Stars
Towards a Generative 3D World Engine for Embodied Intelligence
We propose a novel partition method for reliable feature-aligned quadrangulation.
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Stable Virtual Camera: Generative View Synthesis with Diffusion Models
Code of MCMat: Multiview-Consistent and Physically Accurate PBR Material Generation;
[ICLR 2025 Spotlight] Official Implementation for ToST (Token Statistics Transformer)
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
An open source code repository of driving world models, with training, inferencing, evaluation tools, and pretrained checkpoints.
[ICCV 2025] Official impl. of "MV-Adapter: Multi-view Consistent Image Generation Made Easy"
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
Official implementation of OneDiffusion paper (CVPR 2025)
Flatten Anything: Unsupervised Neural Surface Parameterization
A detailed diagram laying out the full Flux.1 [dev] architecture as shared by Black Forest Labs at https://github.com/black-forest-labs/flux.
深入探索精选的套壳站和必备API资源。本文为初学者和经验丰富的运营者提供一站式指南，涵盖常见问题解答和基础攻略，助您迈向套壳站副业成功之路。Dive into a curated selection of shell sites and essential APIs. This article offers a comprehensive guide for both beginners a…
Official inference repo for FLUX.1 models
[CVPR 2025 Highlight] Material Anything: Generating Materials for Any 3D Object via Diffusion
A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.