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

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

基于大模型的智能对话客服工具，支持微信、拼多多、千牛、哔哩哔哩、抖音企业号、抖音、抖店、微博聊天、小红书专业号运营、小红书、知乎等平台接入，可选择 GPT3.5/GPT4.0/ 懒人百宝箱 （后续会支持更多平台），能处理文本、语音和图片，通过插件访问操作系统和互联网等外部资源，支持基于自有知识库定制企业 AI 应用。

一个用来记录武汉大学杨景媛论文问题的仓库

Public repo for HF blog posts

AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓，同时包含工作和科研过程中的新想法、新问题、新资源与新项目

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

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

📚 AIGC 求职面经、必备基础知识、提示词工程、ChatGPT、Stable Diffusion、Prompt、Embedding、Fintune 等 AIGC 求职你所需要知道的一切~

SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions

links and status of cool gradio demos

Consistency Models Made Easy

The official implementation of the ICML 2024 paper "MemoryLLM: Towards Self-Updatable Large Language Models" and "M+: Extending MemoryLLM with Scalable Long-Term Memory"

The official repository of the dots.vlm1 instruct models proposed by rednote-hilab.

MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer

一个高仿小红书的图文社区项目，支持图文发布、社交互动等核心功能，旨在提供从前端到后端的完整实践范本

Official Pytorch Implementation of Our CVPR2023 Paper: "Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization"

A Pytorch Implementation of Finite Scalar Quantization

[ICLR 2026] Discrete Diffusion Divergence Instruct (DiDi-Instruct)

Unofficial implementation of 2D ProlificDreamer

一个基于 ChatGPT、帮助更多的人维护自身权益的 AI 律师

Score identity Distillation with Long and Short Guidance for One-Step Text-to-Image Generation

official code for Diff-Instruct algorithm for one-step diffusion distillation

Official Pytorch Implementation of Our CVPR2023 Paper: "Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation"

A clean Pytorch Implementation of Mean Flow, with FID evaluation on the fly

image-to-text model for PDF.js

We introduce DI*-SDX-1step Model, which is a leading human-preferred 1-step text-to-image model of 1024 resolution.

仿小红书社区

Inference code for SD3