Extensions/ComfyUI-Step1X-3D
ComfyUI Extension

ComfyUI-Step1X-3D

ComfyUI-Step1X-3D is now available in ComfyUI, delivering high-fidelity 3D asset generation with consistent geometry-texture alignment. It supports multi-style outputs:…

By Yuan-ManX·Created about a year ago·Updated about a year ago· 14
Yuan-ManX/ComfyUI-Step1X-3D
Nodes
On cloudLocal install
Stars14
Updatedabout a year ago
Readme

ComfyUI-Step1X-3D

ComfyUI-Step1X-3D is now available in ComfyUI, delivering high-fidelity 3D asset generation with consistent geometry-texture alignment. It supports multi-style outputs: cartoon, sketch, and photorealistic.

Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets.

Installation

  1. Make sure you have ComfyUI installed

  2. Clone this repository into your ComfyUI's custom_nodes directory:

cd ComfyUI/custom_nodes
git clone https://github.com/Yuan-ManX/ComfyUI-Step1X-3D.git
  1. Install dependencies:
cd ComfyUI-Step1X-3D

pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url https://download.pytorch.org/whl/cu124
pip install -r requirements.txt
pip install torch-cluster -f https://data.pyg.org/whl/torch-2.5.1+cu124.html

cd step1x3d_texture/custom_rasterizer
python setup.py install
cd ../differentiable_renderer
python setup.py install

Model

Models Downloading

| Model | Download link | Size | Update date |
|-----------------------------|-------------------------------|------------|------| | Step1X-3D-geometry| 🤗 Huggingface | 1.3B | 2025-05-13 | | Step1X-3D-geometry-label | 🤗 Huggingface | 1.3B | 2025-05-13| | Step1X-3D Texture | 🤗 Huggingface | 3.5B |2025-05-13| |Models in ModelScope |🤗 ModelScope | 6.1B | 2025-05-14|

Open filtered high quaily datasets

| Data source | Download link | Size | Update date |
|-----------------------------|-------------------------------|------------|------| | Objaverse| 🤖Huggingface | 320K |2025-05-13| | Objaverse-XL | 🤖Huggingface | 480K |2025-05-13| | Assets for texture synthesis | 🤖Huggingface | 30K |2025-05-13| | Assets in ModelScope| 🤖ModelScope | 830K |2025-05-14|

Given the above high quality 3D assets, you can follow methods from Dora to preprocess data for VAE and 3D DiT training, and from MV-Adapter for ig2mv training.