Comments (14)
Got the same error. After googling, I found the command:
pip install taming-transformers-rom1504
It worked until I get another error down the line... Will create an issue soon
from instruct-pix2pix.
Can you offer a bit more context? What are you trying to run?
from instruct-pix2pix.
When I want to run "edit_app.py" it gives this error
from instruct-pix2pix.
I'm not able to reproduce this error. Have you installed the dependencies and downloaded a checkpoint?
conda env create -f environment.yaml
conda activate ip2p
bash scripts/download_checkpoints.sh
from instruct-pix2pix.
I'm not able to reproduce this error. Have you installed the dependencies and downloaded a checkpoint?
conda env create -f environment.yaml conda activate ip2p bash scripts/download_checkpoints.sh
Yes, I did these steps.
from instruct-pix2pix.
Did the environment creation (the first command) return any errors?
from instruct-pix2pix.
I also had to downgrade the cudatoolkit package to version 9.0 (I was getting an error in the creation of the conda env).
from instruct-pix2pix.
Got the same error. After googling, I found the command: pip install taming-transformers-rom1504 It worked until I get another error down the line... Will create an issue soon
pip install taming-transformers-rom1504 helped me solve the problem. But now I'm getting an error "AssertionError: Torch not compiled with CUDA enabled". I guess I need to downgrade too.
from instruct-pix2pix.
Thanks for the updates. Let me know once you figure out a working formula, and we can figure out how to integrate a fix for your systems into the current environment.yaml requirements file.
from instruct-pix2pix.
Got the same error. After googling, I found the command: pip install taming-transformers-rom1504 It worked until I get another error down the line... Will create an issue soon
pip install taming-transformers-rom1504 helped me solve the problem. But now I'm getting an error "AssertionError: Torch not compiled with CUDA enabled". I guess I need to downgrade too.
Same here. Haven't found a solution to that...
from instruct-pix2pix.
sorry to chime in with unrelated post - but @holynski I guess you saw https://github.com/haha-lisa/RDM-Region-Aware-Diffusion-Model ? seems like there's some overlap. need to explore papers and code more.
best to install pytorch with cuda from the selected option / seems conda is installing cpu option by default.
https://pytorch.org/get-started/locally/
from instruct-pix2pix.
Have you try this
bash scripts/download_checkpoints.sh
from instruct-pix2pix.
The error message "ImportError: cannot import name 'VectorQuantizer2' from 'taming.modules.vqvae.quantize'" suggests that there is a problem with the import statement for the 'VectorQuantizer2' module from the 'taming.modules.vqvae.quantize' package.
There could be a few reasons for this error:
1.The package 'taming' is not installed on your system, or it's not in the correct location. Make sure that the package is installed and that the import statement is pointing to the correct location.
2.The module 'VectorQuantizer2' does not exist in the package 'taming.modules.vqvae.quantize'. You can check the package documentation to see if it's been replaced or removed in a later version.
3.There's a naming collision with another module or package in your code. Make sure that you don't have any modules or packages with the same name in your codebase.
4.There's a typo in your import statement. Make sure that the package, module, and submodule names are spelled correctly.
Try to resolve the issue by checking the package location, package version, module name and import statement. Also, you can try to install the package again, or use a different version of the package.
from instruct-pix2pix.
Got the same error. After googling, I found the command: pip install taming-transformers-rom1504 It worked until I get another error down the line... Will create an issue soon
pip install taming-transformers-rom1504 helped me solve the problem. But now I'm getting an error "AssertionError: Torch not compiled with CUDA enabled". I guess I need to downgrade too.
Have you solved the issue?
from instruct-pix2pix.
Related Issues (20)
- "Some weights of the model checkpoint at openai/clip-vit-large-patch14 were not used" HOT 2
- Hi , any update ?
- The edit_cli runs well but edit_app returns nothing. HOT 1
- FeatureReguest/Enhancement/Idea
- NOT the file config.json?
- which version cuda should i choose for this application?
- Cannot Download Checkpoint HOT 2
- finetuning pretrained model using the custom dataset HOT 5
- Learning Rate scheduler
- demo broken
- How to Accelerate Training Data Generation with SDXL-Turbo or LCM?
- Torch version conflict between ip2p and k-diffusion HOT 1
- is the finetuned GPT3 model that generates edit captions from edit instructions openly available?
- Max Resolution
- Prompt to prompt implementation for dataset generation
- metadata.jsonl in the clip-filtered-dataset
- AttributeError: 'AutoencoderKL' object has no attribute 'quantize' HOT 2
- RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu) HOT 3
- Masking
- How to download the dataset in China Mainland
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 instruct-pix2pix.