Open-source image-to-3D and text-to-3D generation model from Hi3D, formerly Sparc3D, trained on ~2M curated 3D assets.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Hi3D 1.0 (formerly Sparc3D) is the open-source release of Hi3D's 3D generation model. It generates detailed 3D assets from images or text prompts. According to the vendor, it was trained on nearly 2 million curated 3D assets and evaluated for multi-view quality, local details and geometric usability, and validated in production workflows before release.\n\nThe open-source package provides model weights and resources for local deployment, with source code and deployment guides on GitHub. A YouTube creator reports a total size of about 7.74 GB. The vendor also offers an online version for use without local deployment.\n\nThe open release is version 1.0. Hi3D's newer version 3.0 remains closed and is offered through the hosted service. The vendor says v3.0 reaches 2048³ voxel-level geometry resolution and up to 8K textures. The hosted service uses a credit-based subscription model with a free plan, paid plans and credit packs.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Hi3D open-sourced its version 1 model for detailed 3D asset generation from prompts or images. The latest version 3 remains closed. Total size is about 7.74 GB and it compares favorably with other open 3D generators.
Closest neighbours by meaning, not just by category.
Model · Tencent
Tencent's unified multimodal model for 3D understanding, text-to-3D generation, instruction-based editing and part generation.
Model
Image-to-3D generator from Tsinghua and Tencent ARC Lab that builds meshes pixel-aligned to the input view.
App
Open-source desktop app that generates 3D meshes from images using AI models running locally on your GPU.
Model · MiniMax
Open-weights MiniMax image generation and editing model producing up to ~16 MP images in 6 sampling steps.
Model · MiniMax
Open-weight video generation model from MiniMax, part of its H3 family alongside H3 Image.
Library · World Labs
World Labs tooling that turns a single image into an editable 3D environment with meshes, splats, physics and lighting.
