Hugging Face's logo

TrNi
/
efficient-cube3d

Text-to-3D
torchao
3d-generation
quantized
int4
rtn
Model card Files
xet
 Community
TrNi commited on
Commit
eeadb19
·
verified ·
1 Parent(s): 3608761

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -13,7 +13,7 @@ library_name: torchao
13
  pipeline_tag: text-to-3d
14
  ---
15
 
16
- ## 🚀 First INT4 Quantized Cube3D — Run on Half the VRAM
17
 
18
  ![](https://img.shields.io/badge/VRAM_-14.3_GB_(44%25↓)-brightgreen)
19
  ![](https://img.shields.io/badge/Loading-88%25_faster-blue)
@@ -29,6 +29,11 @@ Presenting the **first INT4 quantized version** of [Cube3D v0.5](https://hugging
29
 
30
  > 💡 The 44% VRAM reduction means this model now fits on a single 16 GB GPU (e.g. NVIDIA L4, A10 etc.), bringing high-quality text-to-3D generation to individual researchers and end-user hardware.
31
 
 
 
 
 
 
32
  # Cube3D v0.5 — RTN W4A16 INT4 (torchao)
33
 
34
  Post-training quantized version of [Roblox/cube3d-v0.5](https://huggingface.co/Roblox/cube3d-v0.5), a text-to-3D mesh generative model.
 
13
  pipeline_tag: text-to-3d
14
  ---
15
 
16
+ # 🚀 First INT4 Quantized Cube3D — Run on Half the VRAM
17
 
18
  ![](https://img.shields.io/badge/VRAM_-14.3_GB_(44%25↓)-brightgreen)
19
  ![](https://img.shields.io/badge/Loading-88%25_faster-blue)
 
29
 
30
  > 💡 The 44% VRAM reduction means this model now fits on a single 16 GB GPU (e.g. NVIDIA L4, A10 etc.), bringing high-quality text-to-3D generation to individual researchers and end-user hardware.
31
 
32
+ ![Easy categories](assets/easy.gif)
33
+ ![Medium categories](assets/medium.gif)
34
+ ![Complex categories](assets/complex.gif)
35
+
36
+
37
  # Cube3D v0.5 — RTN W4A16 INT4 (torchao)
38
 
39
  Post-training quantized version of [Roblox/cube3d-v0.5](https://huggingface.co/Roblox/cube3d-v0.5), a text-to-3D mesh generative model.