# KeyVID (Hugging Face Hub)

This folder contains the **KeyVID** Hugging Face upload utilities and the model checkpoint files tracked via **Git LFS**.

## Links

- **Model repo**: `https://huggingface.co/RyanWW/KeyVID`
- **Dataset repo**: `https://huggingface.co/datasets/RyanWW/KeyVID_data`

## Usage

### Download the model (checkpoints) from Hugging Face

Option A — **Git LFS clone** (recommended for large files):

```bash
git lfs install
git clone git@hf.co:RyanWW/KeyVID
# or:
# git clone https://huggingface.co/RyanWW/KeyVID
```

Option B — **Python** download a single file:

```bash
pip install -U huggingface_hub
python -c "from huggingface_hub import hf_hub_download; print(hf_hub_download(repo_id='RyanWW/KeyVID', filename='keyframe_generation/generator_checkpoint.ckpt'))"
```

### Use the dataset from Hugging Face

Option A — **Python** (recommended):

```bash
pip install -U datasets
python -c "from datasets import load_dataset; ds = load_dataset('RyanWW/KeyVID_data'); print(ds)"
```

Option B — **Git LFS clone**:

```bash
git lfs install
git clone git@hf.co:datasets/RyanWW/KeyVID_data
# or:
# git clone https://huggingface.co/datasets/RyanWW/KeyVID_data
```

### Upload (from this repo)

```bash
pip install -U huggingface_hub
python upload_fast.py
# or:
python upload.py
```

To upload a different local folder, set:

```bash
export KEYVID_PATH=/path/to/KeyVID_folder
python upload.py
```