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
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Pure MLX MiniMax-H3 text-to-video-and-audio inference for Apple Silicon.
Browse, preview and compare Wan2GP / WanGP video generations side by side, with the embedded generation settings and a diff of what changed between runs.
Python wrapper for ByteDance's Seedance 2.5 API — Text-to-Video, Image-to-Video, realistic human faces, native 4K, consistent character generation.
Demo of the Collection of Qwen Image Edit LoRAs
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Apple Silicon music generation — MusicGen, Stable Audio Open, Bark.
Free unlimited AI text-to-speech - turn text files into Korean books (PDF + audiobook)
The Open-Source Elevenlabs alternative AI Voice Clone, Dub, Dictate, Transcribe, Audiobook creator and Voice workflow studio.
OdysseusFeatured
Self-hosted AI workspace for local-first chat, agents, tools, memory, research, documents, email, and model endpoint management.
@cocktailpeanut
9 check-ins
Contribute to Wan-Video/Wan-Animate-2 development by creating an account on GitHub.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Any book, performed by a full cast — effortlessly.
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).
The agent IDE that builds itself
Contribute to Larryvrh/ComfyUI-MiniMax-H3-Turbo development by creating an account on GitHub.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Open source agent built on local models, with its own inference engine. 100% private and offline