4danyone-rerun / PROVENANCE.md
pablovela5620's picture
Vendor the inference-path subset of the fdanyone package
1b2e96f
|
Raw History Blame
1.36 kB
# Provenance
`fdanyone/` is a copy, not a fork. Regenerate it with `./sync_vendor.sh`.
| Item | Value |
| --- | --- |
| Source repository | <https://github.com/pablovela5620/4DAnyone-5090> |
| Branch | `space-streaming` |
| Commit | `0cc334c2b260ff19b23d423ac8123d318ed602ff` |
| Synced | 2026-08-27T05:15:32Z |
## Excluded from the copy
- `fdanyone/nerfstudio/`, `fdanyone/freetimegs/`, `fdanyone/vendor/freetimegs/` — 3DGS
and 4DGS reconstruction, which this Space does not run.
- `fdanyone/cli.py` — the Fire shim for `scripts/`, which is not copied either.
- `__pycache__/`.
## Patched in the copy
- `fdanyone/assets.py`: `MODEL_FILES` drops `models_t5_umt5-xxl-enc-bf16.pth`,
`4danyone/umt5-xxl/`, and the perceptual VGG-19. `prepare_run` calls
`ensure_models`, which downloads every missing entry — inside the ZeroGPU
allocation. The Space passes `prompt_embedding_path`, so the 11 GB encoder is
never loaded, and it must never be fetched either.
## GVHMR
GVHMR is a git submodule of the source repository and is deliberately absent
here. `download_assets.py` clones it into the ephemeral disk at boot, at the
pinned revision below, and `fdanyone_app.py` passes that path as `gvhmr_root`.
| Item | Value |
| --- | --- |
| Repository | <https://github.com/zju3dv/GVHMR> |
| Revision | `6ec3ca39336c50492c0fae65fba2fb831fc7d866` |