Global radar

Caption private data with uncensored models

Image-to-3D generation with Microsoft TRELLIS.2, running natively on Apple Silicon via PyTorch MPS. Gradio GUI with a 3D viewer, Metal-accelerated PBR texture baking, and GLB/OBJ export. No NVIDIA GPU required. Requires macOS on Apple Silicon (M1 or later), 24GB+ unified memory recommended. https://github.com/SUP3RMASS1VE/trellis-mac-GUI

[Mac Onlyl] An all-in-one LLMs Chat UI for Apple Silicon Mac using MLX Framework. https://github.com/qnguyen3/chat-with-mlx

High-quality image generation and editing powered by SenseNova-U1-8B-MoT (NEO-Unify architecture). Supports text-to-image, image-to-image editing, and reasoning mode.

[v0.5.1] FramePack Video App offering multiple generation types: Original, F1, video extension, end frame. Features include: LoRA support, job queueing, advanced timestamped prompts, offline mode, a post-processing suite including upscaling, interpolation, filters and more!

Identify and download missing models for ComfyUI workflows automatically.

Nodes related to video workflows

Stable Diffusion WebUI Forge is a platform on top of Stable Diffusion WebUI (based on Gradio) to make development easier, optimize resource management, and speed up inference. https://github.com/lllyasviel/stable-diffusion-webui-forge?tab=readme-ov-file

Build your own voice for StyleTTS2

Official inference code for SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis

Create songs, albums and artwork locally on Apple MLX with ACE-Step v1.5, MFLUX, local agents and LoRA training.

Unify Efficient Fine-Tuning of 100+ LLMs https://github.com/hiyouga/LLaMA-Factory

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

Microsoft's 7B parameter computer use agent with Gradio interface

wan2.2 fast video generation with high-res stop frames

PiD-Image-Upscaler is an experimental, advanced super-resolution and image-to-image refinement application based on the state-of-the-art PiD (Pixel Diffusion Decoder) framework by NVIDIA. This application couples local generative text-to-image and image-to-image pipelines.

PiD-Image-Upscaler is an experimental, advanced super-resolution and image-to-image refinement application based on the state-of-the-art PiD (Pixel Diffusion Decoder) framework by NVIDIA. This application couples local generative text-to-image and image-to-image pipelines.

a research paper for generative cartoon interpolation: https://github.com/ToonCrafter/ToonCrafter

Next generation face swapper and enhancer

A local-first, AI-powered dating and world simulator game that runs in your browser.