%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Recently, Lucheng Technology's self-developed Open-Sora 2.0 video generation model has been included in the "State of AI Report 2025," one of the most influential annual summaries of artificial intelligence globally. This report highlights significant breakthroughs in research, industry, and society over the past year. The inclusion of this model is not only a recognition of Lucheng Technology's efforts in the field of video generation but also indicates that its achievements are receiving widespread attention from the global AI community.
Open-Sora is an open-source video generation model launched by Lucheng Technology, which combines its powerful training framework Colossal-AI. It has gained significant recognition in the open-source community and academic circles, with approximately 70,000 GitHub stars and ranking first globally in its field. More than 500 papers have cited this model.
In terms of distributed training, Lucheng Technology has successfully reduced checkpoint disk writing time by 97% and lowered overall computing costs by about 90% through optimized training methods and architectures. This achievement enables academic research to be smoothly transformed into practical engineering projects, promoting the commercial application of technology.
Additionally, the ecosystem applications of Open-Sora have attracted widespread attention, with the community's activity and influence continuously increasing. Many individual developers and teams, such as LambdaLabs, have rapidly fine-tuned the Open-Sora model to create various style generation models, including LEGO-style animated videos.
The LAMB technology of Lucheng Technology's team has also brought fast and accurate training results for Snapchat's Snap Video team, and helped the Meta team train the MobileNet-V3 model with the highest global downloads on Hugging Face.
Open-Sora is working together with Lucheng Technology's product Video Ocean to integrate video generation capabilities into the actual production processes of more creators and enterprises, continuously defining new benchmarks for the next generation of AI video in terms of speed and quality. Lucheng Technology thanks everyone who has paid attention to, supported, and contributed to the Open-Sora model and the Video Ocean platform, and looks forward to continuing to work together in the future of AI video generation.
For more information, please visit the Video Ocean official website: https://video.luchentech.com/, and the reference link: https://www.stateof.ai.
Key Points:
🌟 Open-Sora 2.0 has been included in the "2025 AI Report," reflecting its important position in the field of video generation.
🚀 The model has received approximately 70,000 GitHub stars, ranks first globally, and has been cited by more than 500 papers.
🤝 Lucheng Technology has significantly reduced computing costs through optimized training methods, promoting the practical application of technology.