zhen-dong / magic-me Goto Github PK
View Code? Open in Web Editor NEWCodes for ID-Specific Video Customized Diffusion
Home Page: https://magic-me-webpage.github.io/
License: Apache License 2.0
Codes for ID-Specific Video Customized Diffusion
Home Page: https://magic-me-webpage.github.io/
License: Apache License 2.0
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~ π
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!
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?
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?
Line 357 in 16bf220
pytorch1.12.0 canβt work with any versions of xformers, but the train.py requiring xformers to be used. How can i solve this problem?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
π Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. πππ
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google β€οΈ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.