TRELLIS
Scalable and Versatile 3D Generation from images
Scalable and Versatile 3D Generation from images
Create a 1M faces 3D colored model from an image!
Create 3D models from images
Create 3D meshes from images
Text-to-3D and Image-to-3D Generation
a super consistent video depth model
Generate high-quality predictions from images or videos
Generate depth maps from images and videos
Estimate depth from images
Generate depth and normal maps from images
StableNormal Turbo Beta
A unified multimodal understanding and generation model.
Generate speech from text with customizable voices
Make Custom Voices With KokoroTTS
A Diffusion Model for Video Inpainting
Generate depth video from input video
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)