Store

A GUI for masking/rotoscoping video using AI models

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

A SillyTavern extension that creates character with LLMs.

Simple and easy to use DDNS. Support Aliyun, Tencent Cloud, Dnspod, Cloudflare, Callback, Huawei Cloud, Baidu Cloud, Porkbun, GoDaddy, Namecheap, NameSilo...

Forked from Wan2GP, a fast AI Video Generator, for the Apple Silicon.

Contribute to SUP3RMASS1VE/RoopUnleashed development by creating an account on GitHub.

Speech-to-text with NVIDIA Canary in Rust

Video inpainting (object removal / video completion) - sczhou/ProPainter

Official inference repo for FLUX.2 models

An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism

将视频瞬间转化为手绘故事 Turn Video Moments into Hand-Drawn Stories

The official code of Yume

MoCha: End-to-End Video Character Replacement without Structural Guidance

A single Gradio + React WebUI with extensions for ACE-Step, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, AudioGen, MusicGen, Tortoise, RVC, Vocos, Demucs, SeamlessM4T, and Bark!

A single Gradio + React WebUI with extensions for ACE-Step, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, AudioGen, ...

Contribute to kijai/ComfyUI-FramePackWrapper development by creating an account on GitHub.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

AuraSR-v2 - An open reproduction of the GigaGAN Upscaler from fal.ai https://huggingface.co/spaces/gokaygokay/AuraSR-v2