Commit
•
405c047
1
Parent(s):
54ff45b
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,9 @@ license: apache-2.0
|
|
| 3 |
pipeline_tag: text-to-3d
|
| 4 |
---
|
| 5 |
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
### MeshGPT-alpha-preview
|
| 8 |
|
|
@@ -10,6 +13,8 @@ MeshGPT is a text-to-3D model based on an autoencoder (tokenizer) and a transfor
|
|
| 10 |
The autoencoder's purpose is to be able to translate 3D models into tokens which then the decoder part of it can convert back to 3D mesh.<br/>
|
| 11 |
For all purposes and definitions the autoencoder is the **world first** published **3D model tokenizer**! (correct me if i'm wrong!)
|
| 12 |
|
|
|
|
|
|
|
| 13 |
## Model Details
|
| 14 |
The autoencoder (tokenizer) is a relative small model using 50M parameters and the transformer model uses 184M parameters and the core is based on GPT2-small.
|
| 15 |
Due to hardware contraints it's trained using a codebook/vocabablity size of 2048.<br/>
|
|
|
|
| 3 |
pipeline_tag: text-to-3d
|
| 4 |
---
|
| 5 |
|
| 6 |
+
<p style="text-align: center;">
|
| 7 |
+
<a href="https://huggingface.co/spaces/MarcusLoren/MeshGPT" style="font-size: 24px; font-weight: 600;">DEMO</a>
|
| 8 |
+
</p>
|
| 9 |
|
| 10 |
### MeshGPT-alpha-preview
|
| 11 |
|
|
|
|
| 13 |
The autoencoder's purpose is to be able to translate 3D models into tokens which then the decoder part of it can convert back to 3D mesh.<br/>
|
| 14 |
For all purposes and definitions the autoencoder is the **world first** published **3D model tokenizer**! (correct me if i'm wrong!)
|
| 15 |
|
| 16 |
+
|
| 17 |
+
|
| 18 |
## Model Details
|
| 19 |
The autoencoder (tokenizer) is a relative small model using 50M parameters and the transformer model uses 184M parameters and the core is based on GPT2-small.
|
| 20 |
Due to hardware contraints it's trained using a codebook/vocabablity size of 2048.<br/>
|