youtianhong

**Describe the bug** The resulting image is not clear enough, There are silhouettes behind the characters **Is there any way to optimise this by rembg?** **To Reproduce** I have tested...

run rembg error

9

**Describe the bug** **When I run "rembg --help", it report this error as below:** A module that was compiled using NumPy 1.x cannot be run in NumPy 2.0.0 as it...

MuseV多块显卡执行图片生成依然报OOM

10

问题背景： 启动的时候，大概占用了12G显存，然后我在gradio界面上开始执行图生视频，报OOM return torch.group_norm(input, num_groups, weight, bias, eps, torch.backends.cudnn.enabled) torch.cuda.OutOfMemoryError: **CUDA out of memory. Tried to allocate 176.00 MiB (GPU 0; 14.57 GiB total capacity; 13.61 GiB already allocated; 118.75...

text2video 可以跑 （环境4块显卡，共64G） 1.使用默认显卡，video2video跑不了， 报torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 456.00 MiB (GPU 0; 14.57 GiB total capacity; 13.55 GiB already allocated; 192.75 MiB free; 14.12 GiB reserved...

Currently we will use scenarios where multiple threads are inferencing at the same time, is there any solution for this, CUDA inference logic is not thread safe? 请问有什么解决办法吗？CUDA推理逻辑不是线程安全的？ Error is...