---
title: XVerse
canonical_url: "https://www.modelscope.cn/models/bytedance-community/XVerse"
md_url: "https://www.modelscope.cn/models/bytedance-community/XVerse.md"
repository: bytedance-community/XVerse
last_updated: 2026-06-05
license: apache-2.0
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - black-forest-labs/FLUX.1-dev
base_model_relation: adapter
parameters: 1.5B
tensor_type:
  - BF16
library_name:
  - lora
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - pytorch
downloads: 10
stars: 0
tags:
  - LoRA
  - personalization
  - multi-subject
---

# XVerse

> XVerse - bytedance-community 在 ModelScope 开源的模型。XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation

bytedance-community/XVerse 是 ModelScope 魔搭社区上的 1.5B 参数text-to-image-synthesis模型，采用 apache-2.0 许可，基于 black-forest-labs/FLUX.1-dev 构建。

- **Repository**: bytedance-community/XVerse
- **License**: apache-2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 1.5B
- **Base model**: black-forest-labs/FLUX.1-dev
- **Tags**: LoRA, personalization, multi-subject
- **Downloads**: 10
- **Stars**: 0
- **Last updated**: 2026-06-05

Source: https://www.modelscope.cn/models/bytedance-community/XVerse

---

# XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation

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).

<p align="center">
    <a href="https://arxiv.org/abs/2506.21416">
            <img alt="Build" src="https://img.shields.io/badge/arXiv%20paper-2506.21416-b31b1b.svg">
    </a>
    <a href="https://bytedance.github.io/XVerse/">
        <img alt="Project Page" src="https://img.shields.io/badge/Project-Page-blue">
    </a>
    <a href="https://github.com/bytedance/XVerse">
        <img alt="Github" src="https://img.shields.io/badge/GitHub-Code-darkgreen.svg?logo=github">
    </a>
    <a href="https://huggingface.co/ByteDance/XVerse">
        <img alt="Build" src="https://img.shields.io/badge/🤗-HF%20Model-yellow">
    </a>    
</p>

![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)

## Introduction

**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.

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.

## How to Use
see https://github.com/bytedance/XVerse

Where to send questions or comments about the model: https://github.com/bytedance/XVerse/issues

## Citation
If XVerse is helpful, please help to ⭐ the repo.

If you find this project useful for your research, please consider citing our paper:
```bibtex
@article{chen2025xverse,
  title={XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation},
  author={Chen, Bowen and Zhao, Mengyi and Sun, Haomiao and Chen, Li and Wang, Xu and Du, Kang and Wu, Xinglong},
  journal={arXiv preprint arXiv:2506.21416},
  year={2025}
}
```