1h ago

Creator bidhan releases Paris 2.0, a decentralized video model that beats monolithic training by 2x on FVD

ByteDance also open-sourced BAGEL, a 7B multimodal model.

0
Original post

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 model trained on the same data and compute budget, and Paris 2.0 outperformed the monolithic by ~2x on FVD benchmark.

9:59 AM · May 28, 2026 View on X
Reposted by

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

bidhanbidhan@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 model trained on the same data and compute budget, and Paris 2.0 outperformed the monolithic by ~2x on FVD benchmark.

4:59 PM · May 28, 2026 · 41.3K Views
5:26 PM · May 28, 2026 · 8.3K Views
Creator bidhan releases Paris 2.0, a decentralized video model that beats monolithic training by 2x on FVD · Digg