Phosphene 4.16.3 - three fixes from the field
Three fixes, all from things you ran into. How to get it: press Update in Pinokio, then restart Phosphene. No...
Apps
Announcements
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...
SlashRoyale A self-hosted Clash Royale private server with a web admin panel, packaged as a one-click Pinokio...
A local-first thumbnail designer: text, effects, shapes and images over a canvas, exported to PNG/JPG.
Pinned, privacy-conscious Pinokio launcher for SUPIR photo restoration.
Fully offline document-to-speech converter using Coqui TTS models (XTTS v2, Bark, VITS, YourTTS) and StyleTTS 2. Converts EPUB, PDF, DOCX, HTML, and TXT files to audio with voice cloning support. No API keys or cloud services required.
Fully offline document-to-speech converter using OpenVoice V2. Tone color conversion and voice cloning via MeloTTS. Converts EPUB, PDF, DOCX, HTML, and TXT files to audio. No API keys or cloud services required.
Reconstruct 3D Gaussian Splatting worlds from video using non-rigid alignment. Supports fast and extensive modes with 2DGS/3DGS rendering. https://github.com/lukasHoel/video_to_world
Password-locked file browser for every drive on this machine.
A local prompt-writing assistant for Ideogram 4, MiniMax H3 video, and plain-text image models, powered by a local LLM (llama-server).
AI Song Generation with Full Style Control - Generate complete songs with lyrics, vocals, and instrumental tracks using Tencent AI Lab's SongGeneration (LeVo) model. [NVIDIA ONLY]
26 check-ins
Local LoRA trainer for MiniMax H3, Flux2 Klein 9B & Krea 2 — trains against the exact models you deploy. Desktop GUI + headless CLI. NVIDIA only (RTX 30/40/50, driver 555+).
A god roleplaying sandbox — AI characters talk to each other with automated conversations, character development, and god interference. Works with any OpenAI-compatible local LLM (e.g. LM Studio).
Describe an image, get a 100% schema-valid Ideogram 4 JSON prompt — generated fully locally with an embedded llama.cpp (no Ollama or LM Studio required).
WebUI for ML-Sharp (3DGS)Featured
One-click 3D Gaussian Splatting generation from a single image.
@franzipol
5 check-ins
An all-in-one, 100% local AI video, image & music studio. Its Director mode turns a single prompt into a full music video or short film — LLM-planned, shot by shot. Built on the WanGP pipeline (Wan 2.1/2.2, LTX-2.3, Qwen, Hunyuan Video, Flux). Requires an NVIDIA GPU (6GB+ VRAM).
Password-locked file browser for every drive on this machine.
Hunyuan3D-2-LowVRAMFeatured
Text/Image to 3D (Cross Platform: Mac + Windows + Linux): High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models. https://github.com/deepbeepmeep/Hunyuan3D-2GP
11 check-ins
A diep.io private-server with a web control panel for editing settings and managing the game server
Gradio UI for the official LTX-2 video model trainer — LoRA, audio-video, IC-LoRA, and full fine-tuning.
Browse ComfyUI workflow templates and manage missing model files in the folders exposed by a running local ComfyUI server.
@cocktailpeanut1 check-in
flux-webuiFeatured
Minimal Flux Web UI powered by Gradio & Diffusers (Flux Schnell + Flux Merged)
16 check-ins