Unlimited OCR – Searchable PDF: Local OCR with Live Markdown & PDF Output
I’ve released Unlimited OCR – Searchable PDF , a local Pinokio app built around Baidu Unlimited-OCR for OCR'i...
Launcher updates
Phosphene 4.5.0 - updates now actually finish
Several releases have landed since I last posted here, and one of them explains something a few of you have r...
roop-unleashed-wip — an actively developed fork with 3D pose matching, advanced masking, and expression warping
roop-unleashed-wip: more control over the swap, not just a swap button roop-unleashed-wip is my ongoing fork ...
Maestro v1.8.5 with MiniMax-Music3 & other fixes and improvements!
Haha! This is crazy. Maestro v1.8.5 w/ MiniMax-Music3 just dropped. As a test, I prompted "Wheels on the Bus ...
Have you ever felt bored and wanted to watch two AI characters talk to each other, but were too lazy to prope...
Store
#ai187#tts56#image-generation44#video-generation38#utility34#133#video25#agent24#faceswap22#3d21#music21#audio19#image-edit18#audio-generation15#ui15#3dgen14#voice14#llm13#voice-clone13#image12#agents11#ses-klonlama11#song-generation11#training11#generation10#music-generation10#n8n10#pinokio10#song10#automation9
MaestroFeatured
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).
@blizaine
119 check-ins
Multi-voice text-to-speech for stories and audiobooks, with local and cloud TTS engines plus optional LLM text processing.
@xerophayze
5 check-ins
Stealth headless browser for AI agents - bypass Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwright replacement.
Manage Hermes CLI skins in a web UI, edit live YAML fields, and save or activate skins with built-in previews.
Chinese sentence-based video clipping with FunASR
[AMD ONLY] All-in-one local AI video, image & music studio built on the WanGP pipeline (Wan 2.1/2.2, LTX-2.3, Qwen, Hunyuan Video, Flux). ROCm-powered. Supported on Windows and Linux for RDNA 2-4 dGPUs (RX 6000/7000/8000/9000) and gfx1150-53 APUs (Strix Point/Halo, Krackan Point/Halo). 6 GB+ VRAM recommended. For NVIDIA GPUs use the upstream Maestro app. Credits: the app itself is Maestro by Blizaine (github.com/Blizaine/Maestro) — this is just an AMD installer wrapper around it. The clone-at-install-time approach used to port it to AMD was pioneered by 6Morpheus6's wan2gp-amd (github.com/6Morpheus6/wan2gp-amd).
Password-locked file browser for every drive on this machine.
Local Baidu Unlimited-OCR with live rendered Markdown and optional Searchable Scan or Reconstructed PDF output.
CapCap is a Windows desktop app for short-form video localization and dubbing. It brings transcription, translation, subtitle styling, voice generation, timeline editing, preview, and export into a single project workflow for Vietnamese-focused content production.
MiniMax H3 ComfyUIFeatured
MiniMax H3 omni-modal video generation in ComfyUI. Text/image/video/audio in, video with native 32kHz stereo audio out (768p default, 1080p+ supported). Disk-optimized: pruned INT8 + NVFP4 weights (~63GB instead of ~290GB). NVIDIA only.
@thomas_eric
10 check-ins
AI-powered model downloader, workflow bridge, timeline video editor, and manager for ComfyUI.
Control plane for the KH Studio family — generation queues, episode render workers, health, models, and machine-level scheduling.
Suno at home. Local AI music generation studio — full songs with vocals, lyrics, covers, and music videos. Built on ACE-Step 1.5 XL.
@nerual_dreming5 check-ins
Higgs Audio v3 TTS + AI text director, voice cloning, podcast & audiobook (multi-speaker). 100+ languages, offline, NVIDIA GPU.
@nerual_dreming4 check-ins
ElevenLabs at home. Multilingual TTS with Voice Design, Voice Cloning, and end-to-end LoRA fine-tuning straight from a video or podcast. Built on VoxCPM2 by OpenBMB. 30 languages incl. Russian.
@nerual_dreming3 check-ins
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
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).
