Comments (6)
I fixed by change the torch version. Thank you for your response.
from gen-l-video.
Thanks a lot.
from gen-l-video.
Hi, this error might be (but not definitely) caused by the GPU memory overflow. The default batch size in the hike.yaml file is set to 3, which needs around 30 GB of memory for tuning. If your GPUs have smaller memory, you can try reducing the batch size slightly in the hike.yaml file. This should help with the memory issue. Let me know if you need further assistance!
from gen-l-video.
Could you tell me which version you just changed into? That might help me to inspect the potential problem in my requirements.yaml
from gen-l-video.
I followed this, but my cuda version is 11.7.
I reinstalled torch with cuda 11.7, the problem is fixed
from gen-l-video.
Hello,
I have been able to reproduce the issue you're encountering. The good news is that it can be resolved by compiling xformers from the source code. The new method for setting up the environment has been updated in the readme file. You can choose either cudatoolkit 11.7 or 11.6, both of them will work properly.
Let me know if there's anything else I can help you with.
Best regards.
from gen-l-video.
Related Issues (19)
- Inquiry about Minimum VRAM Requirement for Text-to-Video Model HOT 1
- accelerate launch one-shot-tuning.py --control=pose HOT 4
- code with videocrafter HOT 1
- Question about the One-shot tuning Text-to-Video algorithm HOT 1
- UserWarning: None of the inputs have requires_grad=True. Gradients will be None HOT 2
- Question about LORA
- ValueError: __len__() should return >= 0
- Adapting existing ModelScope architectures to generate long videos HOT 1
- Image guided video editing
- git clone https://huggingface.co/andite/anything-v4.0. This address is currently inaccessible and cannot download relevant weight files. What should I do HOT 1
- different samplers in the temporal co-denoising
- unknown mid_block_type : UNetMidBlock2DCrossAttn HOT 1
- What is the VRAM Requirements? HOT 1
- scheduler_config.json is missing
- Failed to follow the setup instructions on the ubuntu:latest docker image
- How can I use feature Multi-Text Conditioned Long Video Generation? HOT 6
- _pickle.UnpicklingError: invalid load key, 'v'.
- TypeError: 'NoneType' object is not subscriptable
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 gen-l-video.