microsoft/TRELLIS.2-4B
Image-to-3D • Updated
• 664
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Fast, multi-speaker TTS (44.1kHz) with voice cloning
ultra-fast video model, LTX 0.9.8 13B distilled
High-fidelity 3D Generation from images
Segment images with click points and download cutouts
A small but powerful reasoning model
State-of-the-art audio transcription in your browser
In-browser image background removal
In-browser image segmentation w/ 🤗 Transformers.js
Classify images in real-time using labels
Separate songs into individual stems (vocals, drums, etc.)
Generate expressive speech from text and voice reference
Generate images from text prompts (PRO users only)