Content & Design

EmbodiedGen Text To 3D is an AI tool developed by HorizonRobotics that enables users to generate 3D models from simple text descriptions. Users can provide either English or Chinese text prompts to initiate the 3D model creation process. Additionally, the tool offers the option to include a reference image, which can guide the system in synthesizing matching images before converting the chosen image into a textured 3D model. This functionality makes it a versatile solution for quickly prototyping or generating 3D assets without extensive manual modeling. The tool is hosted on Hugging Face Spaces, indicating its accessibility and potential for community use.

ECON - Clothed Human Digitization is an AI tool hosted on Hugging Face Spaces, designed for generating 3D avatars from single photos. It leverages the ECON (Explicit Clothed humans Optimized via Normal integration) model to produce detailed clothed human models. While the tool aims to provide advanced digitization capabilities, the current live website indicates a runtime error, preventing immediate use or demonstration of its features. The underlying technology suggests a focus on realistic human representation for various applications, potentially including virtual try-on, animation, or game development. However, due to the error, specific functionalities and user experience cannot be fully assessed at this time.

Era3D MV Demo is presented as a demonstration of the Era3D platform's capabilities in 3D visualization. Hosted on Hugging Face Spaces, it was intended to allow users to explore and test 3D rendering functionalities. However, the current status indicates a runtime error, preventing the application from functioning as intended. The error message points to an issue during the initialization of ZeroGPU, suggesting a problem with the underlying hardware or software environment required for the demo to run. This prevents any interaction with the tool's features or assessment of its intended performance.

Hunyuan3D-2 is an advanced, open-source large-scale 3D synthesis system developed by Tencent-Hunyuan, designed for generating high-resolution textured 3D assets. The system operates on a two-stage generation pipeline, first creating a bare mesh with its Hunyuan3D-DiT shape generation model, and then synthesizing a texture map using its Hunyuan3D-Paint model. This approach effectively decouples shape and texture generation, offering flexibility for both generated and handcrafted meshes. Hunyuan3D-2 supports various platforms including Macos, Windows, and Linux, and can be used via code, a Gradio App, an API Server, or a Blender Addon. It aims to simplify the 3D asset re-creation process and has demonstrated superior performance compared to other state-of-the-art models in geometry details, condition alignment, and texture quality.

EmbodiedGen Image To 3D is an AI tool hosted on Hugging Face Spaces by HorizonRobotics, designed to convert single 2D images into realistic and physically plausible 3D models. Users can upload a photo of an object, with an optional SAM segmentation feature to refine the input. The application then processes the image to construct a 3D model, which can be previewed as a rotating video directly within the interface. For further use, the generated 3D model is available for download as a mesh. Additionally, the tool can estimate physical properties of the object, adding another layer of utility for various applications requiring accurate 3D representations.

Frame Interpolation is an AI tool hosted on Hugging Face that specializes in generating intermediate frames between two uploaded images. This functionality allows users to create smooth video transitions, effectively turning a sequence of still images into a fluid animation or video. By specifying the desired number of intermediate frames, the application can produce a seamless visual flow, which is ideal for creating slow-motion effects or increasing the frame rate of existing content. The tool is available for free, making it accessible for various creative projects and useful for video editors and animators looking to enhance their visual content with smooth, AI-generated transitions.

MetalSplatter is a Swift/Metal library designed for rendering 3D Gaussian Splats on Apple platforms, including iOS, macOS, and visionOS (with amplification for stereo rendering on Vision Pro). It allows users to load and visualize PLY, SPZ, and .splat files, making it ideal for real-time radiance field rendering. The library includes modules for core rendering, reading/writing PLY files (PLYIO), interpreting splat files (SplatIO), and a sample application to demonstrate usage. While documentation is a work in progress, the sample app provides a minimal illustration of its capabilities. It's an open-source project, offering a foundational tool for developers working with 3D Gaussian Splatting technology.

Limory - Live Memory AR is an innovative mobile application that leverages Augmented Reality (AR) technology to convert static photos into dynamic, engaging video clips. Users can trim and crop videos, select frames, and then print and share their augmented memories. The app is designed to create unforgettable moments by adding stunning animations and effects to personal photos, making them come alive simply by using a smartphone camera. It offers a unique way to share AR experiences with friends and family, or even send them as a gift. Limory works seamlessly across different environments and supports both Dark Mode and Light Mode on iPhone and iPad.

Image To 2.5D is an AI tool designed to convert standard 2D images into 2.5D representations, providing a simulated sense of depth. This application is intended to clone a GitHub repository and launch a demo app locally, requiring users to provide a GitHub URL in an .env file. However, the tool is currently facing significant technical issues, including runtime errors and storage limit exceeded messages, which prevent it from functioning as intended. The platform indicates a workload eviction due to exceeding a 50GB storage limit, making it currently unusable for its stated purpose.

Splatt3R is the official implementation of a research project focused on zero-shot Gaussian Splatting from uncalibrated image pairs. This feed-forward model is designed to directly predict 3D Gaussians from standard images, eliminating the need for complex calibration processes. It is particularly useful for computer vision and 3D graphics applications where rapid 3D scene reconstruction from minimal input is critical. The tool provides an initial codebase, a research paper, a project webpage, and a Gradio demo for easy experimentation. Users can set up an Anaconda environment, compile CUDA kernels, and utilize pretrained models and data from ScanNet++ to train their own models or generate 3D scene representations.

spz is an open-source file format developed by Niantic Labs for compressing 3D Gaussian splats. This format significantly reduces file sizes, typically by a factor of 10 compared to traditional PLY files, while maintaining virtually imperceptible visual quality. The project provides a robust C++ library for saving and loading .spz data, along with convenient Python bindings built using nanobind, making it accessible for various development environments. It supports configurable spherical harmonics quantization to balance file size and quality, and includes features like coordinate system conversions and vendor-specific extensions for camera limits. The format is designed for efficient storage and interoperability in 3D graphics applications.

SplatVFX offers an experimental approach to 3D Gaussian Splatting within the Unity VFX Graph, enabling developers and VFX artists to integrate advanced real-time 3D rendering into their projects. While not production-ready, it provides a foundation for exploring complex visual effects and experimental graphics. Users can import `.splat` files, convert `.ply` files, and adjust capacity for larger point clouds. The tool highlights the potential of Gaussian Splatting in Unity, despite current limitations such as color space artifacts and projection inaccuracies, encouraging further development and experimentation in the field.

Starring You® AI by JibJab offers an interactive platform for creating personalized and entertaining content. Users can easily swap faces into a wide array of hilarious images, GIFs, and videos, transforming themselves or their friends into the central character. The tool provides dynamic templates with fun animations and music, making it simple to produce engaging visual content. It's ideal for crafting unique party invitations, sharing memorable moments through eCards, or creating personalized music videos. With Starring You® AI, users can become a superstar in their messages and enjoy seeing themselves in various animated scenarios throughout the year.

LOTUS Depth is an AI tool designed for advanced depth estimation, allowing users to generate detailed depth maps from uploaded images or videos. The application supports two distinct modes: generative and discriminative. In generative mode, users can optionally provide a seed to influence the output. This tool is particularly useful for analyzing the spatial relationships and distances of objects within visual media. Hosted on Hugging Face, LOTUS Depth provides a accessible platform for researchers, developers, and enthusiasts interested in computer vision and 3D reconstruction tasks.

Multi HMR is an AI tool designed for 3D human pose estimation and model reconstruction. Users can upload an image, and the application will generate 3D models of humans, overlaying them onto the original image. It also provides a separate 3D view of the reconstructed models, allowing for detailed inspection. The tool offers adjustable parameters such as detection threshold and NMS kernel size, giving users some control over the reconstruction process. While the tool aims to provide advanced 3D modeling capabilities, it is currently experiencing a runtime error preventing full functionality.

Splat To Mesh is an AI tool hosted on Hugging Face designed for converting Gaussian Splat (.ply) files into 3D Mesh (.glb) files. This conversion facilitates 3D modeling and visualization, leveraging the LGM model for detailed mesh generation. The tool aims to simplify the process of transforming complex splat data into a more universally usable 3D mesh format. While the specific Space on Hugging Face is currently paused, the underlying functionality offers a valuable solution for users working with Gaussian Splats who need to integrate them into standard 3D workflows. It caters to individuals and professionals looking to streamline their 3D asset creation and manipulation.

GRM offers a live demonstration of the Large Gaussian Reconstruction Model, a cutting-edge AI technology designed for efficient 3D reconstruction and generation. Hosted on Hugging Face Spaces, this application allows users to experience the model's capabilities directly through an embedded iframe. The tool is free to use and operates under the permissive MIT license, making it accessible for researchers, developers, and enthusiasts interested in advanced 3D AI applications. While primarily a demo, it showcases the potential for creating and reconstructing 3D assets with high efficiency, without requiring any user input beyond viewing the demo.

SpaRP is a Hugging Face Space developed by sudo-ai that allows users to generate 3D textured meshes and pose estimations from a few unposed images of an object. This tool is particularly useful for creating 3D models from 2D inputs, streamlining the process of 3D asset creation. For optimal results, the application supports the use of background-removed images, which can significantly improve the quality of the generated 3D models. It is an accessible web-based application, making it easy for users to upload images and obtain 3D outputs without needing specialized software.

4d-gaussian-splatting is an open-source implementation for real-time photorealistic dynamic scene representation and rendering, based on the ICLR 2024 paper "Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting." This tool allows users to model dynamic scenes using native 4D Gaussian primitives, offering a coherent integrated approach to space and time dimensions. It builds upon the principles of 3D Gaussian Splatting and provides a dedicated rendering pipeline. The project includes resources for data preparation using datasets like DyNeRF and DNeRF, and offers scripts for training models. It's ideal for researchers and developers working on advanced 3D and animation projects.

ReconViaGen is a powerful AI tool hosted on Hugging Face Spaces, designed for generating high-fidelity 3D geometry from multi-view images. Users can easily upload either a video or multiple pictures of an object, and the application will process them to create a detailed 3D model. This model can then be viewed as a rotating preview directly within the app. A key feature is the ability to download the generated 3D model as a GLB file, providing flexibility for further use in other 3D applications or projects. The tool also offers an optional export feature, enhancing its utility for various creative and technical workflows.

Roblox 3D Assets Generator v1 is a specialized AI tool hosted on Hugging Face that enables users to quickly create 3D models directly from images. Designed with the Roblox platform in mind, this generator streamlines the asset creation process, allowing for rapid prototyping and development within the Roblox ecosystem. The tool aims to simplify the conversion of 2D images into functional 3D assets, making it accessible for creators who need to populate their virtual worlds efficiently. While currently experiencing a runtime error, its core functionality is to provide a fast and straightforward method for generating game-ready 3D models.

SAM2Point is an AI tool designed for visualizing and segmenting 3D scenes or objects. Users can interact with 3D content and perform segmentation tasks using different types of prompts, including points, bounding boxes, or masks. The application offers flexibility by allowing users to select from various 3D datasets, making it suitable for diverse applications in 3D content analysis and manipulation. While the live website indicates a runtime error, the tool's core functionality revolves around advanced 3D segmentation capabilities, leveraging AI models to process and interpret complex spatial data. It is hosted on Hugging Face, suggesting an accessible platform for experimentation and development in 3D AI.

SGS 1 is an innovative AI tool designed to generate 3D CAD models from image inputs. This tool provides a unique capability for users to transform 2D visual data into detailed 3D models, streamlining the design and prototyping process. It operates as a Hugging Face Space, allowing users to download the tool and run its interactive demo locally on their own machines. This local execution ensures greater control and potentially faster processing for engineers, designers, and 3D modelers looking to quickly create or iterate on 3D designs based on existing images.

Sparc3D is an innovative AI tool designed for generating next-generation, high-resolution 3D models. Users can create detailed 3D shapes by providing a text prompt or adjusting various settings within its embedded interface. The platform, available as a Hugging Face Space, offers a straightforward way to produce complex 3D assets without extensive manual modeling. Once generated, the 3D models are downloadable, making them suitable for integration into game development, design visualization, and other applications requiring precise and high-fidelity 3D content. Sparc3D streamlines the creation process, enabling users to quickly obtain ready-to-use 3D assets.