Running
on
Zero
510
๐งข
Shap-E
text-to-3D & image-to-3D
text-to-3D & image-to-3D
A unified multimodal understanding and generation model.
Framer: Interactive Frame Interpolation
Text Behind Image using birefnet-lite for background removal
Track, rank and evaluate open LLMs and chatbots
Text-to-3D and Image-to-3D Generation
Import a portrait, click to move the head!
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
3D/4D Scenes from a Single Image w/ Controllable Video Diff
remove background from any image