# Tencent-Hunyuan/HunyuanWorld-Voyager

Voyager is an interactive RGBD video generation model conditioned on camera input, and supports real-time 3D reconstruction.

Repository: https://github.com/Tencent-Hunyuan/HunyuanWorld-Voyager
Canonical: https://ross.abutalabs.com/products/hunyuanworld-voyager
Homepage: https://3d-models.hunyuan.tencent.com/world/
Language: Python
License: NOASSERTION
License Family: other
Topics: 3d, 3d-generation, aigc, hunyuan3d, image-to-3d, image-to-video, scene-generation, world-model, world-models
Last push: 2026-04-15T17:30:08+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 77, release rhythm 35, longevity 26
- inputs: {"age_days": 371, "days_push": 140, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1590, forks 163 (observed 2026-08-28T04:05:08.519172+00:00)

## What it is
HunyuanWorld-Voyager is a video diffusion framework from Tencent Hunyuan that generates world-consistent RGBD video and 3D point-cloud sequences from a single image along a user-defined camera path. It includes inference code and model weights, with generated aligned RGB and depth that can be used for real-time 3D scene reconstruction.

## Use cases
- generate a 3d-consistent scene video from a single image
- create an explorable 3d world from one photo
- control the camera trajectory in ai video generation
- generate aligned rgb and depth video for 3d reconstruction
- build a 3d point cloud from a generated video
- image to 3d world model

## When to choose
- you want 3D-consistent video generation from a single input image
- you need RGB and depth outputs that align for direct 3D reconstruction
- you need to steer generation along a custom or user-defined camera path
- you want to generate 3D point-cloud sequences of a scene for world exploration

## When to avoid
- you need general-purpose text-to-video generation without 3D constraints
- you lack a high-VRAM GPU for large video diffusion inference
- you want real-time interactive world creation or play, where successor models like HunyuanWorld-1.5 or HY-World-2.0 may fit better
- you need a production-grade SDK or hosted API rather than a research codebase and model weights

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, video-processing, image-processing, computer-vision, gpu-computing
- domain: artificial-intelligence, deep-learning, machine-learning, computer-vision, image-processing, graphics
- platform: python
- tags: 3d-reconstruction, world-model, video-diffusion, rgbd, point-cloud, camera-control, scene-generation, image-to-video, 3d-world-generation, hunyuan, video, gpu, linux

## Member repositories
- Tencent-Hunyuan/HunyuanWorld-Voyager (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:08.519172+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:54:46.239858+00:00, confidence not recorded.
  - readme: https://github.com/Tencent-Hunyuan/HunyuanWorld-Voyager (fetched 2026-08-28T04:05:08.519172+00:00, sha 1a76ceda588f)
  - homepage: https://3d-models.hunyuan.tencent.com/world/ (fetched 2026-08-29T11:25:24.565467+00:00, sha 64d8acac6828)
- Data as of 2026-08-30T08:39:29.467469+00:00.