Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
|
|
@@ -31,6 +32,7 @@ Install:
|
|
| 31 |
pip install git+https://github.com/MarcusLoppe/meshgpt-pytorch.git
|
| 32 |
```
|
| 33 |
```
|
|
|
|
| 34 |
from meshgpt_pytorch import (
|
| 35 |
MeshAutoencoder,
|
| 36 |
MeshTransformer,
|
|
@@ -38,7 +40,7 @@ from meshgpt_pytorch import (
|
|
| 38 |
)
|
| 39 |
|
| 40 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 41 |
-
transformer = MeshTransformer.from_pretrained("MarcusLoren/
|
| 42 |
|
| 43 |
output = []
|
| 44 |
output.append((transformer.generate(texts = ['sofa','bed', 'computer screen', 'bench', 'chair', 'table' ] , temperature = 0.0) ))
|
|
@@ -79,4 +81,4 @@ The tokens generated by the transformer can then be converted into 3D mesh using
|
|
| 79 |
The idea for MeshGPT came from the paper ( https://arxiv.org/abs/2311.15475 ) but the creators didn't release any code or model.
|
| 80 |
Phil Wang (https://github.com/lucidrains) drew inspiration from the paper and did a ton of improvements over the papers implementation and created the repo : https://github.com/lucidrains/meshgpt-pytorch
|
| 81 |
My goal has been to figure out how to train and implement MeshGPT into reality. <br/>
|
| 82 |
-
See my github repo for a notebook on how to get started training your own MeshGPT! [MarcusLoppe/meshgpt-pytorch](https://github.com/MarcusLoppe/meshgpt-pytorch/)
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
pipeline_tag: text-to-3d
|
| 4 |
---
|
| 5 |
|
| 6 |
|
|
|
|
| 32 |
pip install git+https://github.com/MarcusLoppe/meshgpt-pytorch.git
|
| 33 |
```
|
| 34 |
```
|
| 35 |
+
import torch
|
| 36 |
from meshgpt_pytorch import (
|
| 37 |
MeshAutoencoder,
|
| 38 |
MeshTransformer,
|
|
|
|
| 40 |
)
|
| 41 |
|
| 42 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 43 |
+
transformer = MeshTransformer.from_pretrained("MarcusLoren/MeshGPT-preview").to(device)
|
| 44 |
|
| 45 |
output = []
|
| 46 |
output.append((transformer.generate(texts = ['sofa','bed', 'computer screen', 'bench', 'chair', 'table' ] , temperature = 0.0) ))
|
|
|
|
| 81 |
The idea for MeshGPT came from the paper ( https://arxiv.org/abs/2311.15475 ) but the creators didn't release any code or model.
|
| 82 |
Phil Wang (https://github.com/lucidrains) drew inspiration from the paper and did a ton of improvements over the papers implementation and created the repo : https://github.com/lucidrains/meshgpt-pytorch
|
| 83 |
My goal has been to figure out how to train and implement MeshGPT into reality. <br/>
|
| 84 |
+
See my github repo for a notebook on how to get started training your own MeshGPT! [MarcusLoppe/meshgpt-pytorch](https://github.com/MarcusLoppe/meshgpt-pytorch/)
|