mnistMuddle
blended-latent-diffusion
mnistMuddle | blended-latent-diffusion | |
---|---|---|
2 | 1 | |
3 | 514 | |
- | - | |
0.0 | 4.5 | |
almost 3 years ago | 5 months ago | |
Jupyter Notebook | Jupyter Notebook | |
- | 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.
mnistMuddle
-
Basic Auto Encoder project - Generating poorly written digits [PyTorch]
yes, you are thinking in the right direction. I'm passing the input image to get the latent vector and then decoding it. For each of the 10 classes, I've also computed the average latent vector to represent that label cluster. Check this code here - LINK
-
[P] Basic Auto Encoder project - Generating poorly written digits (PyTorch)
Hi, looking for your thoughts and feedback I created this side project to play with latent domain. The aim was to transform an input image to something that looks somewhere between 2 digits. The repository below will give you a practical exposure to Auto Encoders, Latent Domain, PyTorch, Hosting on Streamlit. GitHub Repository - LINK
blended-latent-diffusion
-
Blended Latent Diffusion's code has been released.
The research paper https://arxiv.org/abs/2206.02779 has finally released their code https://github.com/omriav/blended-latent-diffusion after I asked about it 2 days ago in an issue.
What are some alternatives?
first-order-model - This repository contains the source code for the paper First Order Motion Model for Image Animation
Kandinsky-2 - Kandinsky 2 — multilingual text2image latent diffusion model
Diffusion-Models-Papers-Survey-Taxonomy - Diffusion model papers, survey, and taxonomy
Rerender_A_Video - [SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation
glami-1m - The largest multilingual image-text classification dataset. It contains fashion products.
DiffusionFastForward - DiffusionFastForward: a free course and experimental framework for diffusion-based generative models
MultiDiffusion - Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)
paper-implementations - Attempts to implement various deep learning, computer vision papers.
daam - Diffusion attentive attribution maps for interpreting Stable Diffusion.
min-3-flow - A multistage text to image framework. Built from a inference-reduced set of min-dalle, glid-3-xl, and SwinIR.
WhereIsAI - AI company, product, and tool collection.
Frido - Research code for paper "Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis"