* 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>
