Stars
Code of Pyramidal Flow Matching for Efficient Video Generative Modeling
SCEPTER is an open-source framework used for training, fine-tuning, and inference with generative models.
State-of-the-Art zero-shot voice conversion & singing voice conversion with in context learning
Text-to-Music Generation with Rectified Flow Transformers
Official implementation of "Separate Anything You Describe"
Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.
LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
real time face swap and one-click video deepfake with only a single image
SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement
[CVPR 2024 Highlight] "MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis" (Official Implementation)
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
Example UI implementing the RTVI web client
Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person
Repository for training models for music source separation.
Official implementation of Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
Bring portraits to life via Monitor!
基于python的网页自动化工具。既能控制浏览器，也能收发数据包。可兼顾浏览器自动化的便利性和requests的高效率。功能强大，内置无数人性化设计和便捷功能。语法简洁而优雅，代码量少。
The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.
Implementation of UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks
Understand Human Behavior to Align True Needs
[SIGGRAPH'24] CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
AL GAL是专门为Galgame场景设计的程序，旨在让得每一名用户都能享受到独一无二的剧情。程序基于renpy框架开发