pytorch_model.pt is official HunyuanVideo VAE

model.safetensors is from lllyasviel/flux_redux_bfl for Image Encoder (SigLIP) Model

clip_l.safetensors is Text Encoder 2 (CLIP) Model

llava_llama3_fp16.safetensors is Text Encoder 1 (LLaMA) Model

FramePackI2V_HY_bf16.safetensors is DiT Model

FramePack_F1_I2V_HY_20250503.safetensors is the F1 DiT Model

Downloads last month: -; Downloads are not tracked for this model. How to track

Safetensors

Model size

428M params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support