Paris 2.0: Video diffusion model trained on decentralized, heterogeneous GPUs

Researchers have developed Paris 2.0, the first video generation model pre-trained through decentralized computation across heterogeneous GPUs, eliminating the need for a monolithic cluster. The model achieved a 2x improvement in Frechet Video Distance over a centralized counterpart trained on the same data with an equivalent compute budget. This breakthrough closes the open problem of temporally coherent video generation under decentralized training, potentially democratizing access to advanced AI video generation.

Computer Science Computer Vision and Pattern Recognition Submitted on 25 May 2026 v1 https://arxiv.org/abs/2605.26064v1 , last revised 27 May 2026 this version, v2 Title:Paris 2.0: A Decentralized Diffusion Model for Video Generation View PDF /pdf/2605.26064 HTML experimental https://arxiv.org/html/2605.26064v2 Abstract: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. Submission history From: Marcos Villagra view email /show-email/b05cc136/2605.26064 Mon, 25 May 2026 17:27:22 UTC 2,417 KB v1 /abs/2605.26064v1 v2 Wed, 27 May 2026 11:28:25 UTC 3,047 KB References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .