Store

MIDIfren is an Audio Stem & MIDI Processor in Python🎵. Convert audio to MIDI, extract stems, sonify MIDI files ...

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

Contribute to bmaltais/kohya_ss development by creating an account on GitHub.

Contribute to presenton/presenton_docker development by creating an account on GitHub.

Contribute to presenton/presenton_electron development by creating an account on GitHub.

[NVIDIA Only] Dead simple web UI for training FLUX LoRA with LOW VRAM support (From 12GB)

Full-stack AI video generation app with image/text input and premium NSFW toggle

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs

ICCV‑23 video in‑/out‑painting

Creates short videos for TikTok, Instagram Reels, and YouTube Shorts using the Model Context Protocol (MCP) and a REST API.

Contribute to mannaandpoem/OpenManus development by creating an account on GitHub.

Image inpainting tool powered by SOTA AI models. Remove any unwanted object, defect, or even people from your pictures, and replace (powered by stable diffusion) anything in your pictures. https://www.iopaint.com/

Public repository of the slides2video app for pinokio

Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"

Text-to-Speech using IndicF5 for Indian languages

A GUI for music separation AI demucs

🎵 Kokoro TTS Chinese Version - High-quality Chinese text-to-speech system with 103 voice models, web interface, and command-line tools

[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.

GLM-4-Voice | 端到端中英语音对话模型