namiachy

> Hi, I previously tested using local weights and forgot to remove them. I have now modified the code, so it no longer requires loading any local weights. Please run...

I see, just clone those 4 models and copy into corresponding folders under .cache path

and It throws a new error： Details Traceback (most recent call last): File "C:\Users\namiachy\StoryDiffusion\venv\lib\site-packages\gradio\queueing.py", line 501, in call_prediction output = await route_utils.call_process_api( File "C:\Users\namiachy\StoryDiffusion\venv\lib\site-packages\gradio\route_utils.py", line 258, in call_process_api output =...

> > I see, just clone those 4 models and copy into corresponding folders under .cache path > > It would be easier if your script auto-downloaded the required models...

> > Hi, I previously tested using local weights and forgot to remove them. I have now modified the code, so it no longer requires loading any local weights. Please...

已解决！

> How did you solve it? could not run under project's root path. ```python cd run python gradio_ootd.py ``` https://github.com/levihsu/OOTDiffusion/issues/88

> 您好，请教下，现存这个，您是怎么控制在8G内呢 好像只能添加 --no_llava，看[#65](https://github.com/Fanghua-Yu/SUPIR/issues/65)

我用的cuda118，所以我配的是pip install torch==2.0.0 torchvision==0.15.1 torchaudio==2.0.1 --index-url https://download.pytorch.org/whl/cu118 其他req可以试着运行python app.py，看到报错找不到什么model就pip install什么，torchaudio和torchvision安装前先卸载一遍torchaudio、torchvision和torch，然后运行pip cache purge清下缓存再装 另外报错缺少model不想走弯路的话可以去隔壁[halfzm/ProPainter-Webui](https://github.com/halfzm/ProPainter-Webui/blob/main/readme_zh.md)项目下载整合包：[百度网盘](https://pan.baidu.com/s/1XkQhzCzTtzVfgQg5heQQrA?pwd=jo38)，解压后每次python app.py报错缺什么模型就在整合包里搜，一般都在env目录下，安装的时候加上版本号pip install “mame”==“version”。

torch的安装可以在https://pytorch.org/get-started/previous-versions/页面自己找