At the Zhongguancun Forum in Beijing last weekend, Chinese startup Shengshu Technology and Tsinghua University unveiled Vidu, a new text-to-video model to compete with OpenAI’s Sora that generates “realistic” 1080p clips up to 16 seconds in length (compared to Sora’s 60 seconds) “with dynamic camera movements, detailed facial expressions, and natural lighting and shadows”.. The […]
In the video below, OPenAI’s CTO, Mira Murati discusses with WSJ’s Joanna Stern how their new text-to-video AI model Sora works. How long does it take to produce a result? As it’s a technology, that is still in its infancy, what about accuracy and consistency and managing the inevitable glitches and imperfections? When are we […]
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 […]
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 […]
Everypixel Journal has been able to establish that 15 billion images have been generated by AI tools DALL-E, Midjourney, Stable Diffusion and Adobe Firefly in the last year. To put that into context, photography was invented circa 1826 and it took until 1975 for the same number of pictures to be taken conventionally. a study by […]
Using characters and scenes he generated with Dall-E, writer / director Chad Nelson and creative agency Native Foreign have made the animated short Critters, which recently debuted on YouTube. The five-minute film, which was partly financed by OpenAI and is a cross between something from Pixar and a David Attenborough-style documentary, we meet a cast […]