ComfyUI-Step1X-3D

ComfyUI-Step1X-3D
★ 13

3D资产生成几何纹理对齐多风格渲染高保真
生成高保真3D资产，确保几何与纹理一致对齐，支持卡通、素描和写实多风格输出。
💡 在ComfyUI中生成几何与纹理一致的高保真3D资产，支持卡通、素描和写实风格。
🍴 2 Forks💻 Python🔄 2025-05-16
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/a9fb3a59e10c
📦 requirements.txt
datasets==2.19.0
diffusers==0.32.2
einops==0.8.0
huggingface-hub==0.26.2
imageio==2.34.1
jaxtyping==0.2.28
joblib==1.4.0
lightning-utilities==0.11.2
matplotlib==3.8.4
numpy==1.26.4
omegaconf==2.3.0
opencv-python-headless==4.10.0.84
pandas==2.2.2
pillow==10.3.0
plyfile==1.0.3
PyMCubes==0.1.4
pyparsing==3.1.2
pytorch-lightning==2.2.4
PyYAML==6.0.1
safetensors==0.4.3
scikit-image==0.23.2
scipy==1.13.0
tensorboard==2.16.2
tensorboardX==2.6.2.2
timm==0.9.16
tokenizers==0.21.0
tqdm==4.66.2
transformers==4.48.0
trimesh==4.3.2
spaces==0.28.3
accelerate==1.5.2
rembg==2.0.65
gradio==5.5.0
wandb==0.18.6
deepspeed==0.16.4
sageattention==1.0.6
mosaicml-streaming==0.11.0
easydict==1.13
open3d==0.19.0
prodigyopt==1.1.2
peft==0.15.1
sentencepiece==0.2.0
pymeshlab==2023.12.post3
onnxruntime==1.21.0
bs4==0.0.2
xatlas==0.0.10
pybind11==2.13.6
pygltflib==1.16.4
kornia==0.8.0
git+https://github.com/NVlabs/nvdiffrast.git
📄 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

  • Make sure you have ComfyUI installed

  • 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

  • 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.