AI

基于Transformer的图像局部特征匹配LoFTR介绍 任务 输入两张RGB图像，局部特征匹配算法将输出两张图片对应像素的位置 模型描述 本模型基于LoFTR: Detector-Free Loc

Clone with HTTP bashbash git clone https://www.modelscope.cn/Fengshenbang/Ziya-Visual-Lyrics-14B.git

Paraformer-large模型介绍 ModelScope-FunASR FunASR希望在语音识别方面建立学术研究和工业应用之间的桥梁。通过支持在ModelScope上发布的工业级语音识别模型的

aa aa

Machine Mindset: An MBTI Exploration of Large Language Models If you like our project, please give

Bert-VITS2 VITS2 Backbone with multilingual bert For quick guide, please refer to webui_preprocess.p

EfficientSAM  Paper ｜  GitHub   EfficientSAM: Leveraged Masked Image Pretraining

Introduction An experimental version of IP-Adapter-FaceID: we use face ID embedding from a face reco

CogAgent CogAgent is an open-source visual language model improved based on CogVLM. ? Paper: https:

[](https://github.com/Inter

Diffusion Model Alignment Using Direct Preference Optimization Direct Preference Optimization (DPO)

AnimateDiff This repository is the official implementation of AnimateDiff. It is a plug-and-play mod

[](https://github.com/Inter

**Non-cherry-picked** random batch by just typing two words "forest elf", without any parameter tw

Stable Zero123 Model Description Stable Zero123 is a model for view-conditioned image generation bas

Qwen-72B-Chat ? Hugging Face   |   ? ModelScope   |    ? Paper    ｜   ?️ Demo WeCh

该模型当前使用的是默认介绍模版，处于“预发布”阶段，页面仅限所有者可见。 请根据模型贡献文档说明，及时完善模型卡片内容。ModelScope平台将在模型卡片完善后展示。谢谢您的理解。 Clone wi

模型介绍 该模型输入要求一张RGB图像，输出结果为稠密深度图。 网络结构 模型描述 该模型基于 AdaBins: Depth Estimation using Adaptive Bins；（Refe

Bert-VITS2 VITS2 Backbone with multilingual bert For quick guide, please refer to webui_preprocess.p

单目法向估计算法介绍 任务 输入一张单目RGB图像，单目法向估计算法将分析场景三维结构、输出图像对应的稠密法向图 模型描述 本模型基于Omnidata: A Scalable Pipeline for