FastVideo

A unified inference and post-training framework for accelerated video generation.

text-extract-api

Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown

moonshine

Fast and accurate automatic speech recognition (ASR) for edge devices

GLM-4-Voice

GLM-4-Voice | 端到端中英语音对话模型

Pyramid-Flow

[ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling

entropix

Entropy Based Sampling and Parallel CoT Decoding

Hunyuan3D-1

EnglishREADME.md | 简体中文README_zh_cn.md Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation           🔥🔥🔥 News!! - Jul 26, 2025: 🤗 We release the first open-source, simulation-capable, immersive 3D world generatio

fast-graphrag

RAG that intelligently adapts to your use case, data, and queries

hallo2

Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation Jiahao Cui1*  Hui Li1*  Yao Yao3  Hao Zhu3  Hanlin Shang1  Kaihui Cheng1  Hang Zhou2  Siyu Zhu1✉️  Jingdong Wang2  1Fudan Univer

Integuru

The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.

Sana

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

lingua

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.