Views
No views yet
.pt avatars (you build those yourself with python -m light_avatar.cli build) and it does not host pre-built TensorRT engines (those are GPU-arch-specific; build them locally from the ONNX via trtexec).1pip install huggingface_hub
2export LIGHT_AVATAR_HOME=~/light-avatar-home
3python -m light_avatar.cli fetch-weights \
4 --weights-repo stevegu1984/light-avatar \
5 --profile build # or: cpu-render | gpu-render | all| profile | size | what for |
|---|---|---|
cpu-render | ~250 MB | CPU rendering of pre-built avatars |
gpu-render | ~252 MB + your TRT engines | GPU rendering with locally-built TRT engines (needs the GridSample3D plugin) |
build | ~2.3 GB | full set needed to distill a per-identity avatar from scratch |
all | ~2.3 GB | same as build today |
LIGHT_AVATAR_HOME/teacher/ tree:teacher/
├── ditto_cfg/
│ └── v0.4_hubert_cfg_trt.pkl
├── ditto_onnx/
│ ├── *.onnx # 12 models
│ └── libgrid_sample_3d_plugin.so # CUDA plugin for warp_network engines
└── flow_student_generic.pt # bf16, generic warm-start flow initdocs/WEIGHTS_HOSTING.md in the main repo for self-hosting instructions, profile semantics, and pinning revisions for reproducible CI runs.