Apps

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

High-quality video and image super-resolution powered by Real-ESRGAN. Upscale your media with advanced AI.

Open-source offline translation library written in Python

Flash Attention 2 for Windows v2.7.0-v2.7.4

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

Ultimate Vocal Remover 5 with Gradio UI. Separate an audio file into various stems, using multiple models

Generate engaging 1 to 5-minute short stories with LLMs and convert them to audio with Coqui TTS, supports voice cloning, built in speakers and multilingual.

plug whisper audio transcription to a local ollama server and ouput tts audio responses

Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.

Lets make video diffusion practical!

Contribute to xh9998/DiffVSR development by creating an account on GitHub.

Pixel art animation and drawing web app powered by React - jvalen/pixel-art-react

Decked-out gradio client for audio diffusion, mainly stable-audio-tools.

Multi-speaker separation, identification, diarization ALL-IN-ONE. It can isolate the target speaker from a conversation audio and do ASR.

[CVPR2024] StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On

In-depth repository of Telegram OSINT resources covering, tools, techniques & tradecraft.