Running
on
T4
393
🗣️
MeloTTS
Fast, efficient, & multilingual text-to-speech
Helpful tools for day-to-day uses...
Fast, efficient, & multilingual text-to-speech
Note Score: 9/10 - Very useful ↳ Analyzes Image into Prompts and keywords (Deep CLIP into styles, medium, artist, etc.)
Note Score: 9/10 - Very useful ↳ Doesn't use Whisper-Large-V3 - onnx version is loaded instead for lower delay
Create a 1M faces 3D colored model from an image!
The most opinionated, anime-themed SDXL model