edm
Generative model framework
This project provides a set of tools and techniques to design and improve diffusion-based generative models.
Elucidating the Design Space of Diffusion-Based Generative Models (EDM)
1k stars
29 watching
149 forks
Language: Python
last commit: 12 months ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 drckf/paysage | An unsupervised learning and generative models library for Python, focusing on probabilistic models and efficient computation. | 119 |
 ehoogeboom/multinomial_diffusion | Extends generative flows and diffusion models to handle categorical data | 207 |
| nvlabs/circuitops | A software framework providing a data infrastructure for generating datasets and deploying generative AI models in circuit optimization tasks. | 72 |
 dfm/tinygp | A lightweight library for building Gaussian Process models in Python | 297 |
 open-mmlab/mmgeneration | Generative model toolkit for GANs and image generation tasks | 1,925 |
| nvlabs/eagle | Develops high-resolution multimodal LLMs by combining vision encoders and various input resolutions | 549 |
 baaivision/emu | A multimodal generative model framework | 1,672 |
 sarababakn/mfcl-neurips23 | An approach to mitigating catastrophic forgetting in federated class incremental learning for vision tasks using a generative model and data-free methods | 15 |
 runtimeverification/evm-semantics | Provides a formal model of the Ethereum Virtual Machine (EVM) semantics in the K programming language. | 509 |
 yang-song/score_sde | An implementation of score-based generative modeling through stochastic differential equations | 1,524 |
 jittorrepos/jdiffusion | A diffusion model library for generating images and videos using JTorch and Diffusers | 243 |
 ermongroup/bgm | Provides an implementation of boosted generative models using Python | 20 |
 tailhq/dynaml | An interactive machine learning development environment with support for Scala, JVM, and popular ML libraries. | 201 |
| nvlabs/prismer | A deep learning framework for training multi-modal models with vision and language capabilities. | 1,299 |
 openai/pixel-cnn | A generative model with tractable likelihood and easy sampling, allowing for efficient data generation. | 1,921 |