Instructions to use suvadityamuk/Step1X-3D-Geometry-1300m-diffusers-3d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use suvadityamuk/Step1X-3D-Geometry-1300m-diffusers-3d with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("suvadityamuk/Step1X-3D-Geometry-1300m-diffusers-3d", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Step1X-3D Geometry 1300m for diffusers-3d
stepfun-ai/Step1X-3D converted into a diffusers-3d
pipeline: ordinary Diffusers and Transformers component folders plus the object3d_model_index.json sidecar that
the package's auto-loader validates before downloading anything. Nothing here requires remote code.
Install
pip install git+https://github.com/suvadityamuk/diffusers-3d.git
pip install "git+https://github.com/suvadityamuk/diffusers-3d.git#subdirectory=packages/diffusers-3d"
diffusers-3d runs every network in plain PyTorch on CPU or GPU. Rendering Gaussian splats needs the optional
gsplat backend; the PBR-textured mesh for TRELLIS.2 needs CuMesh (see the package docs).
Usage
import torch
from diffusers_3d import AutoPipelineForImageTo3D, ImageCondition
pipeline = AutoPipelineForImageTo3D.from_pretrained("suvadityamuk/Step1X-3D-Geometry-1300m-diffusers-3d").to("cuda")
mesh = pipeline(ImageCondition(image=rgba), generator=torch.Generator("cuda").manual_seed(0)).objects[0]
rgba is a (4, H, W) tensor in [0, 1] whose alpha channel masks the object; the pipeline crops and pads it as the released code does. This is the geometry stage (Step1X-3D-Geometry-1300m); the result is an untextured MeshAsset.
Components
| Folder | Class |
|---|---|
image_encoder |
transformers.Dinov2WithRegistersModel |
scheduler |
diffusers_3d.families.step1x3d.scheduler.Step1X3DFlowMatchEulerScheduler |
transformer |
diffusers_3d.families.step1x3d.models.Step1X3DTransformer1DModel |
vae |
diffusers_3d.families.step1x3d.vae.Step1X3DShapeDecoder |
Provenance
Converted with diffusers-3d-convert-step1x3d from diffusers-3d 0.1.0.dev0; the package's family README lists the pinned upstream
revisions and how the conversion maps each tensor. Parity tests against the pinned upstream code are part of the
package test suite.
License and attribution
Step1X-3D weights and code: Apache-2.0, Copyright (c) StepFun. The DINOv2 image encoder weights
are Apache-2.0, Copyright (c) Meta Platforms, Inc. See LICENSE-APACHE-2.0 and NOTICE. Not affiliated with or
endorsed by StepFun or Meta.
- Downloads last month
- -
Model tree for suvadityamuk/Step1X-3D-Geometry-1300m-diffusers-3d
Base model
stepfun-ai/Step1X-3D