Tag

#video generation

20 articles

Google Deepmind argues video generators already contain the world models computer vision has been missing

Learn how to repurpose pre-trained video generators for classic computer vision tasks like depth estimation and semantic segmentation, demonstrating the potential of video generators as universal world models.

Jul 1915

Meet LingBot-World-Infinity: An Open Causal World Model With An Agentic Harness

This explainer introduces LingBot-World-Infinity, an AI system that creates long-term interactive video worlds using advanced techniques to maintain accuracy over time.

Jul 921

Hollywood wants Seedance banned and reportedly also wants to keep using it

Learn how to use AI video generation tools like Seedance to create AI-generated videos. This beginner-friendly tutorial covers the basics of AI video creation and ethical considerations.

Jul 529

Kling AI raises two billion dollars as Kuaishou spins off its fastest-growing business

Kling AI, the video generation unit of Kuaishou, has raised $2 billion in venture capital, with potential funding to reach $3 billion as it prepares for independence.

Jul 236

research

Microsoft Research's Mirage gives video generation a persistent spatial memory that doesn't forget what's around the corner

Microsoft Research's Mirage introduces a new video generation system with persistent spatial memory, improving scene consistency while reducing computational costs.

Jun 1459

India’s Avataar AI launches a video model that costs $0.005 per second, 27x cheaper than rivals

Learn how to create AI-powered videos using open-source tools at a fraction of the cost of commercial solutions, similar to India's Avataar AI's Varya model.

Jun 1248

Cheaper, faster, and culturally aware, Avataar’s video AI is built for India’s scale

Avataar AI's new distilled video model offers affordable, culturally aware AI video generation for India's digital market, priced at $0.005 per second of content.

Jun 1149

Google launches Gemini Omni Flash, a conversational video-generation model with avatar mode held back

Google has launched Gemini Omni Flash, a multimodal video-generation model with avatar mode and default SynthID watermarking. Speech-editing features are being held back for further development.

May 2040

NVIDIA Introduces SANA-WM: A 2.6B-Parameter Open-Source World Model That Generates Minute-Scale 720p Video on a Single GPU

NVIDIA introduces SANA-WM, a 2.6 billion-parameter open-source world model capable of generating 60-second 720p videos with precise camera control on a single GPU.

May 1539

Runway started by helping filmmakers — now it wants to beat Google at AI

This explainer explores how AI video generation serves as a pathway to world models, the theoretical framework for creating general-purpose AI systems that understand and predict complex environments.

May 1554

New AI model generates 45-minute lip-synced video from one photo and runs in real time

A new AI model, LPM 1.0, can generate 45-minute lip-synced videos from a single photo in real time, marking a major advancement in digital avatar technology.

Apr 1396

Google now offers Ultra subscribers video generation with Veo 3.1 Lite at no extra credit cost

This article explains how Google's Veo 3.1 Lite video generation technology works and why offering it to Ultra subscribers at no extra cost represents a strategic shift in AI platform economics.

Apr 1370