Model · 3D
Step1X-3D
StepFun's open 3D model maker: it turns one picture into a clean 3D shape, then paints a texture onto it. Apache 2.0 licence, but running both stages needs a graphics card with about 27 GB of memory.
At a glance
- Open or closed
- Fully openWeights and code downloadable under a standard open licenceCode and weights released (training code too) under Apache 2.0.source · checked 12 Oct 2026 · checked on the maker's own page
- Licence
- Apache License 2.0 (Permissive (e.g. Apache 2.0, MIT))source · checked 12 Oct 2026 · checked on the maker's own page
- Can I sell what I make?
- YesApache 2.0 allows commercial use; the README makes no separate statement. Texture stage is SDXL-based, whose own licence was not checked.source · checked 12 Oct 2026 · checked, but the page was unclear or partial
- Cost
- Free option: Free to download and run; free online demo on Hugging Face Spaces.Plans below.
- How you use it
- On your own computer, Through another serviceGPU figures are for the full shape+texture pipeline; per-stage not given. Tested on Linux-style CUDA 12.4 setup (platform inferred). Also on ModelScope.source · checked 12 Oct 2026 · checked, but the page was unclear or partial
- Skill needed
- TechnicalPython, PyTorch, CUDA and kaolin setup.source · checked 12 Oct 2026 · checked on the maker's own page
- Made by
- StepFunPublished by the stepfun-ai GitHub organisation; country not stated.source · checked 12 Oct 2026 · checked, but the page was unclear or partial
- Status
- AvailableReleased May 2025; last listed update June 2025.source · checked 12 Oct 2026 · checked, but the page was unclear or partial
What you can make with it
- A 3D object or scene, from a photo (main use)
- A 3D object or scene, textures for a 3D model
image to 3D model3D model to 3D model
Stage 1 makes watertight geometry from an image; stage 2 paints textures (SDXL-based).
source · checked 12 Oct 2026 · checked on the maker's own page
Plans and prices
No paid plans listed.
source · checked 12 Oct 2026 · checked on the maker's own page
Related
Where you can run it
Other options for “A 3D object or scene, from a photo”
3D AI Studio, ComfyUI, CSM (Cube), Dzine, fal, Hugging Face, Hunyuan 3D (Tencent), Hunyuan3D 2, Hyper3D Rodin, InstantMesh, Kaedim, KIRI Engine, Krea, Meshy, Mixar, Polycam, Scenario, Sloyd, Spline AI, Stable Fast 3D, Stable Point Aware 3D (SPAR3D), TRELLIS, Tripo AI, TripoSR
About this entry
Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.