Search AI Products and News

HPC-AI Tech recently announced Open-Sora 2.0, a groundbreaking video AI system achieving commercial-grade quality at approximately one-tenth the typical training cost. This represents a potential paradigm shift in the resource-intensive field of video AI, mirroring efficiency gains seen in language models. While existing high-quality video generation systems like Movie Gen and Step-Video-T2V can cost millions of dollars to train, Open-Sora 2.0 offers a significantly more affordable alternative.

Heard of OpenAI's extravagant Sora? With training costs easily exceeding millions of dollars, it's like the Rolls-Royce of video generation. Now, LuChern Technology announces the open-sourcing of its video generation model, Open-Sora 2.0! For a mere $200,000 (equivalent to 224 GPUs), they successfully trained a commercial-grade video generation model with 11 billion parameters. Performance rivals OpenAI Sora. Don't let the low cost of Open-Sora 2.0 fool you...

Recently, the Lu Chen Open-Sora team achieved breakthrough progress in 720p HD video quality and generation speed. They not only made headlines with their advancements in 720p HD video quality and generation time but also open-sourced this technology, causing a sensation in the entire community!

Open-Sora has released a complete reproduction architecture scheme for Sora, which can reduce the reproduction cost by 46%. The model training input sequence length is extended to 819K patches, supporting dynamic resolution, various model structures, and multiple video compression methods. The performance improves by over 40% compared to the baseline scheme, while also reducing costs.