zzsi

stable-diffusion

A latent text-to-image diffusion model

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

dolly

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

lora

Using Low-rank adaptation to quickly fine-tune diffusion models.

taming-transformers

Taming Transformers for High-Resolution Image Synthesis

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

butterfly

🦋Butterfly，A JavaScript/React/Vue2 Diagramming library which concentrate on flow layout field. (基于JavaScript/React/Vue2的流程图组件)

python-causality-handbook

Causal Inference for the Brave and True. A light-hearted yet rigorous approach to learning about impact estimation and causality.

AutoPR

Run AI-powered workflows over your codebase

edm

Elucidating the Design Space of Diffusion-Based Generative Models (EDM)

multimodal-maestro

Effective prompting for Large Multimodal Models like GPT-4 Vision, LLaVA or CogVLM. 🔥

pix2seq

Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)

memorizing-transformers-pytorch

Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch

fast-DiT

Fast Diffusion Models with Transformers

WonderJourney

scholarphi

An interactive PDF reader.

ChangeFormer

[IGARSS'22]: A Transformer-Based Siamese Network for Change Detection

mae_st

Official Open Source code for "Masked Autoencoders As Spatiotemporal Learners"

Prompt-Segment-Anything

This is an implementation of zero-shot instance segmentation using Segment Anything.

block-recurrent-transformer-pytorch

Implementation of Block Recurrent Transformer - Pytorch

reward-modeling

latent-diffusion-for-language

lvc

Official repo for our CVPR 22 paper: "Label, Verify, Correct: A Simple Few-Shot Object Detection Method"

energy-transformer-jax

The Energy Transformer block, in JAX

TransCD

A Transformer-based model for scene change detection

Energy-Based-CrossAttention

The official repository of "Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models".

audioslides.io

Use Amazon Polly, Google Slides and FFMpeg to create videos that can be updated at anytime by anyone. This project is written in Elixir.

colab-badge-action

Organize your jupyter notebooks with "Open in Colab" badges

MDSM

Multiscale de-noising score matching