zhen-dong / magic-me Goto Github PK

Hello, AUTOMATIC1111 I will install Magie-Me add-ons https#/github.com/Zhen-Dong/Magic-Me on a server with 16 video card, the answer is enough please

Hi @visionMaze @Zhen-Dong ,
thanks for the interesting work! May I ask if there is any plan to apply this method to other VDMs, such as VideoCrafter?

Hi, thanks for your excellent work here.

After reading the paper, I have got two problems: 1) how to derive a natural face by leveraging partial denoising to refine the face in Face VCD without face keypoint control since I2I or V2V pipelines would lead to inconsistent local results; 2) how to preserve the background, with mask or something or the extended ID token would help?

thanks!

Hi, firstly thanks for your great work!

During train.py LINE 181 - LINE 198, I get these warnings while loading pretrained ckpts.

load inferece unet missing keys: 588, unexpected keys: 0
load clip text encoder missing keys: 0, unexpected keys: 1
load inferece vae missing keys: 16, unexpected keys: 16

I'm not very sure if it's ok, because the code reports that there're several tensors not found or loaded. I wonder if you could share your log during training, so I can check by myself. THANKS~ 😄

Hello, appreciate for sharing this amazing work.

After reading the paper and code, I wonder which part in the code is about Face VCD &Tile VCD. Thanks!

While this seems like legitimate project with good intentions, you violate various laws and the GitHub Terms of Usage by scraping GitHub emails and sending spam advertisement emails for this project.

Please stop sending spam emails and never do this again.

loss = loss.sum([1,2,3,4])/masks.sum([1,2,3,4])
if masks.sum([1,2,3,4]) contains 0, then the loss will be NaN
so i simply change the upper code to loss = loss.sum([1,2,3,4])/(masks.sum([1,2,3,4])+1e-6), Is this appropriate?

Dear authors,
Thanks for your awesome work. When I created the environment with "conda env create -f environment.yaml", I got error "libtorch_cpu.so: undefined symbol: iJIT_NotifyEvent". I didn't find solution in the internet. Have you ever met this issue?

what processor is used please answer

Thank you for your very good work, and, where can I download ComfyUI's Magic-Me-3D Gaussian Noise node?

Thank you for your excellent work. Could you provide a pipeline that can generate the samples of video editing with reference images in the readme?

pytorch1.12.0 can’t work with any versions of xformers, but the train.py requiring xformers to be used. How can i solve this problem?