27 projects
fireredtts3-mnn
FireRedTTS3 zero-shot TTS on MNN int8 (CPU, torch-free, ~4x faster)
music3-mnn
MiniMax-Music3 (~11B) text-to-music inference on MNN (Apple Silicon CPU/Metal)
anima-mlx
Anima-2.9B anime text-to-image on Apple Silicon via MLX (CLI + Python API, auto-downloads weights)
index-tts-2.5-mnn
IndexTTS-2.5 voice cloning on MNN: fast CPU inference, torch-free, one-click uvx
index-tts-2.5-onnx
IndexTTS-2.5 voice cloning on ONNX Runtime: fp32 bit-exact, torch-free, one-click uvx, CPU/CUDA
index-tts-2.5-mlx
IndexTTS-2.5 voice cloning on Apple Silicon: MLX int8, torch-free, one-click uvx
mmh3turbo
MiniMax-H3 video+audio generation on Apple Silicon, with custom int8 Metal kernels
zimgturbo
Z-Image-Turbo text-to-image on Apple Silicon, accelerated with int8 custom Metal kernels
zimage-mnn
Z-Image-Turbo text-to-image generation on MNN (Apple Silicon Metal / CPU)
qwen3-asr-mnn
Qwen3-ASR (0.6B/1.7B) speech recognition on pure CPU via MNN — no PyTorch required at runtime
qwen3-tts-mnn
Qwen3-TTS (12Hz, voice clone) inference on pure CPU via MNN — no PyTorch required at runtime
lyrichroma
Convert audio to video with auto-generated karaoke subtitles
supertonic-mnn
CLI tool for Supertonic MNN inference
mstt-funasr
mstt_funasr-A plugin for mstt to add support for FunASR models.
mstt
mstt-A command-line tool and Python library for running speech-to-text against multiple models.
flopth
A program to calculate FLOPs and Parameters of Pytorch models
chumpy-fork
chumpy fork, with latest python, pip and numpy support
mimic-head
Unofficial One-click Version of LivePortrait, with Webcam Support
talkgpt4all
A voice chatbot based on GPT4All and OpenAI Whisper, running on your PC locally
dompare
A program to diff two directories recursively
bing-brush
One-line Image Generating Program Based on the Bing Image Createor (Powered by DALL·E 3)
mp-face-stylizer
A cli program of face stylizer based on MediaPipe
dinov2-retrieval
A cli program of image retrieval using dinov2
easybox
A simple but powerful bounding box annotation tool by Python
py-reuse
Collection of useful python functions
dozy
A simple and user-friendly tool for operating images and videos
yammtool
Yet Another MultiMedia Tool
