魔搭文本生成视频大模型初体验

  |   0 评论   |   0 浏览

背景

初体验

环境准备

python

wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh
sh Miniconda3-latest-Linux-x86_64.sh
source ~/.bashrc
conda create -n funasr python=3.7
conda activate funasr

安装或更新ModelScope

pip install "modelscope[audio_asr]" --upgrade -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

安装依赖

pip install open_clip_torch pytorch-lightning opencv-python

生成视频

from modelscope.pipelines import pipeline
from modelscope.outputs import OutputKeys

p = pipeline('text-to-video-synthesis', 'damo/text-to-video-synthesis')
test_text = {
'text': 'A panda eating bamboo on a rock.',
    }
output_video_path = p(test_text,)[OutputKeys.OUTPUT_VIDEO]
print('output_video_path:', output_video_path)

效果

tmp_8tez6ja.mp4 201K

参考

  1. 文本生成视频大模型-英文-通用领域