Giters
Mehdi Cherti (mehdidc)

mehdidc

Geek Repo

110

followers

108

following

5k

stars

Company:Juelich Supercomputing Center (JSC), Forschungszentrum Jülich GmbH, LAION

Location:Germany

Home Page:https://mehdidc.github.io

Twitter:@mehdidc

Github PK Tool:Github PK Tool

Mehdi Cherti's starred repositories

YOLOv6

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

Language:Jupyter NotebookLicense:GPL-3.0Stargazers:5579Issues:62Issues:784

discoart

🪩 Create Disco Diffusion artworks in one line

Language:PythonLicense:NOASSERTIONStargazers:3837Issues:34Issues:106

YaLM-100B

Pretrained language model with 100B parameters

Language:PythonLicense:Apache-2.0Stargazers:3728Issues:48Issues:28

min-dalle

min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch

Language:PythonLicense:MITStargazers:3477Issues:25Issues:76

k-diffusion

Karras et al. (2022) diffusion models for PyTorch

Language:PythonLicense:MITStargazers:2133Issues:41Issues:62

GLIP

Grounded Language-Image Pre-training

Language:PythonLicense:MITStargazers:2011Issues:45Issues:168

ClassyVision

An end-to-end PyTorch framework for image and video classification

Language:PythonLicense:MITStargazers:1585Issues:71Issues:77

parti

License:Apache-2.0Stargazers:1524Issues:56Issues:9

fastdup

fastdup is a powerful free tool designed to rapidly extract valuable insights from your image & video datasets. Assisting you to increase your dataset images & labels quality and reduce your data operations costs at an unparalleled scale.

Language:PythonLicense:NOASSERTIONStargazers:1437Issues:21Issues:227

Video-Pre-Training

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

Language:PythonLicense:MITStargazers:1225Issues:27Issues:30

CLAP

Contrastive Language-Audio Pretraining

Language:PythonLicense:CC0-1.0Stargazers:1204Issues:27Issues:77

stable-diffusion

Language:Jupyter NotebookLicense:MITStargazers:1028Issues:24Issues:25

Arrival-Movie-Live-Coding

Documents from a live coding session by Christopher Wolfram related to content from the 2016 film Arrival

Language:MathematicaLicense:NOASSERTIONStargazers:947Issues:84Issues:2

RegionCLIP

[CVPR 2022] Official code for "RegionCLIP: Region-based Language-Image Pretraining"

Language:PythonLicense:Apache-2.0Stargazers:662Issues:10Issues:97

LIA

[ICLR 22] Latent Image Animator: Learning to Animate Images via Latent Space Navigation

Language:PythonLicense:NOASSERTIONStargazers:575Issues:28Issues:23

parti-pytorch

Implementation of Parti, Google's pure attention-based text-to-image neural network, in Pytorch

Language:PythonLicense:MITStargazers:509Issues:14Issues:10

dalle2-laion

Pretrained Dalle2 from laion

Language:PythonStargazers:496Issues:23Issues:38

simulacra-aesthetic-captions

Dataset of prompts, synthetic AI generated images, and aesthetic ratings.

Stargazers:384Issues:13Issues:9

vqgan-clip

Language:Jupyter NotebookLicense:MITStargazers:342Issues:9Issues:16

LAION-Face

The human face subset of LAION-400M for large-scale face pretraining.

Language:PythonStargazers:253Issues:4Issues:10

perceiver-ar

Language:PythonLicense:Apache-2.0Stargazers:228Issues:12Issues:8

artbench

Benchmarking Generative Models with Artworks

Language:PythonLicense:NOASSERTIONStargazers:217Issues:8Issues:6

Implicit-Language-Q-Learning

Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"

Language:PythonLicense:MITStargazers:192Issues:6Issues:8

glid-3

combination of OpenAI GLIDE and Latent Diffusion

Language:PythonLicense:MITStargazers:135Issues:9Issues:4

t5x_retrieval

Language:PythonLicense:Apache-2.0Stargazers:88Issues:6Issues:4

perceiver-ar-pytorch

Implementation of Perceiver AR, Deepmind's new long-context attention network based on Perceiver architecture, in Pytorch

Language:PythonLicense:MITStargazers:85Issues:4Issues:8

Elevater_Toolkit_IC

Toolkit for Elevater Benchmark

Language:PythonLicense:MITStargazers:64Issues:4Issues:15

temporal-embedding-aggregation

Aggregating embeddings over time

Language:PythonStargazers:30Issues:3Issues:29

conditioned-prior

(wip) Use LAION-AI's CLIP "conditoned prior" to generate CLIP image embeds from CLIP text embeds.

Language:PythonLicense:MITStargazers:23Issues:4Issues:0

NeoGen

A tool for generating awesome AI art

Language:PythonStargazers:17Issues:5Issues:3