Highlights
- Pro
Stars
A framework for high-quality material transfer that allows users to adjust the degree of material application.
MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion
RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesis
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
Fast and memory-efficient exact attention
[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
An official implementation of PRM, a feed-forward framework for high-quality 3D mesh generation from a single image.
Official PyTorch implementation of the CVPR 2024 Highlight Paper "Real-time 3D-aware Portrait Video Relighting"
Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA
Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]
UV-free Texture Diffusion (UV3-TeD) is a denoising diffusion probabilistic model constrained to operate on the surface of 3D objects and capable of generating textures as coloured point-clouds.
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
[SIGGRAPH2024] DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
Interactive Text-to-Texture Synthesis via Unified Depth-aware Inpainting.
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
STAR: Scale-wise Text-to-image generation via Auto-Regressive representations
TexPainter: Generative Mesh Texturing with Multi-view Consistency
This repository contains the code for CVPRW 2024 paper: Generating Material-Aware 3D Models from Sparse Views
[CVPR 2024] code release for "DiffusionLight: Light Probes for Free by Painting a Chrome Ball"