hi3d-official/Hi3Dv1.0
image-to-3d model by hi3d-official
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
English · 简体中文 High-resolution 3D geometry refinement built upon Sparc3D. Live Demo · GitHub Repository · International Website · China Website Technical Report (PDF) · Download PDF Released on October 23, 2026. Hi3D v1.0 refines a coarse mesh into high-resolution geometry, conditioned on a reference image of the same object. Built upon the Sparc3D representation and refinement architecture, it progressively samples sparse latents, decodes them with a self-pruning sparse VAE, and extracts a mesh. The project report describes training on approximately two million curated 3D assets and refinement up to an effective sparse extraction-grid resolution of 1536³. The Python package and public API retain the names sparc3d and Sparc3DPipeline for compatibility. This repository provides the Hi3D v1.0 refinement model artifacts. Inference code is available in the GitHub repository. Training code and the paper's evaluation harness are not included. Model artifacts are available on Hugging Face. The examples load hi3d-official/Hi3Dv1.0 directly;…
Read the full model card ↗ · Preview checked 2026-10-31T04:15:10.230Z
Inside the original model card — Document outline
- Hi3D v1.0
- Overview
- System overview
- Visual comparisons
- Local geometry
- Multi-view comparisons
- Installation
- Model artifacts
- Python API
- Memory offload and progress
- Command line
- Optional Hunyuan coarse-generation example
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
- Technical Report (PDF)
- Download PDF
- pipeline details
- ![Additional multi-view examples for a humanoid bust, mechanical robots, and a stylized character
- installation
- upstream source license
- Hunyuan3D-2 mini model license
- external models and optional examples
- coarse-stage installation notes
- Reproduction
- Hi3D Open License Agreement Version 1.0
- license scope
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
hi3d-official/Hi3Dv1.0 is a image-to-3d model repository published by hi3d-official on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-to-3d
- Library
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 147
- Hugging Face trending score
- 96
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-16T07:51:15.000Z
- Last modified
- 2026-10-23T16:04:31.000Z
Compatibility and lineage
Reported languages: en, zh
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:49:30.141Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.