3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion

TL;DR

3DTopia-XL is a 3D diffusion transformer (DiT) operating on primitive-based representation.
It can generate 3D asset with smooth geometry and PBR materials from single image or text.

Paper | Project Page | Video | Weights | Hugging Face 🤗 | WiseModel

teaser_en.mp4

News

[10/2024] WiseModel demo released!

[09/2024] Technical report released!

[09/2024] Hugging Face demo released!

[09/2024] Inference code released!

Citation

If you find our work useful for your research, please consider citing this paper:

@article{chen2024primx,
  title={3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion},
  author={Chen, Zhaoxi and Tang, Jiaxiang and Dong, Yuhao and Cao, Ziang and Hong, Fangzhou and Lan, Yushi and Wang, Tengfei and Xie, Haozhe and Wu, Tong and Saito, Shunsuke and Pan, Liang and Lin, Dahua and Liu, Ziwei},
  journal={arXiv preprint arXiv:2409.12957},
  year={2024}
}

TODO List

• Dataset and captions
• Training code
• Text-conditioned model
• Image-conditioned model
• Inference code
• Technical report
• Huggingface demo

Installation

We highly recommend using Anaconda to manage your python environment. You can setup the required environment by the following commands:

# install dependencies
conda create -n primx python=3.9
conda install pytorch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 pytorch-cuda=11.8 -c pytorch -c nvidia
# requires xformer for efficient attention
conda install xformers::xformers
# install other dependencies
pip install -r requirements.txt
# compile third party libraries
bash install.sh
# Now, all done!

Pretrained Weights

Our pretrained weight can be downloaded from huggingface

For example, to download the singleview-conditioned model in fp16 precision for inference:

mkdir pretrained && cd pretrained
# download DiT
wget https://huggingface.co/FrozenBurning/3DTopia-XL/resolve/main/model_sview_dit_fp16.pt
# download VAE
wget https://huggingface.co/FrozenBurning/3DTopia-XL/resolve/main/model_vae_fp16.pt
cd ..

We will release the multiview-conditioned model and text-conditioned model in the near future!

Inference

Gradio Demo

The gradio demo will automatically download pretrained weights using huggingface_hub.

You could locally launch our demo with Gradio UI by:

python app.py

Alternatively, you can run the demo online

CLI Test

Run the following command for inference:

python inference.py ./configs/inference_dit.yml

Furthermore, you can modify the inference parameters in inference_dit.yml, detailed as follows:

Parameter	Recommended	Description
input_dir	-	The path of folder that stores all input images.
ddim	25, 50, 100	Total number of DDIM steps. Robust with more steps but fast with fewer steps.
cfg	4 - 7	The scale for Classifer-free Guidance (CFG).
seed	Any	Different seeds lead to diverse different results.
export_glb	True	Whether to export textured mesh in GLB format after DDIM sampling is over.
fast_unwrap	False	Whether to enable fast UV unwrapping algorithm.
decimate	100000	The max number of faces for mesh extraction.
mc_resolution	256	The resolution of the unit cube for marching cube.
remesh	False	Whether to run retopology after mesh extraction.

Training

We will release the training code and details in the future!

Acknowledgement

This work is built on many amazing research works and open-source projects, thanks all the authors for sharing!

• PrimDiffusion
• MVP
• DiT
• nvdiffrast
• kiuikit
• Trimesh
• litmodel3d