modular-diffusion
modular-diffusion copied to clipboard
Python library for designing and training your own Diffusion Models with PyTorch.
How to run the Unconditional Diffusion example on custom dataset without grayscale? It returns error whenever the dataset is not grayscaled
The pages in question are: - https://cabralpinto.github.io/modular-diffusion/guides/custom-modules/ - https://cabralpinto.github.io/modular-diffusion/modules/noise-type/ - https://cabralpinto.github.io/modular-diffusion/modules/loss-function/ The issue is caused by LaTeX expressions that don't fit smaller screens. I'm not quite sure how this could...
It'd be nice to have a dark button switch at the top for those more sensitive to bright lights.
Currently, we're using default Astro settings (Shiki with the `github-dark` theme). However, the syntax highlighting is clearly lacking, with many words not being highlighted. [Useful link](https://docs.astro.build/en/guides/markdown-content/#syntax-highlighting).
As the documentation states, the current implementations are neither the most effective or efficient. The U-Net implementation was adapted from the [The Annotated Diffusion Model](https://huggingface.co/blog/annotated-diffusion) and the Transformer implementation was...
As the library grows, it is important to make sure that nothing is broken when new features are added. After doing some research, I think a good way of doing...
The library currently only works for Python 3.10+ which might pose an inconvenience to some users.
Add a documentation page explaining how standard image generation practices with Diffusion Models translate to Modular Diffusion.
Add a documentation page explaining how standard text generation practices with Diffusion Models translate to Modular Diffusion.
Currently, `ClassifierFree` guidance is hardcoded in the `Model` class and the `Guidance` base class cannot be extended to create custom guidance behavior.