Store

[CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation

F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching https://huggingface.co/spaces/mrfakename/E2-F5-TTS

OneTrainer para Pinokio vato loco

Kimi K2 is the large language model series developed by Moonshot AI team

Forget everything you thought you knew about AI art generation - RuinedFooocus is here to completely reinvent the game!

NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B

Fast and High-Quality Zero-Shot voice clone Text-to-Speech with Flow Matching

Fast and High-Quality Zero-Shot voice clone Text-to-Speech with Flow Matching Multilingual

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale (CVPR 2025)

Powerful & Easy-to-Use Video Face Swapping and Editing Software

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

[WINDOWS/LINUX ONLY] Easily train a good VC model with voice data <= 10 mins!: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI

Utility for extracting prompt metadata from Civitai AI images, auto-downloading the associated resources, and outputting/formatting the prompt information.

Transcribe and summarize video content using AI. Open-source, multi-platform, and supports multiple languages.

Prompt, run, edit, and deploy full-stack web applications using any LLM you want!

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

Open-source offline translation library written in Python

This Gradio application demonstrates the capabilities of the "dots.ocr" model, a powerful multilingual document parser.