Dataset?
#2
by
eggsbenedicto
- opened
Amazing work! Would like to continue on this track. However, your huggingface dataset page appears to be empty. Do I need a dataset for this or am I misunderstanding the training process.
Sorry for the delay. Please check https://huggingface.co/datasets/RaphaelLiu/PusaV0.5_Training. This repository contains the pre-encoded training dataset used for fine-tuning the Pusa-V0.5 video generation model. The dataset consists of 52,695 pre-encoded latent samples derived from VIDGEN-1M, though Pusa-V0.5 was trained using only 16,000 of this dataset.