OpenAI describes its new tool as “an AI model that can generate realistic and imaginative scenes from text instructions” We’re teaching AI to understand and simulate the physical world in motion, with the goal of training models that help people solve problems that require real-world interaction. Introducing Sora, our text-to-video model. Sora can generate videos […]
China’s Tencent, the home of WeChat, has announced a new version of its open source video generation model DynamiCrafter – visit the GitHub page. Like others, it uses the diffusion method to turn captions and still images into seconds-long videos. What is the diffusion method? It turns captions and still images into seconds-long videos. Diffusion models […]
The 2024 Sundance Film Festival (18-28 January) hosted the premiere of Eno, a new documentary charting the career of one of the music industry’s greatest living innovators. The film, by Gary Hustwit and generative AI specialist Brendan Dawes, is unusual in that a new version is created every time it is watched, using the amusingly anagrammatic […]
A generative artist who goes by the name Princess Prompt has published a set of pretty stunning images she created using the latest generative AI tools showing what The Simpsons might look like in real life. This is not a new thing, but the quality just keeps getting better and better … Below is a […]
The predictions are that, through tools like Stable Video Diffusion, Pika, Runway, Meta’s Emu Video and, soon-ish, Midjourney, generative video is going to be one of the big talking points and disruptors in 2024 And if the predictions are correct, more video content creators will start to learn how to automatically edit footage, synthesise voiceovers, […]
With thanks to Eric Vyacheslav on Linkedin, this is Open AI’s recommended strategy for getting the best out of prompting GPT. 1 – write clear instructions be specific: Clarity in instructions leads to more relevant outcomes. define the desired output length and complexity. demonstrate preferred formats. minimise ambiguity to enhance model accuracy 2 – provide […]