- Add experimental visual postproc chain (lo-fi scifi hologram)
- TODO: not configurable yet, it's always on until I fix this
- Improve emotion preset loading logic
- Even if an emotion preset JSON is missing, load the emotion from _defaults.json.
- Add blunder recovery (emotion preset factory reset) options to manual poser
- Fix factory-default preset name angry -> anger
- Manual poser: return nonzero exit code on init error
- Manual poser too now auto-installs THA3 models if needed
- Move TODO list into its own file, dump everything there
- Add a README for the new revised talkinghead
- Rewrite sway animation (much more natural now)
- History-free, rate-based formulation
- Use all non-morph axes: head, neck, body
- Every few seconds, randomize a new deviation from the target pose for all sway axes.
- Assign this as the target pose, and let the pose interpolator perform the actual animation.
- Micro-sway: add small dynamic noise (re-generated every frame) on top of sway target pose.
- This makes the motion look more natural, especially once we are near the target pose.
- Add breathing animation
- When entering "confusion" emotion, allow blinking quickly in succession
- Add framerate limiter, currently hardcoded to send ~24 FPS
- Reduces average GPU usage if the GPU renders faster than this.
* talkinghead: fix and improve THA3 manual poser
* server.py: no, don't yet use fp16 for talkinghead
* talkinghead: remove wxPython dependency from live mode
* comment out unused functions
* add TODO list
* coding style
* remove unused import
* add TODO marker
* message wordings
* fix typos in variable names
* talkinghead updates
* talkinghead updates
* Empty commit
* presentation order, sectioning
* fix the inMotion flag update
* mark a TODO
* refactor
* remove done TODO items
* mark a TODO
* comment wording
* pause animation while loading a new image
* parser doesn't belong here, not a command-line app anymore
* message wording
* use finally
* remove superfluous "global" declarations
* lots of cleanup
* remove silly sys.path entry
* improve docstring
* oops
* app.py now only serves the live mode for the plugin
* talkinghead live mode: remove ifacialmocap stuff (unused)
* improve comment
* list walking is so 1990s
* use double quotes consistently
* remove now-unused ifacialmocap-related files from the repo
* remove done TODO item
* improve docstring
* update comment
* remove now-unused function
* update comment
* improve docstring
* add TODO marker
* oops, typo
* add --talkinghead-model command-line option to server.py
Default is 'auto': float16 on GPU, float32 on CPU.
* talkinghead: auto-install THA3 models if needed
* remove tha3/models from git repo (have autodownload now)
* Add hf-hub as explicit dependency
* Add THA models to gitignore
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
