Pinokio

Announcements

Phosphene

@bizarro18h ago

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...

Vibe Player

@saffmila1d ago

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 · Creation Lab

@theinaog1d ago

HocusPocus – Major Update

HocusPocus – Major Update HocusPocus is a local studio for turning an idea into a full production: story, ima...

YUE2 // GROOVE

@bearbone2d ago

YUE2 // GROOVE 1.0.8 released ! — Cover works again on new installs, and the Library player takes a colour

A fix for Cover and a small visual touch for the Library player. Updating once gets you both. Thanks to @pdxc...

Slash Royale

@avoidr3d ago

Slash Royale: Self-hosted clash royale private server

SlashRoyale A self-hosted Clash Royale private server with a web admin panel, packaged as a one-click Pinokio...

Type:api

Platform:All

GPU:All

Recommended Latest Check-ins

Sort:Latest

KDTalker

SUP3RMASS1VE/KD-Talkerv3.6updated 1y ago

Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait

@sup3rmass1ve0 check-insNVIDIAAMDApple

InstructIR

tjoen/instructir.pinokioupdated 1y ago

[Nvidia GPU only] High-Quality Image Restoration Following Human Instructions

1 check-inNVIDIAAMDApple

StreamDiffusion

cocktailpeanutlabs/streamdiffusionv3.0updated 1y ago

[NVIDIA ONLY] A Pipeline-Level Solution for Real-Time Interactive Generation https://github.com/cumulo-autumn/StreamDiffusion

0 check-insNVIDIAAMDApple

LatentSync

Deepfake-Zatylkin/LatentSync-Pinokiov3.2updated 1y ago

0 check-insNVIDIAAMDApple

vid2pose

cocktailpeanutlabs/vid2posev1updated 1y ago

Video to Openpose & DWPose (All OS supported) https://github.com/sdbds/vid2pose

#ai #utility

0 check-insNVIDIAAMDApple

CocktailPeanut

cocktailpeanutlabs/CocktailPeanutv3.6updated 1y ago

test

0 check-insNVIDIAAMDApple

MagicAnimate

cocktailpeanut/MagicAnimate.pinokiov3.0updated 1y ago

[NVIDIA ONLY] Temporally Consistent Human Image Animation using Diffusion Model https://showlab.github.io/magicanimate/

@cocktailpeanut0 check-insNVIDIAAMDApple

AllTalk-TTS v2

pinokiofactory/AllTalk-TTSv3.3updated 1y ago

[NVIDIA ONLY] AllTalk-TTS is a unified UI for E5-TTS, XTTS, Vite TTS, Piper TTS, Parler TTS and RVC, based on CoquiTTS, including a finetune mode.

2 check-insNVIDIAAMDApple

VersatileAudioSuperResolution

masonjames/VASR-for-Pinokiov1.5updated 1y ago

0 check-insNVIDIAAMDApple

browser-use

Ripkore/browser-usev3.6updated 1y ago

Run AI Agent in your browser. https://github.com/browser-use/web-ui

@ripkore0 check-insNVIDIAAMDApple

Deeper Hermes

ARTBYKILEM/deeperhermesv3.6updated 1y ago

deep hermes, but without the need for a system prompt. Autonomously responds based on its OWN judgment https://github.com/cocktailpeanut/deeperhermes

0 check-insNVIDIAAMDApple

macOS-use

pinokiofactory/macOS-usev3.6updated 1y ago

[Mac Only] We make AI agents that control Mac apps: https://github.com/browser-use/macOS-use

#agent #ai

0 check-insNVIDIAAMDApple

moondream2

cocktailpeanutlabs/moondream2v3.0updated 1y ago

a tiny vision language model that kicks ass and runs anywhere https://github.com/vikhyat/moondream

#ai #vlm

0 check-insNVIDIAAMDApple

AudioSep

cocktailpeanut/AudioSep.pinokiov2.0updated 1y ago

Separate Anything You Describe (https://huggingface.co/spaces/Audio-AGI/AudioSep)

#ai #audio #audio-edit

@cocktailpeanut

2 check-insNVIDIAAMDApple

Video2Openpose

cocktailpeanutlabs/vid2openposev3.0updated 1y ago

Turn any video into Openpose video https://huggingface.co/spaces/fffiloni/video2openpose2

#ai #utility

0 check-insNVIDIAAMDApple

Video2Openpose

cocktailpeanut/vid2openpose.pinokiov3.0updated 1y ago

Turn any video into Openpose video https://huggingface.co/spaces/fffiloni/video2openpose2

@cocktailpeanut0 check-insNVIDIAAMDApple

Bark Voice Cloning

cocktailpeanutlabs/barkv1.1updated 1y ago

Upload a clean 20 seconds WAV file of the vocal persona you want to mimic, type your text-to-speech prompt and hit submit! A local version of https://huggingface.co/spaces/fffiloni/instant-TTS-Bark-cloning

#ai #voice #voice-clone

7 check-insNVIDIAAMDApple

[NVIDIA GPU ONLY] LGM

cocktailpeanutlabs/lgmv3.0updated 1y ago

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation https://huggingface.co/spaces/ashawkey/LGM

#3dgen #ai #3d

0 check-insNVIDIAAMDApple

DiffBIR

bycloud-AI/DiffBIR-Windowsupdated 1y ago

DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

0 check-insNVIDIAAMDApple

dust3r

cocktailpeanutlabs/dust3rv1.3updated 1y ago

Geometric 3D Vision Made Easy https://dust3r.europe.naverlabs.com/

#3dgen #ai

0 check-insNVIDIAAMDApple

RadarFeed

Global feed

Latest posts from the community.

Install seems to be failing for mac at moment - conda requirement won't install from miniforge.

@mpd · Phosphene

Checked in to God's Eye View.

@adalangh · Community

Checked in to God's Eye View.

@runner01 · Community

Checked in to God's Eye View.

@dave_44_95 · Community

Having trouble with Apps on Pinokio Like Wen2 Crator shows worning that this info showing could be a ...

@prince_dargon7 · Community

Global radar

Projects people are discovering or following now.

Followedjust now

God's Eye View

A live 3D intelligence console for planet Earth.

Followed1 min

YUE2 // GROOVE

YUE2 // GROOVE is the latest music studio built on the open-source Yue2 model and its inference stack. Generate high-quality full songs from style and lyrics with an editable score plan — powered by the latest YuE model — cover from audio with SheetSage2 and MERT2, refine and compare edits, and keep your works in a reusable, easy-to-manage library. You get high-quality creation with real creative control. Hardware: an NVIDIA GPU with 24 GB VRAM on Linux (YuE2's recommended setup, validated end-to-end on NVIDIA L4 hosts; a 16 GB memory budget runs everything the app can produce, and 12 GB runs the unquantized model at CFG 1.0 or for shorter songs) or an Apple Silicon Mac with 32 GB+ unified memory (where this app is developed and tested). Windows is best effort: install, launch, Cover and a full-length song verified on Windows 11 (RTX 2070, 8 GB); song generation there runs through the GGUF engine. Cards under 16 GB (and Windows) get the optional GGUF engine: the same model through yue2.cpp with an 8-bit backbone, 8.2 GB peak for a full song, measured indistinguishable from the reference rendering in a blind ABX, a different take for the same seed; the reference PyTorch configuration stays the default wherever it fits.

Followed3 min

Uncensored Local Studio

Run image generation, GGUF language models, Whisper speech recognition, and Kokoro speech synthesis locally from one offline studio.

Followed8 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).

Followed9 min

MagicQuill

An intelligent, interactive Image Editing System. Easily erase and add objects on a user-friendly interface.