# 字节跳动开源7B多模态模型BAGEL

- 来源：Chubby♨️ (@kimmonismus)
- 发布时间：2026-05-29 01:26
- AIHOT 分数：66
- AIHOT 链接：https://aihot.virxact.com/items/cmpps9gk600qcslm6djqg1zif
- 原文链接：https://x.com/kimmonismus/status/2060050186076815792

## AI 摘要

字节跳动开源多模态模型BAGEL，单一7B参数模型即可执行图像生成、编辑、风格转换与视觉理解，采用Apache 2.0许可。引用推文显示，该公司此前已发布首个去中心化训练的视频生成模型Paris 2.0，其在FVD基准上性能约为同等数据与算力单体模型的2倍。

## 正文

ByteDance just open-sourced one of the most capable multimodal models out there.

BAGEL does image generation， editing， style transfer， and visual understanding - all in a single 7B parameter model. Apache 2.0 licensed！

One model. No switching between specialized tools.
Amazing

### 引用推文

> bidhan：We're releasing Paris 2.0, which, to our knowledge, is the world's first decentralized trained video generation model. We benchmarked it against a monolithic mo...