jy0205

OpenHands. 🙌 OpenHands: AI-Driven Development

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

NExT-Vid. Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations

SoraWatermarkCleaner. The fastest and highest-quality deep learning powered Sora2 watermark cleaner.

ms-swift. Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

Awesome_Think_With_Images. Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.

Vision-Language-Models-Overview. A most Frontend Collection and survey of vision-language model papers, and models GitHub repository. Continuous updates.

Megatron-Bridge. Training library for Megatron-based models with bidirectional Hugging Face conversion capability

EasyR1. EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

InternVL. [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Pai-Megatron-Patch. The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

big_vision. Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

Awesome-RL-based-Reasoning-MLLMs. This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-based Reasoning MLLMs!

DMD2. (NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

IC-Light. More relighting!

Cosmos-Tokenizer. A suite of image and video neural tokenizers

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Pyramid-Flow. [ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling

flux. Official inference repo for FLUX.1 models

Duix-Mobile. 🚀 The best real-time interactive AI avatar(digital human) with on-premise deployment and <1.5 s latency.

MINT-1T. 🍃 MINT-1T: A one trillion token multimodal interleaved dataset.

flash-attention. Fast and memory-efficient exact attention

open_clip. An open source implementation of CLIP.

chameleon. Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

ReNO. [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization

rfpp. The codebase of our paper "Improving the Training of Rectified Flows", NeurIPS 2024

cog-consistent-character. Create images of a given character in different poses

LongLoRA. Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

RectifID. [NeurIPS 2024] RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance

HunyuanDiT. Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

piecewise-rectified-flow. PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)

magvit2-pytorch. Implementation of MagViT2 Tokenizer in Pytorch

kornia. 🐍 Geometric Computer Vision Library for Spatial AI

video-subtitle-remover. 基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

InstanceDiffusion. [CVPR 2024] Code release for "InstanceDiffusion: Instance-level Control for Image Generation"

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

Awesome-Video-Datasets. Video datasets

Latte. [TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation.

CompressAI. A PyTorch library and evaluation platform for end-to-end compression research

Learned_Compression. This repository is a paper digest of DNN-based approaches in data compression tasks.

InstaFlow. :zap: InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)

RectifiedFlow. Official Implementation of Rectified Flow (ICLR2023 Spotlight)

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

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

DiT. Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

VideoSys. VideoSys: An easy and efficient system for video generation

ml-ferret. Python

open-prompts. Python

Awesome-Video-Diffusion-Models. [CSUR] A Survey on Video Diffusion Models

Video-ChatGPT. [ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.

generative-models. Generative Models by Stability AI

Video-LLaVA. 【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Text2Video-Zero. [ICCV 2023 Oral] Text-to-Image Diffusion Models are Zero-Shot Video Generators

RewireNeuron. [NeurIPS 2023] Rewiring Neurons in Non-Stationary Environments

Awesome-Video-Diffusion. A curated list of recent diffusion models for video generation, editing, and various other applications.

video2dataset. Easily create large video dataset from video urls

webvid. Large-scale text-video dataset. 10 million captioned short videos.

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

vector-quantize-pytorch. Vector (and Scalar) Quantization, in Pytorch

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

pytorch-fid. Compute FID scores with PyTorch.

WanJuan1.0. 万卷1.0多模态语料

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

mmc4. MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

Megatron-LM. Ongoing research training transformer models at scale

mPLUG-Owl. mPLUG-Owl: The Powerful Multi-modal Large Language Model Family

webdataset. A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

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

datacomp. DataComp: In search of the next generation of multimodal datasets

LAVIS. LAVIS - A One-stop Library for Language-Vision Intelligence

Fengshenbang-LM. Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

awesome-LLMs-In-China. 中国大模型

ChatGLM2-6B. ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

Chinese-LLaMA-Alpaca. 中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

Video-LLaMA. [EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

InternVideo. [ECCV2024] Video Foundation Models & Data for Multimodal Understanding

img2dataset. Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

open_flamingo. An open-source framework for training large multimodal models.

Awesome-Multimodal-Large-Language-Models. :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

FastChat. An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

CVinW_Readings. A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''

Awesome-Anything. General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX

Dreambooth-Stable-Diffusion. Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

dinov2. PyTorch code and models for the DINOv2 self-supervised learning method.

ImageBind. ImageBind One Embedding Space to Bind Them All

PyTorch-VAE. A Collection of Variational Autoencoders (VAE) in PyTorch.

java-books-collections. :books:Java编程书籍收集分享。Java programming books collection to share.:rocket:

AutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Uni-Perceiver. Python

bot-on-anything. A large model-based chatbot builder that can quickly integrate AI models (including ChatGPT, Claude, Gemini) into various software applications (such as Telegram, Gmail, Slack, and websites).

ControlNet. Let us control diffusion models!

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

stable-diffusion-webui. Stable Diffusion web UI

stable-diffusion. A latent text-to-image diffusion model

optimate. A collection of libraries to optimise AI model performances

Open-Assistant. OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.