New projects people are discovering or following across Pinokio.
[Runs fast on NVIDIA GPUs. Works on M1/M2/M3 Macs but slow] VideoCrafter is an open-source video generation and editing toolbox for crafting video content. It currently includes the Text2Video and Image2Video models https://github.com/AILab-CVC/VideoCrafter
a state-of-the-art open-source model for fast feedforward 3D reconstruction from a single image, developed in collaboration between Tripo AI and Stability AI. https://huggingface.co/spaces/stabilityai/TripoSR
enhance the resolution and spatiotemporal continuity of text-generated videos and image-generated videos
LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation https://huggingface.co/spaces/ashawkey/LGM
Pre-mastering & audio enhancement for AI-generated music. 12-stage processing chain with platform presets (Suno, Udio), before/after spectrogram, and broadcast-ready LUFS normalization.
Super fast Multilingual TTS supporting 54 voices across 8 languages.
X-Voice is a multilingual text-to-speech system that enables one speaker to speak 27 languages.
Local generative video, image, and character training on Apple Silicon. Train face + voice LoRAs in-app. Q8 HQ for character clips. MLX native — no cloud, no API key.
Turn an RGB video into a frame-aligned alpha matte
deep hermes, but without the need for a system prompt. Autonomously responds based on its OWN judgment https://github.com/cocktailpeanut/deeperhermes
Phased Consistency Model - generate high quality images with 2 steps https://huggingface.co/spaces/radames/Phased-Consistency-Model-PCM
Complete pipeline for generating whiteboard-style animated videos from a script.
A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.
An intuitive GUI for GLIGEN that uses ComfyUI in the backend https://github.com/mut-ex/gligen-gui
Improving Diffusion Models for Authentic Virtual Try-on in the Wild https://huggingface.co/spaces/yisol/IDM-VTON
Autonomous 16x16 Chess-Grid research agent (KoboldCPP + Qwen GGUF). Walks a grid of Markdown knowledge cells, synthesizes short papers, scores novelty, updates a persistent soul.md.
A multi-voice AI audiobook generator built on Qwen3-TTS — annotate scripts with an LLM, assign unique voices to each character, per-line style instructions for delivery, clone voices from reference audio, design new voices from text descriptions, train custom voices with LoRA fine-tuning, and export to MP3 or Audacity multi-track projects
Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
