ml-lab's repositories
artbench
Benchmarking Generative Models with Artworks
Background-Matting
Background Matting: The World is Your Green Screen
CogVideo
Text-to-video generation.
dalle-mini
DALL·E Mini - Generate images from a text prompt
functional-transformer
A pure-functional implementation of a machine learning transformer model in Python/JAX
Gradient-Free-Optimizers
Simple and reliable optimization with local, global, population-based and sequential techniques in numerical discrete search spaces.
hummingbird
Hummingbird compiles trained ML models into tensor computation for faster inference.
imagen-pytorch
Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
img2dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
instant-ngp
Instant neural graphics primitives: lightning fast NeRF and more
iris-2
Transformers are Sample Efficient World Models
kbd-audio
🎤⌨️ Acoustic keyboard eavesdropping
MiMA
Model of an idealized Moist Atmosphere: Intermediate-complexity General Circulation Model with full radiation
peacasso
UI interface for experimenting with multimodal (text, image) models (stable diffusion).
pips
Particle Video Revisited
Poisson_flow
Code for NeurIPS 2022 Paper, "Poisson Flow Generative Models"
pose-with-style
[SIGGRAPH Asia 2021] Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN
Relighting4D
[ECCV 2022] Relighting4D: Neural Relightable Human from Videos
setfit
Efficient few-shot learning with Sentence Transformers
stable-diffusion-tensorflow
TensorFlow/Keras port of Stable Diffusion
stable-dreamfusion
A working implementation of text-to-3D dreamfusion, powered by stable diffusion.
table-transformer
Model training and evaluation code for our dataset PubTables-1M, developed to support the task of table extraction from unstructured documents.
Thin-Plate-Spline-Motion-Model
[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.
ums
Total Nitrogen Estimation in Agricultural Soils via Aerial Multispectral Imaging and LIBS.
YaLM-100B
Pretrained language model with 100B parameters