Blender MCP is a plugin that connects Blender with Claude AI via the Model Context Protocol (MCP), enabling AI to directly interact with and control Blender. This integration significantly improves 3D modeling efficiency and is suitable for designers and developers.

HiPixel is a native macOS application designed for image super-resolution processing. It utilizes Upscayl's AI model to provide high-quality image upscaling, and achieves fast processing through GPU acceleration. It is suitable for designers and photographers who need image processing. This product runs smoothly on the macOS platform, supports multiple image formats, and provides a convenient folder monitoring function. HiPixel is positioned as an efficient image processing tool, aiming to improve user work efficiency.

LHM (Large-scale Animatable Human Reconstruction Model) utilizes a multimodal transformer architecture for high-fidelity 3D head reconstruction, supporting the generation of animatable 3D human characters from a single image. The model can accurately preserve clothing geometry and texture, and is particularly excellent at restoring facial identity and details, making it suitable for application scenarios with high requirements for 3D reconstruction accuracy.

Cube is a powerful 3D intelligent generation model designed to help developers create various 3D assets and scenes on the Roblox platform. The model features 3D object generation, character animation rigging, and procedural script generation. It significantly enhances creator productivity, sparks more creativity, and helps users build rich 3D experiences faster. The current version is open-source, aiming to share with the research community to advance 3D intelligence. Suitable for developers and creators of all sizes, supporting experimentation, innovation, and promoting responsible use.

Thera is an advanced super-resolution technique capable of generating high-quality images at various scales. Its main advantage lies in its built-in physical observation model, effectively avoiding aliasing artifacts. Developed by a research team at ETH Zurich, this technology is applicable to image enhancement and computer vision, particularly in remote sensing and photogrammetry.

DiffSplat is an innovative 3D generation technology that quickly creates 3D Gaussian point clouds from text prompts and single-view images. This technology leverages a large-scale pre-trained text-to-image diffusion model to efficiently generate 3D content. It addresses the limitations of traditional 3D generation methods concerning dataset size and the ineffective use of 2D pre-trained models, while maintaining 3D consistency. Key advantages of DiffSplat include efficient generation speeds (completed in 1 to 2 seconds), high-quality 3D output, and support for various input conditions. The model has broad prospects in academic research and industrial applications, particularly in scenarios requiring the rapid generation of high-quality 3D models.

ComfyUI-Hunyuan3DWrapper is a plugin based on ComfyUI that encapsulates the Hunyuan3D-2 model for efficient 3D image generation and texture processing. By streamlining the usage process of the Hunyuan3D-2 model, this tool allows users to quickly create high-quality 3D models and textures within the ComfyUI environment. It supports custom configurations and extensions, making it ideal for users engaged in efficient 3D content creation.

Hunyuan3D 2.0 is an advanced large-scale 3D synthesis system developed by Tencent, focusing on generating high-resolution textured 3D assets. The system comprises two core components: the large-scale shape generation model Hunyuan3D-DiT and the large-scale texture synthesis model Hunyuan3D-Paint. By decoupling the challenges of shape and texture generation, it provides users with a flexible platform for 3D asset creation. The system surpasses existing open-source and closed-source models in geometric details, conditional alignment, texture quality, and more, showcasing high practicality and innovation. Currently, the inference code and pre-trained models of this model are open-sourced, allowing users to quickly experience it through the official website or Hugging Face space.

MegaSaM is a system that allows for accurate, rapid, and robust estimation of camera parameters and depth maps from monocular videos of dynamic scenes. This system overcomes the limitations of traditional structure-from-motion and monocular SLAM techniques, which typically assume that the input videos primarily contain static scenes with significant parallax. MegaSaM can be extended to videos of complex dynamic scenes in the real world, including those with unknown fields of view and unconstrained camera paths, through carefully modified depth-visual SLAM frameworks. Extensive experiments on both synthetic and real videos demonstrate that MegaSaM is more accurate and robust in camera pose and depth estimation while being faster or comparable in runtime to previous and concurrent work.

The AI image upscaler leverages artificial intelligence technology to quickly enlarge and improve photo quality without requiring a login. Its main advantage lies in its ability to intelligently analyze and enhance image resolution, making the images clearer and more vivid.

AI Image Enlarger and Photo Enhancer uses advanced artificial intelligence technology to automatically improve image quality, repair blur and noise, enhance details, and is a free online tool.

Blender MCP is a plugin that connects Blender with Claude AI via the Model Context Protocol (MCP), enabling AI to directly interact with and control Blender. This integration significantly improves 3D modeling efficiency and is suitable for designers and developers.

HiPixel is a native macOS application designed for image super-resolution processing. It utilizes Upscayl's AI model to provide high-quality image upscaling, and achieves fast processing through GPU acceleration. It is suitable for designers and photographers who need image processing. This product runs smoothly on the macOS platform, supports multiple image formats, and provides a convenient folder monitoring function. HiPixel is positioned as an efficient image processing tool, aiming to improve user work efficiency.

Vibe Draw is a powerful AI-driven platform that quickly transforms rough sketches into professional-quality 3D models. Its intuitive tools make it easy for designers and developers alike, especially those who want to quickly realize their creative visions. This product can optimize design workflows and is suitable for games, 3D printing, and AR/VR fields. Vibe Draw is suitable for all types of creators, providing a simple and efficient way of 3D design.

LHM (Large-scale Animatable Human Reconstruction Model) utilizes a multimodal transformer architecture for high-fidelity 3D head reconstruction, supporting the generation of animatable 3D human characters from a single image. The model can accurately preserve clothing geometry and texture, and is particularly excellent at restoring facial identity and details, making it suitable for application scenarios with high requirements for 3D reconstruction accuracy.

Cube is a powerful 3D intelligent generation model designed to help developers create various 3D assets and scenes on the Roblox platform. The model features 3D object generation, character animation rigging, and procedural script generation. It significantly enhances creator productivity, sparks more creativity, and helps users build rich 3D experiences faster. The current version is open-source, aiming to share with the research community to advance 3D intelligence. Suitable for developers and creators of all sizes, supporting experimentation, innovation, and promoting responsible use.

Thera is an advanced super-resolution technique capable of generating high-quality images at various scales. Its main advantage lies in its built-in physical observation model, effectively avoiding aliasing artifacts. Developed by a research team at ETH Zurich, this technology is applicable to image enhancement and computer vision, particularly in remote sensing and photogrammetry.

GaussianCity is a framework focused on efficiently generating boundless 3D cities, based on 3D Gaussian rendering technology. This technology, through compact 3D scene representation and a spatially aware Gaussian attribute decoder, solves the memory and computational bottlenecks encountered by traditional methods when generating large-scale city scenes. Its main advantage is the ability to quickly generate large-scale 3D cities in a single forward pass, significantly outperforming existing technologies. This product was developed by the S-Lab team at Nanyang Technological University, with the related paper published in CVPR 2025. The code and models have been open-sourced and are suitable for researchers and developers who need to efficiently generate 3D city environments.