GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation
DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors
MotionDirector: Motion Customization of Text-to-Video Diffusion Models
one-shot-talking-face-replicate
MoE-LLaVA
AnimateLCM Cartoon3D Model
Create a video from an image
Hand Refiner 512x512
MetaVoice-1B: 1.2B parameter base model trained on 100K hours of speech
LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation
Guiding Instruction-based Image Editing via Multimodal Large Language Models
MagicDance: Realistic Human Dance Video Generation with Motions & Facial Expressions Transfer
DUSt3R: Geometric 3D Vision Made Easy
Rethinking Inductive Biases for Surface Normal Estimation
TripoSR: Fast 3D Object Reconstruction from a Single Image
CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model
Visual Style Prompting with Swapping Self-Attention
Open-Sora is a work-in-progress model.
APISR: Anime Production Inspired Real-World Anime Super-Resolution
This model is cold. You'll get a fast response if the model is warm and already running, and a slower response if the model is cold and starting up.
This model runs on A100 (80GB). View more.
