FangGet

grok-1

Grok open release

llama3

The official Meta Llama 3 GitHub site

llm.c

LLM training in simple, raw C/CUDA

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

awesome-pretrained-chinese-nlp-models

Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合

VAR

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

Marigold

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

ml-fastvit

This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023

MoE-LLaVA

Mixture-of-Experts for Large Vision-Language Models

InstantStyle

InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation 🔥

Mora

Mora: More like Sora for Generalist Video Generation

img2img-turbo

One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more

Lumina-T2X

Lumina-T2X is a unified framework for Text to Any Modality Generation

StreamingT2V

StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

StableVITON

[CVPR2024] StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On

llm2vec

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

supersplat

3D Gaussian Splat Editor

LoG

Level of Gaussians

DSINE

[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

sdxs

Official repo of our paper "SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions"

gaussian-opacity-fields

Gaussian Opacity Fields: Efficient and Compact Surface Reconstruction in Unbounded Scenes

MDT

Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)

Long-CLIP

Unichat-llama3-Chinese

UltraLight-VM-UNet

[arXiv] The official code for "UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion Segmentation".

LoRAMoE

LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment

spad

Code for SPAD : Spatially Aware Multiview Diffusers, CVPR 2024

magic-boost

APUS-xDAN-4.0-moe

Its an open source LLM based on MOE Structure.

Taiyi-Diffusion-XL

Taiyi-Diffusion-XL训练代码