A diffusion-based style transfer system that injects multi-token CLIP style embeddings into UNet attention layers for controllable artistic style generation. Includes a custom StyleAttnProcessor, i…

Distributed GPU-Accelerated Framework for Evolutionary Computation. Comprehensive Library of Evolutionary Algorithms & Benchmark Problems.

框架核心是两阶段“粗筛-精滤”数据清洗流程。首先，利用CLIP的多门控决策逻辑进行宏观粗筛，精准剔除插画、图表等非摄影类噪声。随后，利用DINOv2的细粒度特征，创新采用“相对边际分数”识别处于类别边界的混淆样本，并结合GMM模型为各类别动态确定清洗标准。整个流程内置最小样本保留机制，以保护长尾分布下的稀有类别。 在清洗后的高纯度数据上，我们采用非对称协同训练策略。通过Swin Transf…

100% of the code was written by AI. Your Next.js full-stack engineer, integrating Claude, Next.js, shadcn/ui, and a PostgreSQL database.

Official implementation of UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy

https://arxiv.org/abs/2510.10004

🤖 Agentfy is a modular microservices architecture designed to process user requests and execute workflows across multiple social media platforms. ASK ONCE, LET THE AGENT DO THE REST!

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

Official Repo for Paper ‘’HealthGPT : A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation‘’

Evolve-AI

这是一个开箱机即用的服务接口，满足个人对知识库的使用,服务完全免费

Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation

Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models

LAN8720 full function driver library for general MCU and Linux.

惺惺 —— 属于你的社交地盘！惺惺是一个100%开源社交平台，每个人都可以搭建自己的服务器，掌握数据的所有权。此APP非盈利项目！

Liang - Non functional requirements should be part of function interfaces