* fix image to image for coreml
* fix image to image for coreml
* Update metadata.py
* modernize onnxruntime
* introduce cuda@12 and cuda@13 for installer
* introduce cuda@12 and cuda@13 for installer
* temporary fix for inference pool disaster
* temporary fix for inference pool disaster
* use onnxruntime 1.24.4 for cuda@12
* fix test
* fix test
* fix test
* add test for job list
* switch to has_arena_leak guard
* remove directml hack for inference pool
* uninstall every onnxruntime first
* uninstall every onnxruntime first
* restore the directml fix
* restore the directml fix
* fix directml again
* simplify condition
* mark as next, introduce dynamic scale for face debugger
* use latest onnxruntime
* update within Gradio 5
* Remove system memory limit (#986)
* remove system memory limit from ui
* remove system memory limit from args.py
* flatten the face store
* prevent countless importlib.import_module calls
* remove --onnxruntime from install.py
* remove --onnxruntime from install.py
* resolve static inference providers to fix macos (#1127)
* resolve static inference providers to fix macos
* fix lint
* restore old behaviour
* restore old behaviour
* handle ghost and uniface as well
* adjust condition for ghost and uniface
* fix Gradio gallery styles
* remove face store (#1132)
* fix dataflow in streamer
* Face selector auto mode (#1137)
* introduce face selector auto mode
* introduce face selector auto mode
* introduce face selector auto mode
* correct way is to pass source_vision_frames
* make the world a better place
* fix dataflow in faceswapper, no read of files withing inner methods (#1148)
* fix dataflow in faceswapper, no read of files withing inner methods
* fix lint
* adjust code more
* adjust code more
* bring back the face store but for source and reference only (#1149)
* bring back the face store but for source and reference only
* fix ci
* minor improvement
* guard for tobytes()
* drop condition in select_faces()
* Replace CONFIG_PARSER global with @lru_cache (#1147)
* remove global config_parser
* fix import order
* remove lambda
* remove unused block
* optimize app context detection
* decouple common modules from core (#1152)
* decouple common modules from core
* remove that nonsense
* remove that nonsense
* minor adjustment to workflows
* Tag HEVC output as hvc1 and move moov atom to the front (#1153)
* Tag HEVC output as hvc1 and move moov atom to the front
ffmpeg defaults HEVC in MP4 to the 'hev1' sample entry and leaves the moov
atom at the tail. Apple players (QuickTime, Finder QuickLook) refuse to decode
'hev1' and stall reading a tail-placed moov on large files, so hevc_nvenc /
libx265 renders cannot be previewed on macOS.
- add ffmpeg_builder.set_video_tag(): emit `-tag:v hvc1` for every HEVC
encoder (libx265, hevc_nvenc, hevc_amf, hevc_qsv, hevc_videotoolbox).
Applied in merge_video where the encoder is known; `-c:v copy` in the audio
mux / concat steps preserves the tag.
- add ffmpeg_builder.set_faststart(): emit `-movflags +faststart`, applied in
restore_audio / replace_audio / concat_video which write the final output.
H.264 and other codecs are left untouched. Verified on a real hevc_nvenc
render: hev1 hung QuickLook (no thumbnail); after the patch the file is hvc1
with a front-placed moov and QuickLook generates a thumbnail.
* Restrict hvc1 tag and faststart to quicktime containers
Gate set_video_tag / set_faststart on the output container format
(m4v, mov, mp4) via get_file_format(), so non-quicktime muxers no longer
receive -tag:v hvc1 / -movflags +faststart. Trim test_set_video_tag to a
single positive and negative assertion.
Addresses review on #1153.
* Move hvc1 tag and faststart gates into ffmpeg_builder
Rename set_video_tag / set_faststart to conditional_* and push the
container-format gate (m4v, mov, mp4) inside the builders, keeping
ffmpeg.py free of inline conditionals. Matches the set_image_quality
pattern. Addresses review on #1153.
* post cleanup after merge
* Pack target frames (#1158)
* pack target frames
* add todos
* add todos, resolve todos
* resolve todos
* change names
* revert to single target frame for select faces
* fix lint
* return empty frame
* get() have no default
* Fix trim (#1162)
* fix trim
* fix trim
* rename ffmpeg builder method
* rename to temp_frame_set and temp_frame_pattern
---------
Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
* Implement face tracker (#1163)
* add face tracker
* change get_nearest_track_face -> get_nearest_track_index
* create face_creator.py and move methods around
* add type FaceTrack
* naming
* remove iou test, don't belong there
* fix spaces
* rename to interpolate_points
* rename to find_best_face_track
* just track_faces
* cleanp
* previous next naming
* remove >= and >=
* rename
* remove helper from test and use face from source.jpg
* make get_anchor_indices more readable
* track_faces() call before and is forwarded to select_faces
* change to interpolate_faces
* rename methods
* rename methods
* rename variables
* remove dtype
* move face_anlyser -> face_creator
* claenup face_creator.py
* move tests to dedicated test face detector
* move tracking inside select_faces
* simplify face_tracker (#1165)
* minor renaming
* improve face_tracker test (#1166)
* improve face_tracker test
* cleanup
* Add target frame amount (#1167)
* introduce --target-frame-amount
* add ui
* make track_faces conditional
* update choices.py
* fix []
* rename component file to frame_process.py
* fix track preview (#1168)
* introduce face origin (#1169)
* add guard to prevent failure
* show and hide voice extractor according to lip syncer
* rename average_face_coordinates to average_face_geometry
* use static faces for select_faces()
* face store with lock (#1171)
* face store with lock
* face store with lock
* remove refill color from bbox
* adjust tests and handle frame_position proper way
* enforce similar naming
* introduce face tracker score
* introduce face tracker score
* fix/audio-trim-alignment (#1173)
* fix audio offset
* fix audio offset
* remove reference_frame_number check
---------
Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
* reduce face tracker score from 0 to 0.5
* mark as 3.7.0
* make face tracker stateless
---------
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
Co-authored-by: kazuki nakai <kazuki.nakai@agiletec.net>
Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
* 3.7.0 (#1175)
* mark as next, introduce dynamic scale for face debugger
* use latest onnxruntime
* update within Gradio 5
* Remove system memory limit (#986)
* remove system memory limit from ui
* remove system memory limit from args.py
* flatten the face store
* prevent countless importlib.import_module calls
* remove --onnxruntime from install.py
* remove --onnxruntime from install.py
* resolve static inference providers to fix macos (#1127)
* resolve static inference providers to fix macos
* fix lint
* restore old behaviour
* restore old behaviour
* handle ghost and uniface as well
* adjust condition for ghost and uniface
* fix Gradio gallery styles
* remove face store (#1132)
* fix dataflow in streamer
* Face selector auto mode (#1137)
* introduce face selector auto mode
* introduce face selector auto mode
* introduce face selector auto mode
* correct way is to pass source_vision_frames
* make the world a better place
* fix dataflow in faceswapper, no read of files withing inner methods (#1148)
* fix dataflow in faceswapper, no read of files withing inner methods
* fix lint
* adjust code more
* adjust code more
* bring back the face store but for source and reference only (#1149)
* bring back the face store but for source and reference only
* fix ci
* minor improvement
* guard for tobytes()
* drop condition in select_faces()
* Replace CONFIG_PARSER global with @lru_cache (#1147)
* remove global config_parser
* fix import order
* remove lambda
* remove unused block
* optimize app context detection
* decouple common modules from core (#1152)
* decouple common modules from core
* remove that nonsense
* remove that nonsense
* minor adjustment to workflows
* Tag HEVC output as hvc1 and move moov atom to the front (#1153)
* Tag HEVC output as hvc1 and move moov atom to the front
ffmpeg defaults HEVC in MP4 to the 'hev1' sample entry and leaves the moov
atom at the tail. Apple players (QuickTime, Finder QuickLook) refuse to decode
'hev1' and stall reading a tail-placed moov on large files, so hevc_nvenc /
libx265 renders cannot be previewed on macOS.
- add ffmpeg_builder.set_video_tag(): emit `-tag:v hvc1` for every HEVC
encoder (libx265, hevc_nvenc, hevc_amf, hevc_qsv, hevc_videotoolbox).
Applied in merge_video where the encoder is known; `-c:v copy` in the audio
mux / concat steps preserves the tag.
- add ffmpeg_builder.set_faststart(): emit `-movflags +faststart`, applied in
restore_audio / replace_audio / concat_video which write the final output.
H.264 and other codecs are left untouched. Verified on a real hevc_nvenc
render: hev1 hung QuickLook (no thumbnail); after the patch the file is hvc1
with a front-placed moov and QuickLook generates a thumbnail.
* Restrict hvc1 tag and faststart to quicktime containers
Gate set_video_tag / set_faststart on the output container format
(m4v, mov, mp4) via get_file_format(), so non-quicktime muxers no longer
receive -tag:v hvc1 / -movflags +faststart. Trim test_set_video_tag to a
single positive and negative assertion.
Addresses review on #1153.
* Move hvc1 tag and faststart gates into ffmpeg_builder
Rename set_video_tag / set_faststart to conditional_* and push the
container-format gate (m4v, mov, mp4) inside the builders, keeping
ffmpeg.py free of inline conditionals. Matches the set_image_quality
pattern. Addresses review on #1153.
* post cleanup after merge
* Pack target frames (#1158)
* pack target frames
* add todos
* add todos, resolve todos
* resolve todos
* change names
* revert to single target frame for select faces
* fix lint
* return empty frame
* get() have no default
* Fix trim (#1162)
* fix trim
* fix trim
* rename ffmpeg builder method
* rename to temp_frame_set and temp_frame_pattern
---------
Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
* Implement face tracker (#1163)
* add face tracker
* change get_nearest_track_face -> get_nearest_track_index
* create face_creator.py and move methods around
* add type FaceTrack
* naming
* remove iou test, don't belong there
* fix spaces
* rename to interpolate_points
* rename to find_best_face_track
* just track_faces
* cleanp
* previous next naming
* remove >= and >=
* rename
* remove helper from test and use face from source.jpg
* make get_anchor_indices more readable
* track_faces() call before and is forwarded to select_faces
* change to interpolate_faces
* rename methods
* rename methods
* rename variables
* remove dtype
* move face_anlyser -> face_creator
* claenup face_creator.py
* move tests to dedicated test face detector
* move tracking inside select_faces
* simplify face_tracker (#1165)
* minor renaming
* improve face_tracker test (#1166)
* improve face_tracker test
* cleanup
* Add target frame amount (#1167)
* introduce --target-frame-amount
* add ui
* make track_faces conditional
* update choices.py
* fix []
* rename component file to frame_process.py
* fix track preview (#1168)
* introduce face origin (#1169)
* add guard to prevent failure
* show and hide voice extractor according to lip syncer
* rename average_face_coordinates to average_face_geometry
* use static faces for select_faces()
* face store with lock (#1171)
* face store with lock
* face store with lock
* remove refill color from bbox
* adjust tests and handle frame_position proper way
* enforce similar naming
* introduce face tracker score
* introduce face tracker score
* fix/audio-trim-alignment (#1173)
* fix audio offset
* fix audio offset
* remove reference_frame_number check
---------
Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
* reduce face tracker score from 0 to 0.5
* mark as 3.7.0
* make face tracker stateless
---------
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
Co-authored-by: kazuki nakai <kazuki.nakai@agiletec.net>
Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
* update preview
* fix wording
* fix wording
* last minute change to frame distribution
---------
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
Co-authored-by: kazuki nakai <kazuki.nakai@agiletec.net>
Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
* mark as next, introduce dynamic scale for face debugger
* use latest onnxruntime
* update within Gradio 5
* Remove system memory limit (#986)
* remove system memory limit from ui
* remove system memory limit from args.py
* flatten the face store
* prevent countless importlib.import_module calls
* remove --onnxruntime from install.py
* remove --onnxruntime from install.py
* resolve static inference providers to fix macos (#1127)
* resolve static inference providers to fix macos
* fix lint
* restore old behaviour
* restore old behaviour
* handle ghost and uniface as well
* adjust condition for ghost and uniface
* fix Gradio gallery styles
* remove face store (#1132)
* fix dataflow in streamer
* Face selector auto mode (#1137)
* introduce face selector auto mode
* introduce face selector auto mode
* introduce face selector auto mode
* correct way is to pass source_vision_frames
* make the world a better place
* fix dataflow in faceswapper, no read of files withing inner methods (#1148)
* fix dataflow in faceswapper, no read of files withing inner methods
* fix lint
* adjust code more
* adjust code more
* bring back the face store but for source and reference only (#1149)
* bring back the face store but for source and reference only
* fix ci
* minor improvement
* guard for tobytes()
* drop condition in select_faces()
* Replace CONFIG_PARSER global with @lru_cache (#1147)
* remove global config_parser
* fix import order
* remove lambda
* remove unused block
* optimize app context detection
* decouple common modules from core (#1152)
* decouple common modules from core
* remove that nonsense
* remove that nonsense
* minor adjustment to workflows
* Tag HEVC output as hvc1 and move moov atom to the front (#1153)
* Tag HEVC output as hvc1 and move moov atom to the front
ffmpeg defaults HEVC in MP4 to the 'hev1' sample entry and leaves the moov
atom at the tail. Apple players (QuickTime, Finder QuickLook) refuse to decode
'hev1' and stall reading a tail-placed moov on large files, so hevc_nvenc /
libx265 renders cannot be previewed on macOS.
- add ffmpeg_builder.set_video_tag(): emit `-tag:v hvc1` for every HEVC
encoder (libx265, hevc_nvenc, hevc_amf, hevc_qsv, hevc_videotoolbox).
Applied in merge_video where the encoder is known; `-c:v copy` in the audio
mux / concat steps preserves the tag.
- add ffmpeg_builder.set_faststart(): emit `-movflags +faststart`, applied in
restore_audio / replace_audio / concat_video which write the final output.
H.264 and other codecs are left untouched. Verified on a real hevc_nvenc
render: hev1 hung QuickLook (no thumbnail); after the patch the file is hvc1
with a front-placed moov and QuickLook generates a thumbnail.
* Restrict hvc1 tag and faststart to quicktime containers
Gate set_video_tag / set_faststart on the output container format
(m4v, mov, mp4) via get_file_format(), so non-quicktime muxers no longer
receive -tag:v hvc1 / -movflags +faststart. Trim test_set_video_tag to a
single positive and negative assertion.
Addresses review on #1153.
* Move hvc1 tag and faststart gates into ffmpeg_builder
Rename set_video_tag / set_faststart to conditional_* and push the
container-format gate (m4v, mov, mp4) inside the builders, keeping
ffmpeg.py free of inline conditionals. Matches the set_image_quality
pattern. Addresses review on #1153.
* post cleanup after merge
* Pack target frames (#1158)
* pack target frames
* add todos
* add todos, resolve todos
* resolve todos
* change names
* revert to single target frame for select faces
* fix lint
* return empty frame
* get() have no default
* Fix trim (#1162)
* fix trim
* fix trim
* rename ffmpeg builder method
* rename to temp_frame_set and temp_frame_pattern
---------
Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
* Implement face tracker (#1163)
* add face tracker
* change get_nearest_track_face -> get_nearest_track_index
* create face_creator.py and move methods around
* add type FaceTrack
* naming
* remove iou test, don't belong there
* fix spaces
* rename to interpolate_points
* rename to find_best_face_track
* just track_faces
* cleanp
* previous next naming
* remove >= and >=
* rename
* remove helper from test and use face from source.jpg
* make get_anchor_indices more readable
* track_faces() call before and is forwarded to select_faces
* change to interpolate_faces
* rename methods
* rename methods
* rename variables
* remove dtype
* move face_anlyser -> face_creator
* claenup face_creator.py
* move tests to dedicated test face detector
* move tracking inside select_faces
* simplify face_tracker (#1165)
* minor renaming
* improve face_tracker test (#1166)
* improve face_tracker test
* cleanup
* Add target frame amount (#1167)
* introduce --target-frame-amount
* add ui
* make track_faces conditional
* update choices.py
* fix []
* rename component file to frame_process.py
* fix track preview (#1168)
* introduce face origin (#1169)
* add guard to prevent failure
* show and hide voice extractor according to lip syncer
* rename average_face_coordinates to average_face_geometry
* use static faces for select_faces()
* face store with lock (#1171)
* face store with lock
* face store with lock
* remove refill color from bbox
* adjust tests and handle frame_position proper way
* enforce similar naming
* introduce face tracker score
* introduce face tracker score
* fix/audio-trim-alignment (#1173)
* fix audio offset
* fix audio offset
* remove reference_frame_number check
---------
Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
* reduce face tracker score from 0 to 0.5
* mark as 3.7.0
* make face tracker stateless
---------
Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
Co-authored-by: kazuki nakai <kazuki.nakai@agiletec.net>
Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
* queue with futures, kill deque, add couple of todos
* resolve couple of todos
* add more todos
* add more todos and resolve others
* add more todos and resolve others
* fix test
* fix collapse
* adjust naming a bit
* move to push based receive
* move to push based receive, fix mocks
* fix tests
* add todos
* remove asyncio
* remove asyncio
* resolve todos
* move to queue without events
* prevent debug spam
* concurrent stream inference
stream_video.py: pipeline face-swap inference across execution_thread_count workers (ThreadPoolExecutor + bounded in-flight deque, ordered encode) to keep the GPU busy during encode
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* add todos
* add todos
* add missing state
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix tests part1
* improve testing
* use real audio
* more renaming
* switch to hash assertions
* switch to hash assertions
* switch to hash assertions
* switch to hash assertions
* skip on macos
* extract numpy.empty(0) into an empty_vision_frame variable so the sentinel intent is clear
* bring back todos
* bring back todos
* rename opus_buffer to audio
* move reshape and cvtColor into decoder modules
* add audio_codec check
* add audio_codec check
* rename audio video buffer
* simplify receive methods and cleanup test
* todo
* revert decode methods to return pointer
* remove duplicate test_stream_helper — tests live in test_api_stream_helper
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* clean testing suite
* clean testing suite part2
* clean testing suite part3
* add todos
* extend testing suite and kill some mutants
* fix hashes
* fix lint
* fix test
* fix test
* implement tier 1
* fix lint
* cleanup
* cleanup
* fix lint
* use clear_remb method
* use single callback
* improve test
* improve test
* improve test
* improve test
* improve test
* migrate to whip part1
* migrate to whip part2
* migrate to whip part3
* migrate to whip part4
* migrate to whip/whep with bidirectional
* migrate to whip/whep with bidirectional
* use next library
* add _next to lid datachannel files
* cleanup and add todos
* use internal helper rtcGetPayloadTypesForCodec
* fix lint
* refactor decode()
* move logic to codecs
* move logic to codecs
* break encoders and decoders into multiple files
* break encoders and decoders into multiple files
* cleanup more
* drop action for stream endpoints, keep type for self documentation
* restore the v4 store
* fix: align frame_width and frame_height to even in both collect() and read_resolution() in both decoders.
---------
Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com>
