Instructions to use manycore-research/SpatialGen-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use manycore-research/SpatialGen-1.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("manycore-research/SpatialGen-1.0", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
PyTorch3D fails to install on Python 3.10 (requires manual source build)
#3
by nikitavovch - opened
In the project’s requirements.txt, pytorch3d is listed as a dependency.
However, when setting up the environment with Python 3.10, PyTorch 2.3.1, and CUDA 12.1 (the same setup used in your test environment), the installation of pytorch3d fails with the following error:
ERROR: Ignored the following versions that require a different python version:
2.3.0 Requires-Python >=3.11;
2.3.1 Requires-Python >=3.11;
2.3.2 Requires-Python >=3.11;
2.3.3 Requires-Python >=3.11;
2.3.4 Requires-Python >=3.11
ERROR: Could not find a version that satisfies the requirement pytorch3d (from versions: none)
ERROR: No matching distribution found for pytorch3d
Workaround
To make the installation succeed on Python 3.10, it’s necessary to install PyTorch3D from source manually:pip install "git+https://github.com/facebookresearch/pytorch3d.git@stable"