Comments (1)
Hello @100daggerz , I see that in your diffusion parameters, you have modified the timesteps, beta start and beta end.
I would suggest to use the parameters mentioned in the repo and not changing them(for class conditioning you can use the mnist_class_cond.config). One reason for the issue that you are facing could be that at each timestep now you are adding larger amounts of noise, unlike the case of 1000 timesteps.
I am assuming you have done this so the model could be trained faster, but could you try with 1000 timesteps. While the model will take longer to train, I am guessing you would get better results than current case of 200 timesteps.
from stablediffusion-pytorch.
Related Issues (20)
- Bug when saving Latent information? HOT 2
- Unable to run HOT 29
- How to modify config files to generate higher resolution images HOT 8
- How to condition based on multiple features? HOT 2
- Losses for conditional diffusion models HOT 6
- ldm for inpainting HOT 1
- How to improve text-conditioned generation? HOT 1
- How to train a text-conditioned ldm for MNIST dataset? HOT 5
- How to train the model with the image2image mode HOT 2
- Error loading vgg weights
- Why is `disc_fake_loss` applied twice in train_vqvae.py? HOT 2
- How to improve the reconstruction of high-frequency details in the VQVAE training? HOT 8
- Is there a way to configure this to train on Mel Spectrograms? HOT 1
- Why your model generated mnist images are noises? HOT 3
- It wuold be greatly appreciated if model ckpts could be provided HOT 3
- Question - Why using VAE and not just UNet to predict the final output image? HOT 3
- Question about sampling data HOT 2
- Running out of memory... best number of samples for custom data sets? HOT 6
- Unexpected output after sampling using Conditional LDM HOT 6
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 stablediffusion-pytorch.