能不能搞个好复用的东西,这样也好推广啊
装完一堆环境之后,跑代码,发现还要去HG下模型,去HG下模型可以啊,您倒是写明了需要下载什么模型,放在什么路径,我不需要您在线下载,都知道什么原因。
鉴定为就是个博眼球的东西
Sorry for the unclear instructions for downloading the model weights. We have updated the README here.
To further ease your usage, we add auto-downloading to our code. Just run the following command, and the weight will be auto-downloaded.
torchrun --standalone --nproc_per_node 1 scripts/inference.py configs/opensora/inference/16x512x512.py --ckpt-path OpenSora-v1-HQ-16x512x512.pth --prompt-path ./assets/texts/t2v_samples.txt
抱歉,下载模型权限重的说明不明确。我们已在此处更新了自述文件。
为了进一步方便您的使用,我们在代码中添加了自动下载功能。只需运行以下命令,即可重新自动下载。
torchrun --standalone --nproc_per_node 1 scripts/inference.py configs/opensora/inference/16x512x512.py --ckpt-path OpenSora-v1-HQ-16x512x512.pth --prompt-path ./assets/texts/t2v_samples.txt
请问可以提供一个colab的页面么
This issue is stale because it has been open for 7 days with no activity.
The huggingface demo is here: https://huggingface.co/spaces/hpcai-tech/open-sora