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

Update readme.md

Browse Source
This commit is contained in:
Gordon Guocheng Qian 钱国成
2023-08-22 13:48:40 -07:00
committed by GitHub
parent 2273ba7b26
commit 03471a99b3
1 changed files with 8 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
readme.md
View File

@@ -17,13 +17,20 @@ Training convergence of a demo example:
Compare Magic123 without textual inversion with abaltions using only 2D prior (SDS) or using only 3D prior (Zero123): Compare Magic123 without textual inversion with abaltions using only 2D prior (SDS) or using only 3D prior (Zero123):
https://github.com/guochengqian/Magic123/assets/48788073/e5a3c3cb-bcb1-4b10-8bfb-2c2eb79a9289
https://github.com/guochengqian/Magic123/assets/48788073/c91f4c81-8c2c-4f84-8ce1-420c12f7e886
Effects of Joint Prior. Increasing the strength of 2D prior leads to more imagination, more details, and less 3D consistencies. 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" /> <img src="docs/static/2d_3d.png" width="800" />
https://github.com/guochengqian/Magic123/assets/48788073/98cb4dd7-7bf3-4179-9b6d-e8b47d928a68
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.