DenchiSoft / VTubeStudio

Unity script to enforce window aspect ratio for standalone Windows 32/64bit builds.

Experiments with Live2D models and lighting/post-processing.

Example code for frequency-based approach to lip-syncing for use with Live2D Cubism models.

Example Unity application that renders a Live2D Cubism model directly onto your Desktop. Windows only.

Open-Sora： 完全开源的高效复现类Sora视频生成方案

大模型Grok-1开源

#大语言模型#利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

High-Resolution Image Synthesis with Latent Diffusion Models

Stable Diffusion 是一个 text-to-image 扩散模型

Official code for the CVPR 2025 paper "SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models."

#Awesome#Awesome RSS feeds - A curated list of RSS feeds (and OPML files) used in Recommended Feeds and local news sections of Plenary - an RSS reader, article downloader and a podcast player app for android

Large, modern dataset for speech recognition

大语言模型ChatGLM-6B为基座，接入文档阅读功能进行实时问答，可上传txt/docx/pdf多种文件类型。

#计算机科学#Vector Quantized VAEs - PyTorch Implementation

Python disk-backed cache (Django-compatible). Faster than Redis and Memcached. Pure-Python.

[ICML 2024] MagicPose(also known as MagicDance): Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

Qwen 是阿里巴巴集团Qwen团队研发的大语言模型和大型多模态模型系列。

Dagger functions to import Hugging Face GGUF models into a local ollama instance and optionally push them to ollama.com.

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

CBOR codec (RFC 8949, RFC 8742) with CBOR tags, Go struct tag options (toarray, keyasint, omitempty, omitzero), float64/32/16, big.Int, and fuzz tested.

[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance