WaveDiff
RePaint
| WaveDiff | RePaint | |
|---|---|---|
| 1 | 2 | |
| 329 | 1,818 | |
| 5.2% | - | |
| 5.4 | 0.0 | |
| 4 months ago | over 1 year ago | |
| Python | Python | |
| GNU General Public License v3.0 only | - |
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.
WaveDiff
-
This AI Paper Introduces a Novel Wavelet-Based Diffusion Framework that Demonstrates Superior Performance on both Image Fidelity and Sampling Speed
Quick Read: https://www.marktechpost.com/2023/03/31/this-ai-paper-introduces-a-novel-wavelet-based-diffusion-framework-that-demonstrates-superior-performance-on-both-image-fidelity-and-sampling-speed/ Paper: https://arxiv.org/pdf/2211.16152.pdf Github: https://github.com/VinAIResearch/WaveDiff
RePaint
-
A better (?) way of doing img2img by finding the noise which reconstructs the original image
This seems to be a very similar method to RePaint.
- RePaint: Inpainting Using Denoising Diffusion Probabilistic Model
What are some alternatives?
3.eeg_recognation - Machine learning for Anonymous detection of an alcoholic by EEG signals
txt2imghd - A port of GOBIG for Stable Diffusion
pytorch_wavelets - Pytorch implementation of 2D Discrete Wavelet (DWT) and Dual Tree Complex Wavelet Transforms (DTCWT) and a DTCWT based ScatterNet
E2FGVI - Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)
pywt - PyWavelets - Wavelet Transforms in Python
stable-diffusion-webui - Stable Diffusion web UI
custom-diffusion - Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
ssqueezepy - Synchrosqueezing, wavelet transforms, and time-frequency analysis in Python
mmgeneration - MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.