ZhouXiaolin

MiniGPT-4

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

hysteria

Hysteria is a powerful, lightning fast and censorship resistant proxy.

ChatGLM3

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

IF

IP-Adapter

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

latent-consistency-model

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

adetailer

Auto detecting, masking and inpainting with detection model.

PixArt-alpha

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

consistencydecoder

Consistency Distilled Diff VAE

axlearn

An Extensible Deep Learning Library

ninja

Reverse engineered ChatGPT proxy

Paella

Official Implementation of Paella https://arxiv.org/abs/2211.07292v2

OptiVideoEditor-for-iOS

Native Video editor: Video trim, Audio, Video merge, Slow and fast motion, Video transition, Text and Image, Filters, etc...

Collaborative-Diffusion

[CVPR 2023] Collaborative Diffusion

FQ-ViT

[IJCAI 2022] FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer

ArXivQA

WIP - Automated Question Answering for ArXiv Papers with Large Language Models (https://arxiv.taesiri.xyz/)

transformer_vq

QUIK

Repository for the QUIK project, enabling the use of 4bit kernels for generative inference

SSD-1B

SSD-1B, an open-source text-to-image model, outperforming previous versions by being 50% smaller and 60% faster than SDXL.

LLM-FP4

The official implementation of the EMNLP 2023 paper LLM-FP4

Frequency_Aug_VAE_MoESR

Latent-based SR using MoE and frequency augmented VAE decoder

low-bit-optimizers

Low-bit optimizers for PyTorch

deforum-kandinsky

Kandinsky x Deforum — generating short animations

DPM-Solver-v3

Official code for "DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics" (NeurIPS 2023)

MNISTDiffusion

Implement a MNIST(also minimal) version of denoising diffusion probabilistic model from scratch.The model only has 4.55MB.

ScaleLong

The official repository of paper "ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection" (NeurIPS 2023)

FlowGrad

i2vgen-xl