Store

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

This app lets you type a description and creates a picture that matches it. You can set the picture size, seed and other options to tweak the result. The generated image is shown instantly after yo...

a pinokio script launcher for Ultimate Vocal Remover 5

Contribute to JpAndreBTA/Nexus-BTA development by creating an account on GitHub.

Minimal CLI + web UI for OpenAI GPT Image 2 generation. Dual auth: API Key (paid) or OAuth via ChatGPT (free). Text-to-image, image-to-image, parallel gen, custom sizes.

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

Webchat to API (Gemini)

Official implementation of the CVPR 2026 paper "SonoWorld: From One Image to a 3D Audio-Visual Scene."

YouTube Auto-Subscriber Bot | Optimize your audience engagement workflows. A smart channel management tool designed to automate subscription interactions and handle multi-profile sync operations.

Launcher scripts for SillyTavern and ST-Extras.

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

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

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

This app lets you upload a picture that contains a SynthID watermark and returns a cleaned version without the watermark. Just provide the image, and the tool re‑creates the scene using a diffusion...

📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达

The place for AGNT

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

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

Pre-mastering & audio enhancement for AI-generated music. 12-stage processing chain with platform presets (Suno, Udio), before/after spectrogram, and broadcast-ready LUFS normalization.

Official Code of NAVA: Native Audio-Visual Alignment for Generation.