Comments (4)
jet3004
commented on July 24, 2024
Yes, please consider this!
from moore-animateanyone.
lixunsong
commented on July 24, 2024
We haven't tested on Mac, so we're not sure if it will run. You can give it a try and welcome your feedbacks :)
from moore-animateanyone.
cocktailpeanut
commented on July 24, 2024
@lixunsong I got through the installation issues by installing eva-decord instead of decord and making some other adjustments, and also made some changes to the parts with "cuda" hardcoded cocktailpeanut@9a66b89, and got it to start, but when i try to run the inference it crashes running out of memory.
I was guessing that maybe it's not enough to simply change the device, but need to do some other things in addition? Didn't dig too deep into the code enough to understand what I need to do if there is a way. Let me know if there's something I could try!
from moore-animateanyone.
lixunsong
commented on July 24, 2024
Hello @cocktailpeanut , I'm not sure the OOM error was cuased by the limit gpu VRAM. You can first run a smaller generation size, eg 256x256.
from moore-animateanyone.
Related Issues (20)
- When gradient_accumulation_steps is set to greater than 1, a RuntimeError occurs: "Trying to backward through the graph a second time (or directly access saved tensors after they have already been freed)."
- The confusion between pretrained AutoencoderKL version
- About the implementation of the pose guider
- The align between the pose and the reference pic HOT 1
- RuntimeError: Trying to backward through the graph a second time
- 请问权重有百度网盘的下载链接吗？
- error occurs when set gradient_checking = True during stage 2 HOT 1
- OpenSeeFace onnx模型加载失败 HOT 2
- ModuleNotFoundError: No module named 'tracker' HOT 2
- (IDEA/REQUEST) Possible consistancy for Face Reenactment and better animation HOT 1
- stag2 erro!!!!!!!!!! how to sovle it? HOT 6
- Right now it's about 10k videos on Traing dataset
- stage2!!!!how to deal with this issues HOT 1
- Short time
- The issue of mse_loss_weights related to snr
- How does the InferenceNet interact with the denoising unet HOT 3
- 想学习AnimateAnyone快加学习交流群 HOT 4
- About the future works
- About Trainable parameters in ReferenceNet
- A confusion relating to the input range of VAE model HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from moore-animateanyone.