Add pipeline tag

#1
by nielsr HF staff - opened
Files changed (1) hide show
  1. README.md +52 -51
README.md CHANGED
@@ -1,52 +1,53 @@
1
- ---
2
- license: apache-2.0
3
- language:
4
- - en
5
- tags:
6
- - Diffusion Transformer
7
- - Image Editing
8
- - Scepter
9
- - ACE
10
- ---
11
- <h2 align="center">
12
- ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer
13
- </h2>
14
-
15
- <h3 align="center">
16
- <b>Tongyi Lab, Alibaba Group</b>
17
- </h3>
18
-
19
- <div align="center">
20
-
21
- [**Paper**](https://arxiv.org/abs/2410.00086) **|** [**Project Page**](https://ali-vilab.github.io/ace-page/) **|** [**Code**](https://github.com/ali-vilab/ACE)
22
-
23
- </div>
24
-
25
-
26
- ACE is a unified foundational model framework that supports a wide range of visual generation tasks.
27
- By defining CU for unifying multi-modal inputs across different tasks and incorporating long-context CU,
28
- we introduce historical contextual information into visual generation tasks, paving
29
- the way for ChatGPT-like dialog systems in visual generation.
30
-
31
- <p>
32
- <table align="center">
33
- <tr>
34
- <td>
35
- <img src="assets/figures/teaser.png">
36
- </td>
37
- </tr>
38
- </table>
39
- </p>
40
-
41
-
42
-
43
- ## BibTeX
44
-
45
- ```bibtex
46
- @article{han2024ace,
47
- title={ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer},
48
- author={Han, Zhen and Jiang, Zeyinzi and Pan, Yulin and Zhang, Jingfeng and Mao, Chaojie and Xie, Chenwei and Liu, Yu and Zhou, Jingren},
49
- journal={arXiv preprint arXiv:2410.00086},
50
- year={2024}
51
- }
 
52
  ```
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ pipeline_tag: image-to-image
6
+ tags:
7
+ - Diffusion Transformer
8
+ - Image Editing
9
+ - Scepter
10
+ - ACE
11
+ ---
12
+ <h2 align="center">
13
+ ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer
14
+ </h2>
15
+
16
+ <h3 align="center">
17
+ <b>Tongyi Lab, Alibaba Group</b>
18
+ </h3>
19
+
20
+ <div align="center">
21
+
22
+ [**Paper**](https://arxiv.org/abs/2410.00086) **|** [**Project Page**](https://ali-vilab.github.io/ace-page/) **|** [**Code**](https://github.com/ali-vilab/ACE)
23
+
24
+ </div>
25
+
26
+
27
+ ACE is a unified foundational model framework that supports a wide range of visual generation tasks.
28
+ By defining CU for unifying multi-modal inputs across different tasks and incorporating long-context CU,
29
+ we introduce historical contextual information into visual generation tasks, paving
30
+ the way for ChatGPT-like dialog systems in visual generation.
31
+
32
+ <p>
33
+ <table align="center">
34
+ <tr>
35
+ <td>
36
+ <img src="assets/figures/teaser.png">
37
+ </td>
38
+ </tr>
39
+ </table>
40
+ </p>
41
+
42
+
43
+
44
+ ## BibTeX
45
+
46
+ ```bibtex
47
+ @article{han2024ace,
48
+ title={ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer},
49
+ author={Han, Zhen and Jiang, Zeyinzi and Pan, Yulin and Zhang, Jingfeng and Mao, Chaojie and Xie, Chenwei and Liu, Yu and Zhou, Jingren},
50
+ journal={arXiv preprint arXiv:2410.00086},
51
+ year={2024}
52
+ }
53
  ```