项目地址
https://github.com/THUDM/CogVideo
官方在线体验
https://huggingface.co/spaces/THUDM/CogVideoX
docker一键部署,一键启动(需要docker-nvidia)
注意:如果镜像拉取不到,那就是没上传完
docker run -itd --name=cogvideo -p 7878:7878 --gpus=all registry.cn-hangzhou.aliyuncs.com/guoshiyin/cogvideo:v3
元神启动
等待
Loading checkpoint shards: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:02<00:00, 1.05s/it]
Loading pipeline components...: 60%|█████████████████████████████████████████████████████████████████████████████▍ | 3/5 [00:02<00:01, 1.12it/s]The config attributes {'mid_block_add_attention': True} were passed to AutoencoderKLCogVideoX, but are not expected and will be ignored. Please verify your config.json configuration file.
Loading pipeline components...: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:03<00:00, 1.32it/s]
Running on local URL: http://0.0.0.0:7878
Running on public URL: https://6a989d37192c38ef09.gradio.live
This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)
浏览器访问服务
ip:7878
效果展示
效果展示.zip|attachment (1.0 MB)