artbench
denoising-diffusion-pytorch
Our great sponsors
artbench | denoising-diffusion-pytorch | |
---|---|---|
1 | 11 | |
214 | 6,994 | |
- | - | |
10.0 | 8.6 | |
over 1 year ago | 14 days ago | |
Python | Python | |
GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
artbench
-
Public U. Art Club [ so far ✌️ ]
This example is a data set that's been created for training AI models on differentiating between different styles of art. But at the end of that data set an AI is no more capable of defining what impressionism is than it was before but it can produce new art that appears to be impressionist, surrealist, cubist, whatever based on the examples it's been given and the only reason they don't seem to be copies of any handful of paintings is because the AI has scanned and indexed 1,000 distinct paintings in that style. But a human brain can look at a handful of impressionist painting and intuit the commonalities that make "impressionism" a unique style.
denoising-diffusion-pytorch
- Commits · lucidrains/denoising-diffusion-pytorch
-
Help using torchaudio and spectrograms for diffusion
I’m trying to train a diffusion model using this code (https://github.com/lucidrains/denoising-diffusion-pytorch). My idea is to take a short audio segment, transform it into a spectrogram and train the model on these images then have it generate spectrograms then go back to audio. However the model requires square images. I cannot for the life of me figure out how to make a square spectrogram. Also is a regular spectrogram or a mel spectrogram better for this application?
-
Implementation of Google's MusicLM in PyTorch
Generally it's without weights, but MusicLM is also a WIP more mature implementations have descriptions on how to train them and follow ups on small scale/crowd-sourced experiments & research[1].
[1]: https://github.com/lucidrains/denoising-diffusion-pytorch
-
[D] Time Embedding in Diffusion Model
[1] https://colab.research.google.com/drive/1sjy9odlSSy0RBVgMTgP7s99NXsqglsUL?usp=sharing#scrollTo=KOYPSxPf_LL7 [2] https://github.com/lucidrains/denoising-diffusion-pytorch/blob/main/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
-
[D] Can a Diffusion Model be trained with an NVIDIA TITAN X?
Sure. I am using: https://github.com/lucidrains/denoising-diffusion-pytorch
-
[D] Resources to learn and fully understand Diffusion Model Codes
Lucidrains GitHub is always my go to repo for understandable paper implementations https://github.com/lucidrains/denoising-diffusion-pytorch
-
Diffusion model generated exactly the same image as the training image
Thanks for the reply. Is there any suggestion if I wanted to train a model to generate half cat and half butterfly images what I should do? I git cloned the code from https://github.com/lucidrains/denoising-diffusion-pytorch and trained from scratch.
-
[D] Best diffusion model archetype to train?
DDIM/DDPM are the same model to train, they only differ at inference time. To start I would recommend building from lucidrains' MIT licenced version (https://github.com/lucidrains/denoising-diffusion-pytorch). Just play around with the models until you gain an intuition.
-
We just release a complete open-source solution for accelerating Stable Diffusion pretraining and fine-tuning!
Our codebase for the diffusion models builds heavily on OpenAI's ADM codebase , lucidrains, Stable Diffusion, Lightning and Hugging Face. Thanks for open-sourcing!
-
[D] Introduction to Diffusion Models
Once you understand these papers you can begin to understand Palette, and from there I would start with an open-source diffusion implementation like this one and then modify it to suit your needs!
What are some alternatives?
ALAE - [CVPR2020] Adversarial Latent Autoencoders
Papers-in-100-Lines-of-Code - Implementation of papers in 100 lines of code.
autoregressive - :kiwi_fruit: Autoregressive Models in PyTorch.
RAVE - Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder
stylegan2-pytorch - Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
Awesome-Diffusion-Models - A collection of resources and papers on Diffusion Models
pytorch-lightning - Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.
molecule-generation - Implementation of MoLeR: a generative model of molecular graphs which supports scaffold-constrained generation
ColossalAI - Making large AI models cheaper, faster and more accessible
spaCy - 💫 Industrial-strength Natural Language Processing (NLP) in Python