mehdidc

feed_forward_vqgan_clip

Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt

compositionality-datasets-merge

vqgan_nodep

VQGAN from LDM without hell of dependencies

paper_parser

PickScore

retrieval_annotations

scaling-laws-openclip

Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)

simple_dedup

ae_gen

any2dataset

Turn any collection of files into a dataset

dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

model2dataset

clip-retrieval

Easily compute clip embeddings and build a clip retrieval system with them

ConvNeXt

Code release for ConvNeXt model

dataset2metadata

dataset2prediction

dedup_benchmark

deit

Official DeiT repository

denoising-diffusion-gan

Tackling the Generative Learning Trilemma with Denoising Diffusion GANs https://arxiv.org/abs/2112.07804

dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.

embedding-reader

Efficiently read embedding in streaming from any filesystem

litellm

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

ml-engineering

Machine Learning Engineering Guides and Tools

open-diffusion

Simple large-scale training of stable diffusion with multi-node support.

open_clip

An open source implementation of CLIP.

pHash

pHash - the open source perceptual hash library

SLIP

Code release for SLIP Self-supervision meets Language-Image Pre-training

slurm-tracking-bot

Simple slurm tracking bot to check usage

stable-diffusion-webui

Stable Diffusion web UI