The first ๐ฑ Luminia โจ, where we, the community, bring modest ideas ๐ to life, creating anything from datasets and demos to ML models.
CPU translation & chat with any GGUF model (Xet downloads)
Image to 3D + Multi-view Point Cloud
Remove unwanted objects from images with LaMa
XTTS2 voice cloning + Bark TTS in one space
Separate any sound with natural language
Separate each isolated voice for RVC training.
Separate audio into vocals, drums, bass, other stems
Clean & convert voice with VoiceFixer + FreeVC
Image-to-depth, map Monocular depth maps via ZoeDepth.