Phosphene 4.17 - honest times, faces that survive, and films you can fix
Update: press Update in Pinokio, then restart Phosphene. Nothing new to download. We used every flow in Phosp...
Apps
Announcements
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...
HocusPocus – Major Update
HocusPocus – Major Update HocusPocus is a local studio for turning an idea into a full production: story, ima...
A fix for Cover and a small visual touch for the Library player. Updating once gets you both. Thanks to @pdxc...
InstantIDFeatured
state-of-the-art tuning-free method to achieve ID-Preserving generation with only single image, supporting various downstream tasks. https://instantid.github.io/
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Ultron.
Windows / Linux desktop app built with Rust/Tauri for local Higgs Audio v3 TTS inference + local dev api through a native C++/CUDA port
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Qwen3-aligner is an all-in-one audio processing tool powered by **Qwen3-ASR** and **Qwen3-ForcedAligner** from Alibaba's Tongyi Qianwen series. It supports single-file transcription & alignment, batch processing, SRT timestamp repair, and comes with a **bilingual (Chinese/English) Gradio UI**. No limit on audio duration.
Run PrismML Bonsai and Ternary-Bonsai language models locally on macOS, Linux, and Windows with llama.cpp.
@godwish
3 check-ins
Real-time government spending transparency on Solana | Civic tech for democratic accountability | Indonesia open governance
[NVIDIA ONLY] Qwen-Image-Edit-2511 with 19 lazy-loaded LoRAs for single & multi-image editing (anime, pose transfer, relighting, upscaling, style transfer, and more). 4-step fast inference. https://github.com/PRITHIVSAKTHIUR/Qwen-Image-Edit-2511-LoRAs-Fast-Lazy-Load
Contribute to jihadnasrallah1234-sudo/jarvis-voice-assistant development by creating an account on GitHub.
အသံတွေကို Clone လုပ်နိုင်တဲ့ "သာလိကာ Voice Clone" App ပါ။ သတိထားရမှာက ကိုယ်အသံ cone လုပ်မယ့်သူက ကိုယ့်အသံသာဖြစ်ရမယ်။ အကယ်၍ တခြားတစ်ယောက်ရဲ့ အသံဖြစ်မယ်ဆိုရင် မူရင်းအသံပိုင်ရှင်ဆီမှာ ခွင့်ပြုချက် သွားတောင်ပါ။ အသုံးပြုသူသည် တခြားသူအသံကို ယူသုံးပြီး ပြဿနာတစုံတရာဖြစ်ပါက အပြည့်အဝ 100% ယူရမည်။
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Bonsai Demo
开源 AI 视频本地化工具：自动完成 YouTube/Bilibili 视频下载、字幕识别与翻译、语音克隆配音、音轨混合和字幕压制。
Professional text-to-speech with voice cloning — powered by Kyutai Pocket TTS
Wasserman's Filmmaker Suite — Blockout, Motion Previs Studio, Stem Studio, and the Unofficial DaVinci MCP: AI-native filmmaking from first blocking to final mix.
Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 20 other agents.
ApplioFeatured
A simple, high-quality voice conversion tool focused on ease of use and performance.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.