iFighting

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

flux

Official inference repo for FLUX.1 models

StableCascade

Official Code for Stable Cascade

consistency_models

Official repo for consistency models.

Firefly

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

latent-consistency-model

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

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!

datasets

🎁 5,400,000+ Unsplash images made available for research and machine learning

DreamCraft3D

[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

LlamaGen

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

minisora

MiniSora: A community aims to explore the implementation path and future development direction of Sora.

Awesome-Video-Datasets

Video datasets

rq-vae-transformer

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

Groma

[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization

LaVIT

LaVIT: Empower the Large Language Model to Understand and Generate Visual Content

VBench

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

FreeNoise

[ICLR 2024] Code for FreeNoise based on VideoCrafter

MiraData

Official repo for paper "MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions"

TATS

Official PyTorch implementation of TATS: A Long Video Generation Framework with Time-Agnostic VQGAN and Time-Sensitive Transformer (ECCV 2022)

UniRef

[ICCV2023] Segment Every Reference Object in Spatial and Temporal Spaces

laion-datasets

Description and pointers of laion datasets

OmniTokenizer

OmniTokenizer: one model and one weight for image-video joint tokenization.

TaiSu

TaiSu（太素）--a large-scale Chinese multimodal dataset（亿级大规模中文视觉语言预训练数据集）

LVIS-INSTRUCT4V

GenerateU

[CVPR2024] Generative Region-Language Pretraining for Open-Ended Object Detection

tarsier

VAR-CLIP

Implements VAR+CLIP for image generation

OmniVid

vaex

🔥stable, simple, state-of-the-art VQVAE toolkit & cookbook

ControlVAR

This is the official implementation for ControlVAR.