Instructions to use RyanWW/KeyVID with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use RyanWW/KeyVID with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("RyanWW/KeyVID", torch_dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
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):
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:
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):
pip install -U datasets
python -c "from datasets import load_dataset; ds = load_dataset('RyanWW/KeyVID_data'); print(ds)"
Option B — Git LFS clone:
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)
pip install -U huggingface_hub
python upload_fast.py
# or:
python upload.py
To upload a different local folder, set:
export KEYVID_PATH=/path/to/KeyVID_folder
python upload.py