helloworld-S commited on
Commit
50c5a98
·
verified ·
1 Parent(s): be7af3a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +41 -4
README.md CHANGED
@@ -8,10 +8,47 @@ tags:
8
  - personalization
9
  - multi-subject
10
  ---
11
- # XVerse
12
 
13
- Official model of "XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation".
14
 
15
- Paper Link: https://arxiv.org/abs/2506.21416
 
 
 
 
 
 
 
 
 
 
 
 
 
16
 
17
- Github Code: https://github.com/bytedance/XVerse
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  - personalization
9
  - multi-subject
10
  ---
11
+ # XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
12
 
13
+ This repository contains the official model of the paper [XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation](https://arxiv.org/abs/2506.21416).
14
 
15
+ <p align="center">
16
+ <a href="https://arxiv.org/abs/2506.21416">
17
+ <img alt="Build" src="https://img.shields.io/badge/arXiv%20paper-2506.21416-b31b1b.svg">
18
+ </a>
19
+ <a href="https://bytedance.github.io/XVerse/">
20
+ <img alt="Project Page" src="https://img.shields.io/badge/Project-Page-blue">
21
+ </a>
22
+ <a href="https://github.com/bytedance/XVerse">
23
+ <img alt="Github" src="https://img.shields.io/badge/GitHub-Code-darkgreen.svg?logo=github">
24
+ </a>
25
+ <a href="https://huggingface.co/ByteDance/XVerse">
26
+ <img alt="Build" src="https://img.shields.io/badge/🤗-HF%20Model-yellow">
27
+ </a>
28
+ </p>
29
 
30
+ ![XVerse's capability in single/multi-subject personalization and semantic attribute control (pose, style, lighting)](https://github.com/bytedance/XVerse/raw/main/sample/first_page.png)
31
+
32
+ ## Introduction
33
+
34
+ **XVerse** introduces a novel approach to multi-subject image synthesis, offering **precise and independent control over individual subjects** without disrupting the overall image latents or features. We achieve this by transforming reference images into offsets for token-specific text-stream modulation.
35
+
36
+ This innovation enables high-fidelity, editable image generation where you can robustly control both **individual subject characteristics** (identity) and their **semantic attributes**. XVerse significantly enhances capabilities for personalized and complex scene generation.
37
+
38
+ ## How to Use
39
+ see https://github.com/bytedance/XVerse
40
+
41
+ Where to send questions or comments about the model: https://github.com/bytedance/XVerse/issues
42
+
43
+ ## Citation
44
+ If XVerse is helpful, please help to ⭐ the repo.
45
+
46
+ If you find this project useful for your research, please consider citing our paper:
47
+ ```bibtex
48
+ @article{chen2025xverse,
49
+ title={XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation},
50
+ author={Chen, Bowen and Zhao, Mengyi and Sun, Haomiao and Chen, Li and Wang, Xu and Du, Kang and Wu, Xinglong},
51
+ journal={arXiv preprint arXiv:2506.21416},
52
+ year={2025}
53
+ }
54
+ ```