BestHub
Sign in
AI Frontier Lectures
AI Frontier Lectures
Mar 14, 2025 · Artificial Intelligence

Open-Sora 2.0: How an 11B Open-Source Model Beats Closed-Source Video AI at 720p

Open‑Sora 2.0, an open‑source 11‑billion‑parameter video generation model, delivers 720p 24 fps videos with visual quality and text‑image alignment comparable to proprietary systems like HunyuanVideo and Step‑Video, while cutting training costs to $200 k using only 224 GPUs, and the release includes full code, weights, and a Gradio demo.

3D autoencoderAIMMDiT
0 likes · 7 min read
Open-Sora 2.0: How an 11B Open-Source Model Beats Closed-Source Video AI at 720p
NewBeeNLP
NewBeeNLP
Mar 14, 2025 · Artificial Intelligence

How Open‑Sora 2.0 Achieves SOTA Video Generation with Only $200K Training Cost

Open‑Sora 2.0 is an open‑source 11B‑parameter video generation model that matches commercial SOTA performance while being trained on 224 GPUs for just $200,000, thanks to a 3D auto‑encoder, MMDiT architecture, aggressive data filtering, low‑resolution pre‑training, and highly optimized parallel training techniques.

AI modelMMDiTOpen-Sora
0 likes · 9 min read
How Open‑Sora 2.0 Achieves SOTA Video Generation with Only $200K Training Cost
NewBeeNLP
NewBeeNLP
Mar 20, 2024 · Artificial Intelligence

How Open‑Sora 1.0 Replicates Sora: Architecture, Training Pipeline & Performance Insights

This article provides a comprehensive technical walkthrough of Open‑Sora 1.0, covering its Diffusion‑Transformer architecture, three‑stage training strategy, data‑preprocessing scripts, generation quality, and the Colossal‑AI acceleration that together make Sora‑level video synthesis openly reproducible.

AI videoDiffusion TransformerOpen-Sora
0 likes · 12 min read
How Open‑Sora 1.0 Replicates Sora: Architecture, Training Pipeline & Performance Insights