# Paris 2.0: A Decentralized Diffusion Model for Video Generation

arXiv: https://arxiv.org/abs/2605.26064 · HTML: https://mlsanity.com/paper/2605.26064/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 8 of its 9 references that are in the map.
- First posted on arXiv 25 May 2026.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 8 of 8)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [Decentralized Diffusion Models](https://mlsanity.com/paper/2501.05450/) (2025)
- [Paris: A Decentralized Trained Open-Weight Diffusion Model](https://mlsanity.com/paper/2510.03434/) (2025)
- [Expert-Data Alignment Governs Generation Quality in Decentralized Diffusion Models](https://mlsanity.com/paper/2602.02685/) (2026)
- [Heterogeneous Decentralized Diffusion Models](https://mlsanity.com/paper/2603.06741/) (2026)

## Built on by (most cited first, 1 of 1)

- [WorldDiT: A Unified Diffusion Architecture for World and Action Modeling](https://mlsanity.com/paper/2607.23909/) (2026)

## Abstract (arXiv)

We present Paris 2.0, the first video generation model pre-trained through decentralized computation. Its training recipe builds upon Paris 1.0 (arXiv:2510.03434), the first ever open-weight Decentralized Diffusion Model (DDM), which showed that image generation can be trained without a monolithic GPU cluster. However, temporally coherent video generation had remained an open problem under decentralized training, and Paris 2.0 closes it. In low-resolution text-to-video training, against a monolithic model trained on the same data under a matched total compute budget, Paris 2.0 cuts Frechet Video Distance (FVD) from 561.04 to 279.01, a ~2.0x improvement, and lifts CLIP text-video similarity and aesthetic score.