yier
yier
> Try add > > ```python > torch.backends.cudnn.deterministic = True > ``` > > and > > ```python > torch.cuda.manual_seed_all(seed) > ``` > > to see if you can get...
I found the problem, your test_transform should use CenterCrop not RandomCrop
> Hi @georgeunidev and @myndxero Thank you for your feedback. Colossal-AI is only Linux arch supported currently. Support for window is in our plans, but not a high priority, as...
> 使用python 做自动化处理的时候直接调用API进行处理图片，批量处理 批量化的方法你找到了吗？我也想做这个，就是直接python代码里面输入原图和mask做clean，不想要这个界面，你最后解决了吗
> See our instructions here: https://github.com/IDEA-Research/GroundingDINO#hammer_and_wrench-install not clear
> I'm not sure what you mean by reference only. > > Did you mean detect function? > > ``` > r = api.controlnet_detect(images=[img], module='canny') > r.image > ``` this...
I found the reference , but I use two controlnet but only the first one is valid controlnet_units=[unit2, unit1] 