Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional de…

The new backend for 41ai.mooo.com

A beginner-friendly inference to finetune & run inference on open TTS models 🗣️

Krea Realtime 14B. An open-source realtime AI video model.

Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation (ICCV 2025)

Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional de…

revolutionary new technology that turns any image into obama

Custom ComfyUI nodes for film grain, color matching, and video enhancement.

Danny's Bevy exploration

Artcraft

VibeVoice: Expressive, longform conversational speech synthesis. (Community fork)

A tool to prepare datasets for training VibeVoice

ComfyUI nodes to use segment-anything-2

ComfyUI nodes for WanAnimate model input preprocessing

PyTorch implementation of Miipher-2 [2025] which is a speech restoration model by Google DeepMind

EbSynth in Python, version 2

Unofficial WIP LoRa Finetuning repository for VibeVoice

Text-audio foundation model from Boson AI

For People who want to contribute to my site

ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation

Fast and local neural text-to-speech engine

Long-form streaming TTS system for multi-speaker dialogue generation

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

https://www.mixmods.com.br/2025/08/soundize/

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.