{"slug": "paris-2-0-video-diffusion-model-trained-on-decentralized-heterogeneous-gpus", "title": "Paris 2.0: Video diffusion model trained on decentralized, heterogeneous GPUs", "summary": "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.", "body_md": "# Computer Science > Computer Vision and Pattern Recognition\n\n[Submitted on 25 May 2026 (\n\n[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\n\n[View PDF](/pdf/2605.26064)\n\n[HTML (experimental)](https://arxiv.org/html/2605.26064v2)\n\nAbstract: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.\n\nIn 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.\n\n## Submission history\n\nFrom: Marcos Villagra [[view email](/show-email/b05cc136/2605.26064)]\n\n**Mon, 25 May 2026 17:27:22 UTC (2,417 KB)**\n\n[[v1]](/abs/2605.26064v1)**[v2]** Wed, 27 May 2026 11:28:25 UTC (3,047 KB)\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/paris-2-0-video-diffusion-model-trained-on-decentralized-heterogeneous-gpus", "canonical_source": "https://arxiv.org/abs/2605.26064", "published_at": "2026-05-28 18:09:57+00:00", "updated_at": "2026-05-28 18:34:22.034892+00:00", "lang": "en", "topics": ["generative-ai", "computer-vision", "artificial-intelligence", "machine-learning", "ai-research"], "entities": ["Paris 2.0", "Paris 1.0", "Marcos Villagra", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/paris-2-0-video-diffusion-model-trained-on-decentralized-heterogeneous-gpus", "markdown": "https://wpnews.pro/news/paris-2-0-video-diffusion-model-trained-on-decentralized-heterogeneous-gpus.md", "text": "https://wpnews.pro/news/paris-2-0-video-diffusion-model-trained-on-decentralized-heterogeneous-gpus.txt", "jsonld": "https://wpnews.pro/news/paris-2-0-video-diffusion-model-trained-on-decentralized-heterogeneous-gpus.jsonld"}}