Kabachuha

Rank:

Average Model Cost: $0.0000

Number of Runs: 6,416

Models by this creator

modelscope-damo-text2video-pruned-weights

modelscope-damo-text2video-pruned-weights

kabachuha

The ModelScope DAMO Text-to-Video Synthesis model is a pretrained model that generates video sequences based on input text descriptions. It uses deep learning techniques to learn the relationship between textual descriptions and visual content, allowing it to generate realistic and coherent videos that match the given input. This version of the model has been trained with half precision (fp16) weights, which can result in faster inference times while maintaining good performance.

Read more

$-/run

5.2K

Huggingface

Similar creators