DemoFusion
Ruoyi's HomePage
排序
ActAnywhere
ActAnywhere: Subject-Aware Video Background Generation
Draw an Audio
Qi Yang's academic homepage. Research in computer vision, multi-modal learning, and AIGC.
Lepton Search
一个功能强大、易于使用的对话式AI搜索引擎，它提供了一个开源的平台，允许用户构建和运行自定义的搜索和AI应用。通过集成大语言模型和搜索引擎，Lepton Search能够提供快速准确的搜索结果，同时支持用户界面的定制和搜索结果的共享与缓存，非常适合需要构建复杂搜索功能的企业和开发者。
Vary-toy
Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models
Void
Void is an open source AI IDE with full privacy.
abab-music-1
MiniMax 模型体系涵盖语言、视频、语音、图像与音乐五大方向，助力开发者高效构建智能应用。
Llama 3.2
Build with Meta's AI models and tools. Access Muse Spark through Muse Code and Meta Model API with resources to get started.
MetaGPT
Discover the journey from MetaGPT's open-source roots through MGX to Atoms — a complete AI-powered commercialization engine. Describe your idea and start building instantly.
Follow Your Pose
DESCRIPTION META TAG
IP-Adapter
IP-Adapter
OLMo
403
MotionCtrl
Zhouxia Wang — Tenure-Track Associate Professor at Sun Yat-sen University. Research on computer vision, controllable generation, and image/video restoration.
DiffusionGPT
Site not found · GitHub Pages
Make-A-Character
Site not found · GitHub Pages