DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder

🤗 Hugging Face sourceapache-2.08B params16 GBsafetensors✓ 5 checksumsupdated today

Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder ./model-folder

Needs a seeder →

HunyuanVideo_MLLM_text_encoder

This model is adapted from the llava-llama-3-8b-v1_1-transformers model, retaining only its model.language_model and processor.tokenizer. This organization is not the provider of the original model and has no legal affiliation with it.

Intended for use as a text encoder for the HunyuanVideo open-source model.

You can download the model using the following git clone command or the ModelScope SDK:

SDK Download

# Install ModelScope
pip install modelscope

# Download model via SDK
from modelscope import snapshot_download
model_dir = snapshot_download('DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder')

Git Download

# Git model download
git clone https://www.modelscope.cn/DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder.git