Latent Consistency Models Official Repository of the paper: Latent Consistency Models. Project Page:

HybridFormer通用图像分类模型介绍 采用ImageNet-1K数据训练，用于识别1000类通用物体。 创空间快速可视化展示: HybridFormer图像分类-通用 模型描述 Hy

MultiDiffusion MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation MultiDiffusion

SimpleSDXL 在Fooocus基础上增强功能，可无缝迁移升级 Enhanced features base on Fooocus, can be seamless upgrading 中

A cutting-edge foundation for your very own LLM. ?Github • ? TigerBot • ? Hugging Face 快速开始

功能概述 输入一段英文文本，和一张图片，生成符合文本描述和图片中人物姿态的人物图片 输入示例： 文本描述"：a woman standing by the sea" 图片：) 输出示例： 输出为： 环

功能概述 基于扩散模型的图像特征抽取，可用于做特征点匹配。 Project Page | Paper | Colab Demo 环境准备 安装独立repo库 pip install git+http

Motion LoRAs Motion LoRAs allow adding specific types of motion to your animations. Currently the

Motion LoRAs Motion LoRAs allow adding specific types of motion to your animations. Currently the

Motion LoRAs Motion LoRAs allow adding specific types of motion to your animations. Currently the

Motion LoRAs Motion LoRAs allow adding specific types of motion to your animations. Currently the

Motion LoRAs Motion LoRAs allow adding specific types of motion to your animations. Currently the

Motion LoRAs Motion LoRAs allow adding specific types of motion to your animations. Currently the

Motion LoRAs Motion LoRAs allow adding specific types of motion to your animations. Currently the

Motion LoRAs Motion LoRAs allow adding specific types of motion to your animations. Currently the

AnimateDiff is a method that allows you to create videos using pre-existing Stable Diffusion Text to

AnimateDiff is a method that allows you to create videos using pre-existing Stable Diffusion Text to

MiniChat-3B ? arXiv | ? GitHub | ? HuggingFace-MiniMA | ? HuggingFace-MiniChat | ? ModelScope-MiniMA

MiniMA-3B ? arXiv | ? GitHub | ? HuggingFace-MiniMA | ? HuggingFace-MiniChat | ? ModelScope-MiniMA |

ERes2Net 语种识别模型 ERes2Net模型结合全局特征和局部特征，从而提高说话人识别性能。局部特征融合将一个单一残差块内的特征融合提取局部信号；全局特征融合使用不同层级输出的不同尺度声学特征