Global radar

New projects people are discovering or following across Pinokio.
Followed3h ago
LivePortrait
github.com/Lytanshade

LivePortrait - img2vid only: 6GB VRAM & ~8GB download

Followed3h ago
SillyTavern
github.com/drago87

a local-install interface that allows you to interact with text generation AIs (LLMs) to chat and roleplay with custom characters. https://docs.sillytavern.app/

Followed3h ago
audiocraft_plus
github.com/pinokiofactory

AudioCraft Plus is an all-in-one WebUI for the original AudioCraft, adding many quality features on top https://github.com/GrandaddyShmax/audiocraft_plus

Followed3h ago
LightOnOCR-2-1B
github.com/TheAwaken1

State-of-the-art 1B OCR model (83.2% on OlmOCR-Bench). Local version of the HuggingFace demo. Created by Claude Code, orchestrated by TheAwakenOne.

Followed3h ago
Image to Prompt
github.com/cocktailpeanut

Generate editable Ideogram JSON prompts from uploaded images.

Followed3h ago
MFLUX-WEBUI
github.com/pinokiofactory

[MAC ONLY] A powerful and user-friendly web interface for FLUX, powered by MLX and Gradio via MFLUX

Followed3h ago
roop-unleashed
github.com/SUP3RMASS1VE

Uncensored Deepfakes for images and videos without training and an easy-to-use GUI.

Followed3h ago
LivePortrait
github.com/pinokiofactory

Bring portraits to life! https://github.com/KwaiVGI/LivePortrait

Followed4h ago
Direct3D-S2
github.com/Deathdadev

[NVIDIA ONLY] Direct3D-S2 is a scalable 3D shape generation framework leveraging sparse volumetric representations for high-resolution outputs. It features Spatial Sparse Attention (SSA), a novel mechanism that accelerates Diffusion Transformer computations on sparse data, achieving up to 9.6× speedup in training. The unified Sparse VAE architecture maintains a consistent sparse volumetric format across input, latent, and output stages, significantly improving efficiency and stability.

Followed4h ago
TRELLIS
github.com/V-Sekai-fire

A pinokio script for https://github.com/microsoft/TRELLIS

Followed4h ago
flux-webui
github.com/pinokiofactory

Minimal Flux Web UI powered by Gradio & Diffusers (Flux Schnell + Flux Merged)

Followed4h ago
Fooocus2026
github.com/mikecastrodemaria

A personal fork of lllyasviel/Fooocus v2.5.5 with quality-of-life features: Save Preset, CivitAI Model Settings, LoRA trigger words, Embeddings panel, Wildcards editor, Vary-with-aspect-ratio, Custom Resolution, Asset Browser, Restart UI button.

Followed4h ago
StableAudio
github.com/pinokiofactory

An Open Source Model for Audio Samples and Sound Design https://github.com/Stability-AI/stable-audio-tools

Followed4h ago
StoryDiffusion Comics
github.com/cocktailpeanutlabs

create a story by generating consistent images https://github.com/HVision-NKU/StoryDiffusion

Followed4h ago
Hermes + WebUI
github.com/neviah

Hermes Agent with modern WebUI (nesquena/hermes-webui). Persistent memory, multi-provider AI (OpenAI, Anthropic, Gemini, DeepSeek, OpenRouter), scheduled cron jobs, skills, and sessions. Three-panel interface with chat, tasks, memory, and workspace browser. https://github.com/nesquena/hermes-webui

Followed4h ago
ditto
github.com/pinokiofactory

the simplest self-building coding agent https://github.com/yoheinakajima/ditto

Followed4h ago
AudioGradio
github.com/cocktailpeanut

One click installer for AudioCraft MusicGen and AudioGen Gradio UI (Requires at least Pinokio v0.0.56)

Followed4h ago
Hermes Agent
github.com/cocktailpeanut

Self-improving CLI agent by Nous Research with local memory, skills, and messaging workflows.

Followed5h ago
Florence2
github.com/pinokiofactory

An advanced vision foundation model from MicroSoft https://huggingface.co/spaces/gokaygokay/Florence-2

Followed5h ago
n8n
github.com/SUP3RMASS1VE

Secure Workflow Automation for Technical Teams