Store

https://github.com/PierrunoYT/PersonaPlex-Pinokiov5.0updated 1/28/2026, 4:00:16 PMindexed 1/28/2026, 4:01:11 PM

🗣️ PersonaPlex - NVIDIA's real-time speech-to-speech conversational AI model. Natural full-duplex conversations with customizable personas and voices. Requires powerful NVIDIA GPU (16-24GB VRAM), 32GB RAM, and Hugging Face account.

pinokio

https://github.com/pinokiocomputer/pinokioupdated 1/28/2026, 3:58:31 PMindexed 1/28/2026, 3:59:12 PM

AI Browser

#pinokio

FunAudioLLM/Fun-CosyVoice3-0.5B-2512 · Hugging Face

https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512indexed 1/28/2026, 3:08:26 PM

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

ComfyUI

https://github.com/comfyanonymous/ComfyUIupdated 1/28/2026, 2:28:51 PMindexed 1/28/2026, 3:22:57 PM

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Skywork/SkyReels-V2-DF-14B-720P · Hugging Face

https://huggingface.co/Skywork/SkyReels-V2-DF-14B-720Pindexed 1/28/2026, 11:37:49 AM

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

TRELLIS.2

https://github.com/Deathdadev/TRELLIS.2-Pinokiov5.0updated 1/28/2026, 11:24:23 AMindexed 1/28/2026, 11:25:11 AM

One-click installer for Microsoft TRELLIS.2: High-quality 3D asset generation from images with PBR textures.

#3d

F5-TTS

https://github.com/SWivid/F5-TTSupdated 1/28/2026, 11:16:04 AMindexed 1/28/2026, 2:27:38 PM

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

InstantMesh

https://github.com/TencentARC/InstantMeshupdated 1/28/2026, 9:47:06 AMindexed 1/28/2026, 9:56:00 AM

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

Moltbot (F.K.A. ClawdBot)

https://github.com/cocktailpeanut/clawdbot.pinokiov5.0updated 1/28/2026, 9:37:50 AMindexed 1/28/2026, 9:38:12 AM

The AI that actually does things https://www.molt.bot

#agent #ai

Z-Image

https://github.com/Tongyi-MAI/Z-Imageupdated 1/28/2026, 5:45:42 AMindexed 1/28/2026, 12:41:13 PM

Contribute to Tongyi-MAI/Z-Image development by creating an account on GitHub.

mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit · Hugging Face

https://huggingface.co/mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bitindexed 1/28/2026, 5:29:35 AM

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Z-Fusion

https://github.com/ai-anchorite/Z-Fusionv3.7updated 1/28/2026, 4:51:33 AMindexed 1/28/2026, 4:52:10 AM

Z-Image, Flux2 Klein, & SeedVR2 with a Gradio UI. Uses a built-in ComfyUI backend for speed and efficiency! [8GB+VRAM, 16GB+ RAM]

FlashVSR-Pro

https://github.com/LujiaJin/FlashVSR-Proupdated 1/28/2026, 4:28:17 AMindexed 1/28/2026, 5:09:27 AM

Contribute to LujiaJin/FlashVSR-Pro development by creating an account on GitHub.

ComfyUI

https://github.com/Comfy-Org/ComfyUIupdated 1/28/2026, 4:10:22 AMindexed 1/28/2026, 4:30:50 AM

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

huihui-ai/Qwen3-32B-abliterated · Hugging Face

https://huggingface.co/huihui-ai/Qwen3-32B-abliteratedindexed 1/28/2026, 2:46:46 AM

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

QTinker

https://github.com/manat0912/QTinkerv1.0.0updated 1/28/2026, 12:47:24 AMindexed 1/28/2026, 12:48:19 AM

Distill and quantize models using TorchAO with intelligent GPU/CPU management

TTS-Story

https://github.com/Xerophayze/TTS-Storyv2.0updated 1/27/2026, 9:35:55 PMindexed 1/27/2026, 9:36:33 PM

Multi-Voice Text-to-Speech for Stories and Audiobooks. Supports Kokoro and Chatterbox TTS engines with GPU acceleration.

SongGeneration Studio

https://github.com/BazedFrog/SongGeneration-Studiov3.7updated 1/27/2026, 8:47:53 PMindexed 1/27/2026, 9:46:50 PM

AI Song Generation with Full Style Control - Generate complete songs with lyrics, vocals, and instrumental tracks using Tencent AI Lab's SongGeneration (LeVo) model. [NVIDIA ONLY]

#song #ai #music

jordand/echo-tts-base · Hugging Face

https://huggingface.co/jordand/echo-tts-baseindexed 1/27/2026, 7:23:17 PM

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Echo-TTS Preview - a Hugging Face Space by jordand

https://huggingface.co/spaces/jordand/echo-tts-previewindexed 1/27/2026, 7:16:14 PM

Fast, multi-speaker TTS (44.1kHz) with voice cloning