Sandeep Mishra✝︎, Oindrila Saha✝︎, Alan C. Bovik
Accepted at NeurIPS 2024
YouDream introduces a novel approach for generating 3D animal models with anatomically accurate control, ensuring consistency and detail across generated outputs. This work combines text-to-3D generation with precise anatomical structures to cater to tasks requiring high-quality 3D assets in research and industry.
- Release codebase
- Release a detailed documentation
- Release more Animal Prior configurations
- Release Pose Editor (manual pose editing -- suitable for pose-refinement and unseen animal generation)
- Release GPT-pose-editor (automatic pose editing -- suitable for known animals)
- Clone the repository:
git clone https://github.com/YouDream3D/YouDream.git cd YouDream
- Create and activate the conda environment:
conda create -n youdream python=3.9 -y conda activate youdream
- Install dependencies:
conda install pytorch=1.13.0 torchvision pytorch-cuda=11.6 -c pytorch -c nvidia conda install -c iopath iopath conda install pytorch3d -c pytorch3d pip3 install -r requirements.txt
- Download the Animal Pose ControlNet Checkpoint: Visit the Hugging Face model page to download the animal_pose_controlnet checkpoint. Place the downloaded checkpoint folder: "animal_pose_controlnet" in the root directory of YouDream.
- Run the shell scripts to generate 3D models:
./run_all_tiger.sh
If you find this work useful in your research or projects, please cite:
@article{mishra2024youdream,
title={YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals},
author={Mishra, Sandeep and Saha, Oindrila and Bovik, Alan C},
journal={arXiv preprint arXiv:2406.16273},
year={2024}
}
Our Code is based on DreamWaltz. We thank the DreamWaltz contributors for making the code available.
✝︎ Equal contribution.