dearsky/Magic123
1
0
Fork 0
Code Issues 6 Pull Requests Actions Packages Projects Releases Wiki Activity

add abaltion study

Browse Source
This commit is contained in:
Guocheng Qian
2023-08-04 13:07:21 -07:00
parent c883050bd1
commit 4ad512ad41
2 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
docs/static/2d_3d.png vendored Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.5 MiB

4
readme.md
View File

@@ -20,6 +20,10 @@ Compare Magic123 without textual inversion with abaltions using only 2D prior (S
https://github.com/guochengqian/Magic123/assets/48788073/e5a3c3cb-bcb1-4b10-8bfb-2c2eb79a9289 https://github.com/guochengqian/Magic123/assets/48788073/e5a3c3cb-bcb1-4b10-8bfb-2c2eb79a9289
Effects of Joint Prior. Increasing the strength of 2D prior leads to more imagination, more details, and less 3D consistencies.
<img src="docs/static/2d_3d.png" width="800" />
Official PyTorch Implementation of Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors. Code is built upon [Stable-DreamFusion](https://github.com/ashawkey/stable-dreamfusion) repo. Official PyTorch Implementation of Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors. Code is built upon [Stable-DreamFusion](https://github.com/ashawkey/stable-dreamfusion) repo.