ai video generation

Finding the AI Creators Best at Storytelling: Orca Entertainment’s Jingrui AI Creation Contest Comes to Tsinghua University 2026-11-09 10:19:08 Source: QbitAI On November 6, Tsinghua University held the Jingrui AI Creation Contest expert roundtable, “New Technologies Bring New Vitality to Culture, Telling China’s Stories Well with AI” “Excellent works must be carefully polished and shaped by their creators; they cannot possibly be generated with a single c

AI Short-Drama Production Barriers Keep Dropping! Hands-On Test of Jimeng Short Drama Studio: An End-to-End Workflow for Scriptwriting, Storyboarding, and Previsualization; the Partner Program Offers Long-Term Support 2026-11-06 11:20:05 Source: QbitAI Seedance 2.5 costs as little as RMB 0.15 per second Tingyu, reporting from Aofeisi QbitAI | Official WeChat Account: QbitAI Has anyone else like me been binge-watching “The Accident” lately? I’m seriously ho

Cyberpunk Cultivation Meets Home-Appliance Sales! Are AI Short Dramas Now Chasing Double 11 Results? 2026-11-06 14:54:17 Source: QbitAI Taking on High-Difficulty Commercial Video Scenarios Mengyao reporting from Aofeisi, QbitAI | Official WeChat account: QbitAI AI Short Dramas’ Business Models Are Starting to Look Like Taobao’s! Right during the Double 11 shopping festival over the past two days, Taobao Short Drama teamed up with Tmall Little Black Box, Tm

Post-2000-born doctoral student at Zhejiang University delivers again! Packs more than a dozen physical factors into a single world model | Native to Huawei Ascend 2026-11-07 11:31:44 Source: QbitAI The Chinese version of Cosmos delivers another result henry sent from Aofeisi QbitAI | Official WeChat account QbitAI Three and a half months after his company’s valuation surged from RMB 4 billion to nearly RMB 10 billion and he vowed to build a “Chinese versi

We trained a neural network to play Minecraft by Video PreTraining (VPT) on a massive unlabeled video dataset of human Minecraft play, while using only a small amount of labeled contractor data. With fine-tuning, our model can learn to craft diamond tools, a task that usually takes proficient humans over 20 minutes (24,000 actions). Our model uses the native human interface of keypresses and mouse movements, making it quite general, and represents a step t

We explore large-scale training of generative models on video data. Specifically, we train text-conditional diffusion models jointly on videos and images of variable durations, resolutions and aspect ratios. We leverage a transformer architecture that operates on spacetime patches of video and image latent codes. Our largest model, Sora, is capable of generating a minute of high fidelity video. Our results suggest that scaling video generation models is a

Our video generation model, Sora, is now available to use at sora.com. Users can generate videos up to 1080p resolution, up to 20 sec long, and in widescreen, vertical or square aspect ratios. You can bring your own assets to extend, remix, and blend, or generate entirely new content from text.