Comments (2)
Hello,
Yes but that is just for the saving images part. The reason its like that cause for conditional cases I wanted to get original image prediction at all time to visualize when does diffusion start getting a good original image prediction(and I also needed it for my videos to compare how quickly model reaches a good original image prediction with/without conditioning ). Thats why instead of saving xt at all time instances, I save x0_pred for all cases except t=0.
If you look at unconditional sampling, there I am saving xt only (https://github.com/explainingai-code/StableDiffusion-PyTorch/blob/main/tools/sample_ddpm_vqvae.py#L42). So it was just a matter of what I wanted to save and after that forgot to modify. But you are right, will change to consistently save xt all places.
from stablediffusion-pytorch.
Thank you very much!
from stablediffusion-pytorch.
Related Issues (14)
- why the ldm can't generate images well? HOT 2
- 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
- Running out of memory... best number of samples for custom data sets? HOT 6
- Unexpected output after sampling using Conditional LDM HOT 6
- Bug when saving Latent information? HOT 2
- The training loss is not decreasing HOT 1
- Unable to run HOT 29
- How to modify config files to generate higher resolution images HOT 7
- How to condition based on multiple features? HOT 2
- Losses for conditional diffusion models HOT 6
- ldm for inpainting 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 stablediffusion-pytorch.