Tencent Hunyuan3D-1 - Install Locally - 3D Generation AI Model from Text

 This video shows how to locally install Tencent Hunyuan3D-1 model for 3D generation.

Code:

conda create -n ai python=3.9 -y && conda activate ai

conda remove cuda-compiler

conda install gcc_linux-64=11.2.0 gxx_linux-64=11.2.0 -y

conda install cuda=11.8 -c nvidia -y

conda install pytorch=2.0.1 torchvision==0.15.2 pytorch-cuda=11.8 -c pytorch -c nvidia -y

conda install -c iopath iopath -y

conda install -c bottler nvidiacub -y

conda install pytorch3d -c pytorch3d -y

conda install anaconda::cmake -y

conda install conda-forge::lit-nlp -y

conda install anaconda::numpy=1.23.5 -y

git clone https://github.com/tencent/Hunyuan3D-1 && cd Hunyuan3D-1

#From below remove, pytorch3 from env_install.sh file.

chmod a+x env_install.sh

./env_install.sh

pip install huggingface_hub

huggingface-cli login  

mkdir weights

huggingface-cli download tencent/Hunyuan3D-1 --local-dir ./weights

mkdir weights/hunyuanDiT

huggingface-cli download Tencent-Hunyuan/HunyuanDiT-v1.1-Diffusers-Distilled --local-dir ./weights/hunyuanDiT

python3 main.py --text_prompt "a lovely rabbit" --save_folder ./outputs/test/ --max_faces_num 90000 --do_texture_mapping --do_render

python3 main.py --image_prompt "/home/Ubuntu/images/komodo.png" --save_folder ./outputs/test/ --max_faces_num 90000 --do_texture_mapping --do_render