Radar

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

High-resolution 2K image editing with FireRed

Standalone Anima Lora trainer with GUI

ASCII generator (image to text, image to image, video to video)

the subtitle editor :)

AI generates natively editable PPTX from any document — real PowerPoint shapes, not images — no design skills needed

Generates a sound effect that matches video shot

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

Launcher scripts for SillyTavern and ST-Extras.

LLM Frontend for Power Users.

Official implementation of ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation (SIGGRAPH 2026).

Vietnamese TTS · 48kHz · giọng dựng sẵn + nhân bản giọng

Moderní webové studio pro tvorbu, porovnání a kalibraci audio variant.

A UI for creating and sharing interactive ML apps, built with Gradio.

API, CLI, and Web App for analyzing and finding a person's profile in 1000 social media \ websites

Fork of SpargeAttention (SparseSageAttention) for Windows wheels and easy installation

Automate TikTok view boosting with CAPTCHA bypass using Tesseract OCR.

Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ (no longer working)

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.