A little while ago I posted about Orange , a frontend I built for turning ComfyUI workflows into simple tools...
Apps
Announcements
Phosphene 4.17 - honest times, faces that survive, and films you can fix
"Hi. I'm Bizarro. My Mac said three minutes." ... "That was Tuesday." We've all been in that support group. 4...
Panel v0.2.0 has been released, you should update to the latest version within the pinokio launcher, as a bun...
Update: RIFE Video Frame Interpolation (2x/4x FPS Boost) — Runs Smoothly Even on 4GB VRAM
Hey Pinokio community, We just integrated RIFE AI frame interpolation (rife-ncnn-vulkan) directly into Vibe P...
Upload a silent video and provide a brief caption or a detailed chain‑of‑thought description. The system creates matching sound effects and merges them with the original video, returning a new vide...
Generate any application by Vibe Coding it
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.
Enter the lyrics (and optionally a melody) you want to hear sung, and the app will create an audio clip of a synthetic singer using the SoulX‑Singer model. It automatically downloads any needed mod...
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.
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.
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
VITS-based Voice Conversion focused on simplicity, quality and performance
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.
Use LLM for deep research
VibeSurf - AI-powered browser assistant for surfing the web with intelligence
Generative models for conditional audio generation
Image-to-3D Generation
基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版
基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版
A multi-voice AI audiobook generator built on Qwen3-TTS — annotate scripts with an LLM, assign unique voices to each character, per-line style instructions for delivery, clone voices from reference audio, design new voices from text descriptions, train custom voices with LoRA fine-tuning, and export to MP3 or Audacity multi-track projects