-
**Feature (What you would like to be added):**
Docker image with shell access, I currently cannot shell into the pod in Kubernetes.
**Motivation (Why is this needed?):**
I am following https://gi…
-
### First, confirm
- [X] I have read the [instruction](https://github.com/Gourieff/sd-webui-reactor/blob/main/README.md) carefully
- [X] I have searched the existing issues
- [X] I have updated the e…
-
`The Efficient Diffusion Model for Image Restoration by Residual Shifting` is actually an extended version of ResShift, which is worth mentioning.
-
First,it is a real awesome work!
When I run the train.py in the file named Deblurring, I got an error:
> TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the ten…
-
Thanks for the repo. I wonder why you employed 3D deformable convolution along only "HW" dimensions (self.dcn0 = DeformConvPack_d(nf, nf, kernel_size=3, stride=1, padding=1, dimension='HW') in model.p…
-
**Describe the bug**
An invisible "Restoration Table" that lets you see inside the floor. I have not yet put the table of restoration for my players, I began to look at it this morning, I had put one…
vdl19 updated
3 weeks ago
-
I think it would be kind of cool to see the ability to have player color presets in the player settings menu, akin to how the Eternity Engine does it.
Here's an example of what I mean:
**Build Number**: 20241029.5
**Branch**: main
**Platform/OS**: Windows 11/Windows 11/Linux Ubuntu 22.04/MacOS Sequoia 15.0(Apple M1 Pro)
**Architecture**…
-
在做raindrop时，发现device用的是self.accelerator.device，但是运行的时候没有用到GPU，我简单改为'cuda'却会报错，不知道该如何使用GPU，还望指点一下，感谢
bnufw updated
1 month ago
-
作者您好，在您所提的框架中，往原始图像中加入噪声以及denoising network是不是共同构成diffusion model？此外denoising network的输出是什么？是否可以进行修改让其输出已生成的去噪后的高质量图像？ 因为我想使用这个模块仅用于图像去噪，不知是否可行，期待您的答复。