Pinokio
FeedAppsRemoteCreate
Download Pinokio
Sign inCreate accountJoin
Sign inCreate accountJoin

Apps

Announcements

View all

Official updates.

Pinned announcement from Pinokio
pinokio
@cocktailpeanut•4d ago
Pinokio Create: Turn Anything into a 1-Click Launcher, Automatically.Pinokio now talks to your AI agent to package anything into a 1-click launcher, publish to github, and list on pinokio, automatically. Just click the "Create" button at the top, select a template, enter what you want, and open in pinokio. Pinokio will hand off all the instructions needed to your own AI agent, and your agent will take it from there, taking care of everything automatically: Build a new app: Build a new app with 1-click launcher built-in, publish to github, and list to pinokio Publish your own app: Take your existing project, package it as a 1-click launcher, publish to github, and list to pinokio 1-Click Launcher for any existing project you want to try: Take any existing project you want to try out, package it as a 1-click launcher, publish to github and list on pinokio, all automatically.
Phosphene
@bizarro•15h ago
Phosphene 5.0.51: Settings in plain words, and a calm Finish setup cardSettings in plain words (free for everyone): Output format and Live preview now share a "While rendering" box with Save and Undo changes. It says "Not saved yet" until you save; everything else saves as you change it. Finish setup (free for everyone): if setup stopped, a calm card helps you finish in a few minutes and keeps your models. After "All set.", press Retry on any video that failed meanwhile. If setup stops again, it explains the connection or disk space problem and offers Try again. Both changes are in all ten languages the Studio speaks. In Pinokio, press Update, then restart. Release notes: https://phosphene.video/changelog/ https://phosphene.video/
Mumblebox 3D Asset Foundry
@mumblebox•20h ago
Foundry rigging is growing. I'd love your feedback.Quick update on the experimental rigging in Mumblebox Foundry Preview 36. Local AI auto rigging is available, along with tools for refining joints, testing movement and exporting to Blender. But the rigging system and interface are still very basic, and I'm working hard on fleshing them out. Sorry for the rough edges. I'm learning what makes a good rigging experience, and feedback from people who actually rig and animate characters is helping me see where it needs to improve. Wood Man and the acorn from the latest demo. The assets were made in Foundry, Wood Man's rig was refined through its MCP, and the animation and rendering were done in Blender. The acorn's leaf was rigged in Blender too. The interface and user experience are a big focus. I want familiar visual controls that an experienced rigger can pick up, with an approachable starting point for someone doing this for the first time. Go as deep as you want, without having every advanced setting in your face. Some of the improvements I'm planning: Clearer bones and joints, better selection feedback and a more organized workspace. More complete inverse kinematics (IK) and forward kinematics (FK) controls, including switching between them. Better hand and palm controls, with clearer ways to check how the mesh bends. Useful sliders, dials and toggles, grouped around the part you're working on, with immediate visual feedback. Matching MCP tools so your agent can inspect, adjust and help refine the rig while you stay in control. These are development goals, not features I'm claiming are all in the current release. The current experimental editor in Preview 36. This is the starting point I'm working to improve. The MCP side already gives agents tools for inspecting views, probing depth and making precise joint edits. I want the human interface to become just as useful and understandable. If you use Maya, Houdini, Blender, Daz Studio or other rigging tools, I'd really appreciate your perspective: What is the biggest frustration you wish a rigging tool would solve? Which controls or visual cues would you expect to find immediately? Have you tried Foundry's rigging, or connected it to your agent? Where did it feel confusing or fall short? I'm studying what works in those tools and where the experience can be better. Specific examples and screenshots would be especially helpful. Honest criticism is welcome. Try Foundry through Pinokio · GitHub and setup instructions Thank you for the patience, support and feedback. I want to make this a useful community tool, and hearing where it fails is part of getting it there.
EmberWriter
@grumpystrongman•2d ago
EmberWriter 0.16.0 RC1 — A Local AI Writing Studio for PinokioWriting a novel is more than generating paragraphs. It's keeping track of who knows what, what happened three chapters ago, which relationships have changed, and whether a new scene still makes sense in the larger story. I've been building EmberWriter around that challenge. It's a local-first fiction writing studio designed to help authors move from an idea to a complete manuscript while keeping creative decisions in their own hands. Version 0.16.0 RC1 is now available as a public preview through Pinokio. The writing desk is only one part of the experience. EmberWriter also includes series intelligence for tracking characters and continuity across books, a Scene Director for planning and structuring scenes, a Revision Workbench for examining proposed changes, and publishing tools for preparing exports. One principle has guided the development: AI should assist the author without silently rewriting their work or deciding what becomes canon. A suggested revision remains a suggestion. A planned scene doesn't overwrite a chapter just because a model generated something. The application includes local recovery tools, source-linked story evidence, and a Release Lab that makes technical readiness and outstanding issues visible. What's been tested? The latest engineering work includes backend and Windows recovery checks, an isolated end-to-end storyboard-to-writer test, and automated accessibility checks across desktop, tablet, and mobile layouts. RC1 is still a developer preview, not a fully certified production release. Security hardening, fresh-device installation testing, and additional real-model quality evaluation are continuing. I'd recommend starting with the isolated DEMO workspace and keeping backups of any important writing. Try EmberWriter with Pinokio: Open Pinokio on Windows x64. Choose Download from URL. Enter https://github.com/grumpystrongman/EmberWriter-Pinokio Select branch release/0.16.0-rc.1. Install and launch DEMO to explore the application. Application release: https://github.com/grumpystrongman/EmberWriter/releases/tag/preview-0.16.0-rc.1 Pinokio preview release: https://github.com/grumpystrongman/EmberWriter-Pinokio/releases/tag/preview-0.16.0-rc.1 I'd be interested in feedback from people actually writing longer fiction—particularly whether the transition from scene planning to drafting and reviewing changes feels natural. That's where I want the experience to improve most.
MiniMax H3 Studio
@mvrdvk•2d ago
Momo has a message for you!!! https://www.youtube.com/watch?v=0bFra725El4
Forge Studio
@shai7net•2d ago
Forge Studio: a whole AI creative studio on one PC with an 8 GB card, now 1-click in Pinokio 🎬 Built on Stable Diffusion WebUI Forge: • Pictures: FLUX 3 Klein, FIBO 2.0, SDXL and SD 1.5 • Video Studio: Wan 2.2 video from text, a picture, first + last frame, "ingredients", or replacing a character in a video • AnimateDiff dance transfer, Deforum with music keyframes • Simulation 360 worlds, Time Strata, Characters (consistent character sheets → video → 3D) • Forge Studio: a timeline video editor that every tab can drop its results onto • A prompt writer that takes your idea in any language • UI skins: hold any button to restyle it, save and share skins Every shot in the video was made in it, and so was the music. Launcher: https://github.com/Shai7net/forge-studio-pinokio Project: https://github.com/Shai7net/forge-studio Windows + NVIDIA (8 GB or more). First versions, experimental: feedback is very welcome!
FeaturedAnnouncedUpdatedNew
Runs on:Any
System
AnymacOSWindowsLinux
GPU
AnyNVIDIAAMDApple
Show:All projects
LaunchersPluginsAll projects
#tts64#image-generation50#video-generation42#music35#utility35#video28#próba27#3d26
lj1995/GPT-SoVITS · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co/lj1995/gpt-sovitsadded 4mo ago
0 check-insNVIDIAAMDApple
renvveyult
Swap faces in photos and videos in seconds — no training required. Powered by InsightFace and ONNX, with optional TensorRT acceleration, multi-face targeting, enhancement pipelines, and a clean one-click interface.
renvvey/renvveyult2210v3.7added 4mo ago
1 check-inNVIDIAAMDApple
silma-tts
SILMA Arabic TTS v1 Official Repo — a Lightweight Open Bilingual (Arabic & English) Text to Speech Model
silma-ai/silma-ttsadded 4mo ago
0 check-insNVIDIAAMDApple
ACE-Step-1.5-XL
The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
runware/ace-step-1.5-xladded 4mo ago
0 check-insNVIDIAAMDApple
Fish Fin Voice
Lokalny generator audiobooków i lektora AI (Wsparcie dla PL)
koloda1988-jpg/Fish_s2_pro_polishadded 4mo ago
0 check-insNVIDIAAMDApple
ComfyUI-MimicMotion
a comfyui custom node for MimicMotion
aifsh/comfyui-mimicmotionadded 4mo ago
0 check-insNVIDIAAMDApple
agendaplusv2
Contribute to virden26-sudo/agendaplusv2 development by creating an account on GitHub.
virden26-sudo/agendaplusv2added 4mo ago
0 check-insNVIDIAAMDApple
Chat Studio KH
Apple Silicon local LLM chat via MLX — OpenAI-compatible API, runs as a background service. Catalog of ~34 mlx-community quantized chat models across 14 families (Llama, Qwen, Qwen3, Mistral, Ministral, Gemma 4/3/2, Phi, Phi-4, DeepSeek, Devstral, LFM, Nemotron). Includes RAM-fit filter, search, and capability tags (starter/code/reasoning).
theng12/chatstudio-macv3.6added 4mo ago
1 check-inNVIDIAAMDApple
theDAW
Full-featured DAW, DJ, and VJ app interoperable w/Ableton, Reaper, Resolume & more. Stable Audio 3, Magenta RT2, Suno API, Chimera track fusion, Demucs stems, MIDI generate/notate, img > spectrogram > music, drawing > music, VST3 & .gan plugins, automix & key-lock, GLSL shaders, volumetric video, Quest 3 XR interface, MIDI auto-map, RAG assistant
gantasmo/thedawadded 4mo ago
@gantasmo0 check-insNVIDIAAMDApple
study-music
An "awesome music theory" kinda wiki with books, resources and courses for studying everything about music and sound
vpavlenko/study-musicadded 4mo ago
0 check-insNVIDIAAMDApple
krea-2
Official inference code for Krea 2
krea-ai/krea-2added 4mo ago
0 check-insNVIDIAAMDApple
devika
Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI. [⚠️ DEVIKA DOES NOT HAVE AN OFFICIAL WEBSITE ⚠️]
6morpheus6/devikaadded 4mo ago
@morpheus0 check-insNVIDIAAMDApple
gradio
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
cocktailpeanut/gradioadded 4mo ago
@cocktailpeanut0 check-insNVIDIAAMDApple
renvveyult
Swap faces in photos and videos in seconds — no training required. Powered by InsightFace and ONNX, with optional TensorRT acceleration, multi-face targeting, enhancement pipelines, and a clean one-click interface.
renvvey/renvveyultimatumv3.7added 4mo ago
0 check-insNVIDIAAMDApple
3d-object-generation
Contribute to NVIDIA-AI-Blueprints/3d-object-generation development by creating an account on GitHub.
nvidia-ai-blueprints/3d-object-generationadded 4mo ago
0 check-insNVIDIAAMDApple
Ideogram 4
Run Ideogram 4 locally with a simple Gradio UI
bmgames182-lab/Ideogram4v1.0added 4mo ago
0 check-insNVIDIAAMDApple
Comfy-Org/Qwen-Image-Edit_ComfyUI · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co/comfy-org/qwen-image-edit_comfyuiadded 4mo ago
0 check-insNVIDIAAMDApple
my-yt
A clean and minimal youtube frontend, without all the ads and whistles
theawaken1/my-ytadded 4mo ago
@theawakenone0 check-insNVIDIAAMDApple
SoraWatermarkCleaner
The fastest and highest-quality deep learning powered Sora2 watermark cleaner.
linkedlist771/sorawatermarkcleaneradded 4mo ago
0 check-insNVIDIAAMDApple
wepiqx/gemma-4-12B-OBLITERATED-SHQ7-GGUF · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co/wepiqx/gemma-4-12b-obliterated-shq7-ggufadded 4mo ago
0 check-insNVIDIAAMDApple
Previous
1...122123124...308
NextPage 123 of 308

Get project updates

Pulse

View all

The latest posts from across Pinokio.

This app is a masterpiece. It has everything you want. Auto detect firmware for best settings. NSFW c...
@zachman · Maestro
New on Pinokio
@agentmasonxx · Autonomous Multi-Agent Task Fleet
Automatically discovered via GitHub
New on Pinokio
@agentmasonxx · Memory Recall Memory Palace
Automatically discovered via GitHub
New on Pinokio
@agentmasonxx · Jarvis AI Assistant
Automatically discovered via GitHub
New on Pinokio
@agentmasonxx · Real Estate Auction Pipeline
Automatically discovered via GitHub

Radar

View all

Projects getting attention.

Followed·just now
MiniMax H3 ComfyUI
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.
Installable
Followed·18 min
Wan2GP
1-click WanGP Launcher. Super Optimized Gradio UI for AI video creation for GPU poor machines (6GB+ VRAM). Supports Wan 2.1/2.2, Qwen, Hunyuan Video, LTX Video and Flux. https://github.com/deepbeepmeep/Wan2GP
Installable
Followed·24 min
LTX-2.3 (Windows)
Lightricks LTX-2.3 video generation (22B distilled-1.1) with a Gradio UI. Auto-detects GPU and configures offload.
Installable
Followed·28 min
FooocusPlus
An enhanced version of Fooocus giving you access to all of the latest AI image generation models
Installable
Followed·44 min
Maestro
An all-in-one, 100% local AI creative studio, director, and multi-track editor. Generate with MiniMax H3, LTX-2.5/2.3, Wan, Flux, Qwen, and more; turn an idea or song into a planned production; then finish it on the timeline. Requires an NVIDIA GPU (6GB+ VRAM).
Installable
Pinokio
PrivacyTerms
FeedAppsCreateRemote

Explore the community

#showcase
I want to learn graphic designing
@abhimanyu123·16h ago
#cool-project
Preview of my next project!
@theawakenone·6d ago
#guide
Pinokio Create: Turn Anything into a 1-Click Launcher, Automatically.
@cocktailpeanut·4d ago
#testers-wanted
For those of you brave enough to install... Thanks for trying it out. I am adding a bug report feature and fixing the workflows for objects/creatures/vehicles. I am also adding a coding agent driven headless Blender node. I will be looking to optimizes for low memory systems soon. There is alot to do on the Roadmap. Thanks for your interest.
@mumblebox·15d ago