[NVIDIA Only] Dead simple web UI for training FLUX LoRA with LOW VRAM support (From 12GB)
Global radar
New projects people are discovering or following across Pinokio.
Image Dataset Tagger for Stable Diffusion / Lora / DreamBooth Training: https://github.com/mikeknapp/candy-machine
MuScriptor is a multi-instrument music transcription model developed by Kyutai and Mirelo.
[NVIDIA ONLY] Requires 24GB VRAM (Use the lowvram option, it has the same quality). High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models. https://github.com/Tencent/Hunyuan3D-2
Cross-vendor 3D Gaussian Splatting trainer - video to splat to mesh, Vulkan or CUDA.
Local-first AI video editor with optional native MiniMax H3 generation on Apple Silicon.
moondream1 is a tiny (1.6B parameter) vision language model trained by @vikhyatk that performs on par with models twice its size. It is trained on the LLaVa training dataset, and initialized with SigLIP as the vision tower and Phi-1.5 as the text encoder. https://huggingface.co/spaces/vikhyatk/moondream1
Super fast Multilingual TTS supporting 54 voices across 8 languages.
Super fast Multilingual TTS supporting 54 voices across 8 languages.
[ICCV-2023] Official code for work "HumanMAC: Masked Motion Completion for Human Motion Prediction".
AI Voice Assistant — voice conversations, animated face, canvas, music generation, and more.
BomLens — a local-first SBOM generator & open-source risk assessor (CycloneDX). Produce an SBOM, an open-source notice, and a security/license risk report from source code, containers, binaries, firmware, or an SBOM you received. CLI or web UI, no SaaS.
Generate images with spatial accuracy https://huggingface.co/spaces/SPRIGHT-T2I/SPRIGHT-T2I
Create Spotify playlists from Setlist.fm shows using your own API keys.
Open-source AI financial research terminal with real-time market data, news intelligence, and multi-provider AI.
