For a quick start, try the huggingface gradio demo
here
.
Download models
We provide the pretrained diffusion models for chair, vase, table, basket, flower and dandelion. You can download them from
model card
and put them in
./pretrained_models/
.
Alternatively, the inference script will automatically download the pretrained models for you.
This script processes all the chair images in the
./examples/chair
folder and saves the generated 3D models and their rendered images in
./logs
.
To generate other categories, use the corresponding YAML config file such as
vase_demo.yaml
. Currently we supprt
chair
,
table
,
vase
,
basket
,
flower
and
dandelion
generators developped by
Infinigen
.
We train a diffusion model for each procedural generator. The training data is generated by randomly sampling the PCG and render multi-view images. To prepare the training data, run:
Replace
ChairFactory
with other category options as detailed in the
./scripts/prepare_data.py
file. This script also conducts offline augmentation and saves the extracted DINOv2 features for each image, which may consume a lot of disk storage. You can adjust the number of the generated data and the render configurations accordingly.
After generating the training data, start the training by:
DI-PCG is general for any procedural generator. To train a diffusion model for your PCG, you need to implement the
get_params_dict
,
update_params
,
spawn_assets
,
finalize_assets
functions and place your PCG in
./core/assets/
. Also change the
num_params
in your training YAML config file.
If you have any question, feel free to open an issue or contact us.
Citation
If you find our work useful for your research or applications, please cite using this BibTeX:
@article{zhao2024dipcg,
title={DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation},
author={Zhao, Wang and Cao, Yanpei and Xu, Jiale and Dong, Yuejiang and Shan, Ying},
journal={arXiv preprint arxiv:2412.15200},
year={2024}
}
🤗 Acknowledgements
DI-PCG is built on top of some awesome open-source projects:
Infinigen
,
Fast-DiT
. We sincerely thank them all.
Runs of TencentARC DI-PCG on huggingface.co
0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About DI-PCG huggingface.co Model
DI-PCG huggingface.co
DI-PCG huggingface.co is an AI model on huggingface.co that provides DI-PCG's model effect (), which can be used instantly with this TencentARC DI-PCG model. huggingface.co supports a free trial of the DI-PCG model, and also provides paid use of the DI-PCG. Support call DI-PCG model through api, including Node.js, Python, http.
DI-PCG huggingface.co is an online trial and call api platform, which integrates DI-PCG's modeling effects, including api services, and provides a free online trial of DI-PCG, you can try DI-PCG online for free by clicking the link below.
TencentARC DI-PCG online free url in huggingface.co:
DI-PCG is an open source model from GitHub that offers a free installation service, and any user can find DI-PCG on GitHub to install. At the same time, huggingface.co provides the effect of DI-PCG install, users can directly use DI-PCG installed effect in huggingface.co for debugging and trial. It also supports api for free installation.