LHM is a feedforward model that can reconstruct an animatable 3D human body from a single image within seconds. Trained with image reconstruction loss on a large-scale video dataset, our model demonstrates strong generalization capabilities across diverse real-world scenarios.

This is a text-to-video generation model based on the Wan2.1-T2V-1.3B model, fine-tuned with LoRA on the 3dgs-dissolve dataset, capable of generating video content with dissolve effects based on text descriptions.

MultimodalDiffusersOther

A 3D-aware video diffusion model supporting diverse video generation control

Computer VisionDiffusers

SLAM3R is a real-time dense scene reconstruction system based on monocular RGB video, achieving 3D scene reconstruction through feedforward neural network point cloud regression.

Computer VisionSafetensors

SLAM3R is a real-time dense scene reconstruction system based on monocular RGB video, capable of performing point cloud regression through feedforward neural networks to achieve dense 3D reconstruction.

Computer VisionSafetensors

Coinmaker is a LORA model specifically designed for generating coin assets, trained based on SDXL 0.9. It makes the creation of coin assets in scenarios such as video games and rendering easier, more interesting, and more aesthetically pleasing, especially suitable for 3D projection and extrusion modeling in 3D software.

Computer VisionDiffusers