
* Dynamic detector sizes according to model
* Dynamic detector sizes according to model
* Undo false commited files
* Add lib syncer model to the UI
* fix halo (#383)
* Bump to 2.3.0
* Update README and wording
* Update README and wording
* Fix spacing
* Apply _vision suffix
* Apply _vision suffix
* Apply _vision suffix
* Apply _vision suffix
* Apply _vision suffix
* Apply _vision suffix
* Apply _vision suffix, Move mouth mask to face_masker.py
* Apply _vision suffix
* Apply _vision suffix
* increase forehead padding
---------
Co-authored-by: tamoharu <133945583+tamoharu@users.noreply.github.com>
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
* renaming and restructuring (#282)
* Renaming and restructuring
* Renaming and restructuring
* Renaming and restructuring
* Fix gender detection
* Implement distance to face debugger
* Implement distance to face debugger part2
* Implement distance to face debugger part3
* Mark as next
* Fix reference when face_debugger comes first
* Use official onnxruntime nightly
* CUDA on steroids
* CUDA on steroids
* Add some testing
* Set inswapper_128_fp16 as default
* Feat/block until post check (#292)
* Block until download is done
* Introduce post_check()
* Fix webcam
* Update dependencies
* Add --force-reinstall to installer
* Introduce config ini (#298)
* Introduce config ini
* Fix output video encoder
* Revert help listings back to commas, Move SSL hack to download.py
* Introduce output-video-preset which defaults to veryfast
* Mapping for nvenc encoders
* Rework on events and non-blocking UI
* Add fast bmp to temp_frame_formats
* Add fast bmp to temp_frame_formats
* Show total processing time on success
* Show total processing time on success
* Show total processing time on success
* Move are_images, is_image and is_video back to filesystem
* Fix some spacings
* Pissing everyone of by renaming stuff
* Fix seconds output
* feat/video output fps (#312)
* added output fps slider, removed 'keep fps' option (#311)
* added output fps slider, removed 'keep fps' option
* now uses passed fps instead of global fps for ffmpeg
* fps values are now floats instead of ints
* fix previous commit
* removed default value from fps slider
this is so we can implement a dynamic default value later
* Fix seconds output
* Some cleanup
---------
Co-authored-by: Ran Shaashua <47498956+ranshaa05@users.noreply.github.com>
* Allow 0.01 steps for fps
* Make fps unregulated
* Make fps unregulated
* Remove distance from face debugger again (does not work)
* Fix gender age
* Fix gender age
* Hotfix benchmark suite
* Warp face normalize (#313)
* use normalized kp templates
* Update face_helper.py
* My 50 cents to warp_face()
---------
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
* face-swapper-weight (#315)
* Move prepare_crop_frame and normalize_crop_frame out of apply_swap
* Fix UI bug with different range
* feat/output video resolution (#316)
* Introduce detect_video_resolution, Rename detect_fps to detect_video_fps
* Add calc_video_resolution_range
* Make output resolution work, does not auto-select yet
* Make output resolution work, does not auto-select yet
* Try to keep the origin resolution
* Split code into more fragments
* Add pack/unpack resolution
* Move video_template_sizes to choices
* Improve create_video_resolutions
* Reword benchmark suite
* Optimal speed for benchmark
* Introduce different video memory strategies, rename max_memory to max… (#317)
* Introduce different video memory strategies, rename max_memory to max_system_memory
* Update readme
* Fix limit_system_memory call
* Apply video_memory_strategy to face debugger
* Limit face swapper weight to 3.0
* Remove face swapper weight due bad render outputs
* Show/dide logic for output video preset
* fix uint8 conversion
* Fix whitespace
* Finalize layout and update preview
* Fix multi renders on face debugger
* Restore less restrictive rendering of preview and stream
* Fix block mode for model downloads
* Add testing
* Cosmetic changes
* Enforce valid fps and resolution via CLI
* Empty config
* Cosmetics on args processing
* Memory workover (#319)
* Cosmetics on args processing
* Fix for MacOS
* Rename all max_ to _limit
* More fixes
* Update preview
* Fix whitespace
---------
Co-authored-by: Ran Shaashua <47498956+ranshaa05@users.noreply.github.com>
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
* Operating system specific installer options
* Update dependencies
* Sorting before NMS according to the standard
* Minor typing fix
* Change the wording
* Update preview.py (#222)
Added a release listener to the preview frame slider, this will update the frame preview with the latest frame
* Combine preview slider listener
* Remove change listener
* Introduce multi source (#223)
* Implement multi source
* Adjust face enhancer and face debugger to multi source
* Implement multi source to UI
* Implement multi source to UI part2
* Implement multi source to UI part3
* Implement multi source to UI part4
* Some cleanup
* Add face occluder (#225) (#226)
* Add face occluder (#225)
* add face-occluder (commandline only)
* review 1
* Update face_masker.py
* Update face_masker.py
* Add gui & fix typing
* Minor naming cleanup
* Minor naming cleanup part2
---------
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
* Update usage information
* Fix averaged normed_embedding
* Remove blur from face occluder, enable accelerators
* Switch to RANSAC with 100 threshold
* Update face_enhancer.py (#229)
* Update face_debugger.py (#230)
* Split utilities (#232)
* Split utilities
* Split utilities part2
* Split utilities part3
* Split utilities part4
* Some cleanup
* Implement log level support (#233)
* Implement log level support
* Fix testing
* Implement debug logger
* Implement debug logger
* Fix alignment offset (#235)
* Update face_helper.py
* fix 2
* Enforce virtual environment via installer
* Enforce virtual environment via installer
* Enforce virtual environment via installer
* Enforce virtual environment via installer
* Feat/multi process reference faces (#239)
* Multi processing aware reference faces
* First clean up and joining of files
* Finalize the face store
* Reduce similar face detection to one set, use __name__ for scopes in logger
* Rename to face_occluder
* Introduce ModelSet type
* Improve webcam error handling
* Prevent null pointer on is_image() and is_video()
* Prevent null pointer on is_image() and is_video()
* Fix find similar faces
* Fix find similar faces
* Fix process_images for face enhancer
* Bunch of minor improvements
* onnxruntime for ROCM under linux
* Improve mask related naming
* Fix falsy import
* Fix typo
* Feat/face parser refactoring (#247)
* Face parser update (#244)
* face-parser
* Update face_masker.py
* update debugger
* Update globals.py
* Update face_masker.py
* Refactor code to split occlusion from region
* fix (#246)
* fix
* fix debugger resolution
* flip input to horizontal
* Clean up UI
* Reduce the regions to inside face only
* Reduce the regions to inside face only
---------
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
* Fix enhancer, remove useless dest in add_argument()
* Prevent unselect of the face_mask_regions via UI
* Prepare next release
* Shorten arguments that have choices and nargs
* Add missing clear to face debugger
---------
Co-authored-by: Mathias <github@feroc.de>
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
* Simplify bbox access
* Code cleanup
* Simplify bbox access
* Move code to face helper
* Swap and paste back without insightface
* Swap and paste back without insightface
* Remove semaphore where possible
* Improve paste back performance
* Cosmetic changes
* Move the predictor to ONNX to avoid tensorflow, Use video ranges for prediction
* Make CI happy
* Move template and size to the options
* Fix different color on box
* Uniform model handling for predictor
* Uniform frame handling for predictor
* Pass kps direct to warp_face
* Fix urllib
* Analyse based on matches
* Analyse based on rate
* Fix CI
* ROCM and OpenVINO mapping for torch backends
* Fix the paste back speed
* Fix import
* Replace retinaface with yunet (#168)
* Remove insightface dependency
* Fix urllib
* Some fixes
* Analyse based on matches
* Analyse based on rate
* Fix CI
* Migrate to Yunet
* Something is off here
* We indeed need semaphore for yunet
* Normalize the normed_embedding
* Fix download of models
* Fix download of models
* Fix download of models
* Add score and improve affine_matrix
* Temp fix for bbox out of frame
* Temp fix for bbox out of frame
* ROCM and OpenVINO mapping for torch backends
* Normalize bbox
* Implement gender age
* Cosmetics on cli args
* Prevent face jumping
* Fix the paste back speed
* FIx import
* Introduce detection size
* Cosmetics on face analyser ARGS and globals
* Temp fix for shaking face
* Accurate event handling
* Accurate event handling
* Accurate event handling
* Set the reference_frame_number in face_selector component
* Simswap model (#171)
* Add simswap models
* Add ghost models
* Introduce normed template
* Conditional prepare and normalize for ghost
* Conditional prepare and normalize for ghost
* Get simswap working
* Get simswap working
* Fix refresh of swapper model
* Refine face selection and detection (#174)
* Refine face selection and detection
* Update README.md
* Fix some face analyser UI
* Fix some face analyser UI
* Introduce range handling for CLI arguments
* Introduce range handling for CLI arguments
* Fix some spacings
* Disable onnxruntime warnings
* Use cv2.blur over cv2.GaussianBlur for better performance
* Revert "Use cv2.blur over cv2.GaussianBlur for better performance"
This reverts commit bab666d6f9.
* Prepare universal face detection
* Prepare universal face detection part2
* Reimplement retinaface
* Introduce cached anchors creation
* Restore filtering to enhance performance
* Minor changes
* Minor changes
* More code but easier to understand
* Minor changes
* Rename predictor to content analyser
* Change detection/recognition to detector/recognizer
* Fix crop frame borders
* Fix spacing
* Allow normalize output without a source
* Improve conditional set face reference
* Update dependencies
* Add timeout for get_download_size
* Fix performance due disorder
* Move models to assets repository, Adjust namings
* Refactor face analyser
* Rename models once again
* Fix spacing
* Highres simswap (#192)
* Introduce highres simswap
* Fix simswap 256 color issue (#191)
* Fix simswap 256 color issue
* Update face_swapper.py
* Normalize models and host in our repo
* Normalize models and host in our repo
---------
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
* Rename face analyser direction to face analyser order
* Improve the UI for face selector
* Add best-worst, worst-best detector ordering
* Clear as needed and fix zero score bug
* Fix linter
* Improve startup time by multi thread remote download size
* Just some cosmetics
* Normalize swagger source input, Add blendface_256 (unfinished)
* New paste back (#195)
* add new paste_back (#194)
* add new paste_back
* Update face_helper.py
* Update face_helper.py
* add commandline arguments and gui
* fix conflict
* Update face_mask.py
* type fix
* Clean some wording and typing
---------
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
* Clean more names, use blur range approach
* Add blur padding range
* Change the padding order
* Fix yunet filename
* Introduce face debugger
* Use percent for mask padding
* Ignore this
* Ignore this
* Simplify debugger output
* implement blendface (#198)
* Clean up after the genius
* Add gpen_bfr_256
* Cosmetics
* Ignore face_mask_padding on face enhancer
* Update face_debugger.py (#202)
* Shrink debug_face() to a minimum
* Mark as 2.0.0 release
* remove unused (#204)
* Apply NMS (#205)
* Apply NMS
* Apply NMS part2
* Fix restoreformer url
* Add debugger cli and gui components (#206)
* Add debugger cli and gui components
* update
* Polishing the types
* Fix usage in README.md
* Update onnxruntime
* Support for webp
* Rename paste-back to face-mask
* Add license to README
* Add license to README
* Extend face selector mode by one
* Update utilities.py (#212)
* Stop inline camera on stream
* Minor webcam updates
* Gracefully start and stop webcam
* Rename capture to video_capture
* Make get webcam capture pure
* Check webcam to not be None
* Remove some is not None
* Use index 0 for webcam
* Remove memory lookup within progress bar
* Less progress bar updates
* Uniform progress bar
* Use classic progress bar
* Fix image and video validation
* Use different hash for cache
* Use best-worse order for webcam
* Normalize padding like CSS
* Update preview
* Fix max memory
* Move disclaimer and license to the docs
* Update wording in README
* Add LICENSE.md
* Fix argument in README
---------
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
Co-authored-by: alex00ds <31631959+alex00ds@users.noreply.github.com>
* Improve typing for our callbacks
* Return 0 for get_download_size
* Introduce ONNX powered face enhancer
* Introduce ONNX powered face enhancer
* Introduce ONNX powered face enhancer
* Remove tile processing from frame enhancer
* Fix video compress translation for libvpx-vp9
* Allow zero values for video compression
* Develop (#134)
* Introduce model options to the frame processors
* Finish UI to select frame processors models
* Simplify frame processors options
* Fix lint in CI
* Rename all kind of settings to options
* Add blend to enhancers
* Simplify webcam mode naming
* Bypass SSL issues under Windows
* Fix blend of frame enhancer
* Massive CLI refactoring, Register and apply ARGS via the frame processors
* Refine UI theme and introduce donate button
* Update dependencies and fix cpu only torch
* Update dependencies and fix cpu only torch
* Fix theme, Fix frame_processors in headless mode
* Remove useless astype
* Disable CoreML for the ONNX face enhancer
* Disable CoreML for the ONNX face enhancer
* Predict webcam too
* Improve resize of preview
* Change output quality defaults, Move options to the right
* Support for codeformer model
* Update the typo
* Add GPEN and GFPGAN 1.2
* Extract blend_frame methods
* Extend the installer
* Revert broken Gradio
* Rework on ui components
* Move output path selector to the output options
* Remove tons of pointless component updates
* Reset more base theme styling
* Use latest Gradio
* Fix the sliders
* More styles
* Update torch to 2.1.0
* Add RealESRNet_x4plus
* Fix that button
* Use latest onnxruntime-silicon
* Looks stable to me
* Lowercase model keys, Update preview and readme
* Clear VRAM of face analyser on post process
* Mark as NEXT
* Reduce tensorflow memory to 512 MB
* Cosmetics on installer
* Add is_download_done to pre_process() hook to prevent errors
* Use latest onnxruntime
* Testing for download methods, Make get_download_size more robust
* Testing for download methods
* Introduce --skip-download argument
* Catch exception causes by a firewall
* Looks stable to me
* Allow passing the onnxruntime to install.py
* Fix CI
* Disallow none execution providers in the UI
* Use CV2 to detect fps
* Respect trim on videos with audio
* Respect trim on videos with audio (finally)
* Implement caching to speed up preview and webcam
* Define webcam UI and webcam performance
* Remove layout from components
* Add primary buttons
* Extract benchmark and webcam settings
* Introduce compact UI settings
* Caching for IO and **** prediction
* Caching for IO and **** prediction
* Introduce face analyser caching
* Fix some typing
* Improve setup for benchmark
* Clear image cache via post process
* Fix settings in UI, Simplify restore_audio() using shortest
* Select resolution and fps via webcam ui
* Introduce read_static_image() to stop caching temp images
* Use DirectShow under Windows
* Multi-threading for webcam
* Fix typing
* Refactor frame processor
* Refactor webcam processing
* Avoid warnings due capture.isOpened()
* Resume downloads (#110)
* Introduce resumable downloads
* Fix CURL commands
* Break execution_settings into pieces
* Cosmetic changes on cv2 webcam
* Update Gradio
* Move face cache to own file
* Uniform namings for threading
* Fix sorting of get_temp_frame_paths(), extend get_temp_frames_pattern()
* Minor changes from the review
* Looks stable to tme
* Update the disclaimer
* Update the disclaimer
* Update the disclaimer
* Cosmetic changes
* Cosmetic changes
* Run single warm up for the benchmark suite
* Use latest version of Gradio
* More testing
* Introduce basic installer
* Fix typo
* Move more to installer file
* Fix the installer with the uninstall all trick
* Adjust wording
* Fix coreml in installer
* Allow Pyhton 3.9
* Add VENV to installer
* Just some cosmetics
* Just some cosmetics
* Dedicated headless mode, Refine API of UI layouts
* Use --headless for pytest
* Fix testing for Windows
* Normalize output path that lacks extension
* Fix CI for Windows
* Fix CI for Windows
* UI to change output path
* Add conda support for the installer
* Improve installer quite a bit
* Drop conda support
* Install community wheels for coreml silicon
* Improve output video component
* Fix silicon wheel downloading
* Remove venv from installer as we cannot activate via subprocess
* Use join to create wheel name
* Refine the output path normalization
* Refine the output path normalization
* Introduce ProcessMode and rename some methods
* Introduce ProcessMode and rename some methods
* Basic webcam integration and open_ffmpeg()
* Basic webcam integration part2
* Benchmark resolutions now selectable
* Rename benchmark resolution back to benchmark runs
* Fix repeating output path in UI
* Keep output_path untouched if not resolvable
* Add more cases to normalize output path
* None for those tests that don't take source path into account
* Finish basic webcam integration, UI layout now with custom run()
* Fix CI and hide link in webcam UI
* Cosmetics on webcam UI
* Move get_device to utilities
* Fix CI
* Introduce output-image-quality, Show and hide UI according to target media type
* Benchmark with partial result updates
* fix: trim frame sliders not appearing after draggin video
* fix: output and temp frame setting inputs not appearing
* Fix: set increased update delay to 250ms to let Gradio update conditional inputs properly
* Reverted .gitignore
* Adjust timings
* Remove timeout hacks and get fully event driven
* Update dependencies
* Update dependencies
* Revert NSFW library, Conditional unset trim args
* Face selector works better on preview slider release
* Add limit resources to UI
* Introduce vision.py for all CV2 operations, Rename some methods
* Add restoring audio failed
* Decouple updates for preview image and preview frame slider, Move reduce_preview_frame to vision
* Refactor detect_fps based on JSON output
* Only webcam when open
* More conditions to vision.py
* Add udp and v4l2 streaming to webcam UI
* Detect v4l2 device to be used
* Refactor code a bit
* Use static max memory for UI
* Fix CI
* Looks stable to me
* Update preview
* Update preview
---------
Co-authored-by: Sumit <vizsumit@gmail.com>
