edm
by NVlabs
Elucidating the Design Space of Diffusion-Based Generative Models (EDM)
AI summary
Generative model framework
This project provides a set of tools and techniques to design and improve diffusion-based generative models.
- stars
- 1.4K
- forks
- 149
- watching
- 29
Similar projects
Found by comparing what the projects do, not just their names.
Generative model library
An unsupervised learning and generative models library for Python, focusing on probabilistic models and efficient computation.
Categorical model extension
Extends generative flows and diffusion models to handle categorical data
Data generation framework
A software framework providing a data infrastructure for generating datasets and deploying generative AI models in circuit optimization tasks.
dfm/tinygp297
GP model
A lightweight library for building Gaussian Process models in Python
GAN toolkit
Generative model toolkit for GANs and image generation tasks
Multimodal model builder
Develops high-resolution multimodal LLMs by combining vision encoders and various input resolutions
baaivision/emu1.7K
Model framework
A multimodal generative model framework
Forgetting prevention framework
An approach to mitigating catastrophic forgetting in federated class incremental learning for vision tasks using a generative model and data-free methods
EVM model
Provides a formal model of the Ethereum Virtual Machine (EVM) semantics in the K programming language.
Generative model framework
An implementation of score-based generative modeling through stochastic differential equations
Diffusion Model Library
A diffusion model library for generating images and videos using JTorch and Diffusers
Generative model booster
Provides an implementation of boosted generative models using Python
ML dev env
An interactive machine learning development environment with support for Scala, JVM, and popular ML libraries.
Vision-Language Model
A deep learning framework for training multi-modal models with vision and language capabilities.
openai/pixel-cnn1.9K
Generative model
A generative model with tractable likelihood and easy sampling, allowing for efficient data generation.
