# wenqsun/DimensionX

[ICCV'25]DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion

Repository: https://github.com/wenqsun/DimensionX
Canonical: https://ross.abutalabs.com/products/dimensionx
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-10-17T07:46:12+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 47, release rhythm 35, longevity 47
- inputs: {"age_days": 664, "days_push": 320, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1333, forks 77 (observed 2026-08-28T04:04:24.596949+00:00)

## What it is
DimensionX is a research framework that generates photorealistic 3D and 4D scenes from a single image using controllable video diffusion models. It decouples spatial and temporal factors in video diffusion via ST-Director LoRA adapters to enable precise camera trajectory and dynamics control.

## Use cases
- generate a 3D scene from a single photo
- create 4D dynamic scenes from one image
- control camera orbit in video diffusion output
- reconstruct 3D from generated video frames
- train custom camera-control LoRA for video diffusion
- run video diffusion research on scene generation

## When to choose
- you need 3D/4D scene generation from a single image
- you want controllable camera trajectories in video diffusion
- you need state-of-the-art decoupled spatial-temporal video generation research code

## When to avoid
- you need production-ready real-time 3D rendering
- you lack a GPU or cannot run large diffusion models
- you only need simple image-to-video without 3D/4D reconstruction

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, video-processing, stable-diffusion, graphics, simulation
- domain: computer-vision, artificial-intelligence, deep-learning, graphics
- platform: python
- tags: video-diffusion, 3d-reconstruction, 4d-generation, camera-control, lora-adapters, iccv-2025, research-code, video, gpu, linux

## Member repositories
- wenqsun/DimensionX (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:24.596949+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 2026-08-30T04:44:55.865658+00:00, confidence not recorded.
  - readme: https://github.com/wenqsun/DimensionX (fetched 2026-08-28T04:04:24.596949+00:00, sha 4dc2312dac7e)
- Data as of 2026-08-30T08:39:29.467469+00:00.