R4Z0R1337 commited on
Commit
09af026
·
verified ·
1 Parent(s): 16812a5

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +9 -8
app.py CHANGED
@@ -244,23 +244,24 @@ def make3d(images):
244
 
245
 
246
  _HEADER_ = '''
247
- <h2><b>Official 🤗 Gradio Demo</b></h2><h2><a href='https://github.com/TencentARC/InstantMesh' target='_blank'><b>InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models</b></a></h2>
 
248
 
249
- **InstantMesh** is a feed-forward framework for efficient 3D mesh generation from a single image based on the LRM/Instant3D architecture.
250
 
251
- Code: <a href='https://github.com/TencentARC/InstantMesh' target='_blank'>GitHub</a>. Techenical report: <a href='https://arxiv.org/abs/2404.07191' target='_blank'>ArXiv</a>.
252
 
253
- ❗️❗️❗️**Important Notes:**
254
- - Our demo can export a .obj mesh with vertex colors or a .glb mesh now. If you prefer to export a .obj mesh with a **texture map**, please refer to our <a href='https://github.com/TencentARC/InstantMesh?tab=readme-ov-file#running-with-command-line' target='_blank'>Github Repo</a>.
255
- - The 3D mesh generation results highly depend on the quality of generated multi-view images. Please try a different **seed value** if the result is unsatisfying (Default: 42).
256
  '''
257
 
258
  _CITE_ = r"""
259
- If InstantMesh is helpful, please help to ⭐ the <a href='https://github.com/TencentARC/InstantMesh' target='_blank'>Github Repo</a>. Thanks! [![GitHub Stars](https://img.shields.io/github/stars/TencentARC/InstantMesh?style=social)](https://github.com/TencentARC/InstantMesh)
260
  ---
261
  📝 **Citation**
262
 
263
- If you find our work useful for your research or applications, please cite using this bibtex:
264
  ```bibtex
265
  @article{xu2024instantmesh,
266
  title={InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models},
 
244
 
245
 
246
  _HEADER_ = '''
247
+ <h2><b>Welcome to 3DFusion!</b></h2>
248
+ <h2><a href='https://github.com/TencentARC/InstantMesh' target='_blank'><b>3D Mesh Generation from Single Images with 3DFusion</b></a></h2>
249
 
250
+ 3DFusion is a cutting-edge, efficient 3D mesh generation tool based on the powerful LRM/Instant3D architecture.
251
 
252
+ Code and Original Framework: <a href='https://github.com/TencentARC/InstantMesh' target='_blank'>InstantMesh GitHub</a>. Technical report: <a href='https://arxiv.org/abs/2404.07191' target='_blank'>ArXiv</a>.
253
 
254
+ ❗️**Important Notes:**
255
+ - This demo exports both `.obj` and `.glb` meshes, including vertex colors.
256
+ - The 3D mesh generation depends on the quality of generated multi-view images, so try different seed values (default: 42) for optimal results.
257
  '''
258
 
259
  _CITE_ = r"""
260
+ If you find **3DFusion** helpful, please give ato the original <a href='https://github.com/TencentARC/InstantMesh' target='_blank'>InstantMesh repository</a>. We appreciate the work of the TencentARC team! [![GitHub Stars](https://img.shields.io/github/stars/TencentARC/InstantMesh?style=social)](https://github.com/TencentARC/InstantMesh)
261
  ---
262
  📝 **Citation**
263
 
264
+ If you use this work for research or applications, cite it as follows:
265
  ```bibtex
266
  @article{xu2024instantmesh,
267
  title={InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models},