Following an early preview at the start of the year, Sora, OpenAI’s long-awaited video generation model, is ready for public use. If you’re a ChatGPT Plus or Pro subscriber, you can begin experimenting with the tool starting later today, OpenAI announced on Monday. A more powerful model powers the product than the one OpenAI showed off in February. Sora Turbo is significantly faster, according to the company, though OpenAI cautions the new model still has limitations. “It often generates unrealistic physics and struggles with complex actions over long durations,” says the company.
When users first visit the dedicated landing page OpenAI has set up for Sora, they’ll be greeted with a feed of videos the model has created for other people. By clicking on a video, you’ll be able to see the exact prompt someone gave Sora to generate the footage you see. From here, you can also decide to re-cut a video, blend it into a clip you’re working on, or remix it. In this initial release, OpenAI is limiting Sora to generating videos that are up to 1080p and 20 seconds long.
ChatGPT Plus subscribers can use Sora to generate up to 50 videos at 480p per month. Alternatively, Plus users can generate fewer videos at 720p. OpenAI says the Pro plan affords 10 times as much usage, at higher resolutions and longer durations. “We’re working on tailored pricing for different types of users, which we plan to make available early next year,” the company adds.
For safety purposes, each video features a visible watermark and contains C2PA metadata to assist with identification. OpenAI says it will block users from using Sora to create child sexual abuse materials (CSAM) and sexual deepfakes. More broadly, the company plans to limit uploads of people until it has time to refine its safeguards against deepfakes.
Developing…
This article originally appeared on Engadget at https://www.engadget.com/ai/openais-sora-video-generation-ai-model-arrives-globally-later-today-182613208.html?src=rss