Fork of dgrauet/Hunyuan3D-2.1-mlx + our generate_e2e.py CLI, env-tunable remesh (HY3D_REMESH_FACES), and HARDWARE.md. Upstream training data (mini_trainset) and demo images stripped — inference needs none of it. Full upstream history: github.com/dgrauet/Hunyuan3D-2.1-mlx
46 lines
449 B
Plaintext
46 lines
449 B
Plaintext
ninja
|
|
pybind11
|
|
|
|
diffusers
|
|
einops
|
|
opencv-python
|
|
numpy
|
|
torch
|
|
transformers
|
|
torchvision
|
|
#taming-transformers-rom1504
|
|
#ConfigArgParse
|
|
#ipdb
|
|
omegaconf
|
|
|
|
#sentencepiece
|
|
tqdm
|
|
|
|
# Mesh Processing
|
|
trimesh
|
|
pymeshlab
|
|
pygltflib
|
|
xatlas
|
|
#kornia
|
|
#facexlib
|
|
|
|
# Training
|
|
accelerate
|
|
#pytorch_lightning
|
|
#scikit-learn
|
|
#scikit-image
|
|
|
|
# Demo only
|
|
gradio
|
|
fastapi
|
|
uvicorn
|
|
rembg
|
|
onnxruntime
|
|
#gevent
|
|
#geventhttpclient
|
|
|
|
# MLX port
|
|
mlx>=0.31.0
|
|
mlx-arsenal>=0.2.1
|
|
safetensors
|
|
Pillow |