Wanted

Generative models for conditional audio generation

FunGen can be augmented with a Device Controller and a Streamer to connect to XBVR, Stash, local files. See the discord and ko-fi links for more :)

Lightpanda: the headless browser designed for AI and automation

Portable AI agent desktop for Windows — 100 tools, GUI, local models via LM Studio, TTS, Music, ComfyUI, workflows, tool maker. No install. No Docker. No admin rights.

Wan2.2-Lightning: Speed up wan2.2 model with distillation

A framework for efficient model inference with omni-modality models

One-command fine-tuning for Qwen3-TTS text-to-speech model with custom voice samples

Official implementations for paper: Zero-shot Image Editing with Reference Imitation

Contribute to visomaster/visomaster-assets development by creating an account on GitHub.

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

Contribute to mpalatsi/open-webui-discord-bot development by creating an account on GitHub.

[ICLR 2026] UniVideo: Unified Understanding, Generation, and Editing for Videos

Open-source CLI for unrestricted AI - Access powerful models without censorship

A collaboration friendly studio for NeRFs

Code repository for Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model.

The fastest repo in history to surpass 50K stars ⭐, reaching the milestone in just 2 hours after publication. Better Harness Tools that make real things done. Now writing in Rust using oh-my-codex.

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

SkyReels V3: Multimodal Video Generation Model

Lyrics extractor and Structured Lyric formatter AI Utility. This tool will extract just the voice from your music script and transibe it with whisper. The utility listens to the music to apply the appropriate [intro], [verse], [chorus], [solo], and [outro] tags. The package here is a One-Click Pinokio Installer.

A Vietnamese Voice Cloning Text-to-Speech Model ✨