ashawkey commited on
Commit
348168f
1 Parent(s): cb46597

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -1
README.md CHANGED
@@ -3,10 +3,44 @@ license: mit
3
  pipeline_tag: text-to-3d
4
  tags:
5
  - image-to-3d
 
6
  ---
7
 
8
  # LGM
9
 
10
  This model contains the pretrained weights for *LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation*.
11
 
12
- [Project Page](https://me.kiui.moe/lgm/) | [Arxiv](https://arxiv.org/abs/2402.05054)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  pipeline_tag: text-to-3d
4
  tags:
5
  - image-to-3d
6
+ - text-to-3d
7
  ---
8
 
9
  # LGM
10
 
11
  This model contains the pretrained weights for *LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation*.
12
 
13
+ ### [Project Page](https://me.kiui.moe/lgm/) | [Arxiv](https://arxiv.org/abs/2402.05054) | [Weights](https://huggingface.co/ashawkey/LGM)
14
+
15
+
16
+ ## Introduction
17
+ LGM can generate 3D objects from image or text within 5 seconds at high-resolution based on Gaussian Splatting.
18
+
19
+ <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/63367f9a9895307563659be6/9CVJZ5ZXkhheDPKl3M0pM.mp4"></video>
20
+
21
+ <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/63367f9a9895307563659be6/6DM_hNEDLRJOz95pgVjek.mp4"></video>
22
+
23
+
24
+ ## Model Details
25
+ The model is trained on a ~80K subset of [Objaverse](https://huggingface.co/datasets/allenai/objaverse).
26
+ For more details, please refer to our paper.
27
+
28
+ ## Usage
29
+
30
+ To download the model:
31
+ ```python
32
+ from huggingface_hub import hf_hub_download
33
+ ckpt_path = hf_hub_download(repo_id="ashawkey/LGM", filename="model_fp16.safetensors")
34
+ ```
35
+ Please refer to our [repo](https://github.com/3DTopia/LGM) for more details on loading and inference.
36
+
37
+ ## Citation
38
+
39
+ ```
40
+ @article{tang2024lgm,
41
+ title={LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation},
42
+ author={Tang, Jiaxiang and Chen, Zhaoxi and Chen, Xiaokang and Wang, Tengfei and Zeng, Gang and Liu, Ziwei},
43
+ journal={arXiv preprint arXiv:2402.05054},
44
+ year={2024}
45
+ }
46
+ ```