Recently, OpenAI released a compelling news: In its internal testing project, Sora, in addition to the video generation function that has been launched, the image generation function is also being developed in full swing. This new feature allows users to quickly switch between video and image generation, improving creative flexibility.
According to internal messages, Sora will add a hidden toggle button, and users can switch between the two modes by simply selecting in the prompt bar. When selecting image generation, the system will automatically prompt the user to describe an image. This design is designed to simplify user operations and improve the relevance and quality of generated content.
In addition to improvements in image generation capabilities, Sora has also reclassified its video push. The newly launched "Best" and "Top" categories will help users better filter and find content. The “Best” category is similar to the current featured channels, while the “Top” category may rank videos based on the number of likes from users or time periods. This change in the category makes people look forward to Sora's content recommendation mechanism.
For DALL-E3 users, the news is undoubtedly exciting, as DALL-E3 has been somewhat outdated since its launch, especially when compared to competitors like Midjourney. Although Sora's image generation function has not yet been officially launched, the "Images Internal" category in the left navigation bar has aroused users' curiosity. Although this category is currently mainly used for video push, it may also provide related content for image generation in the future.
Some people speculate that this image generation model may be called DALL-E4, but OpenAI has not confirmed this yet. Industry experts speculate that the image generator in Sora may not use DALL-E4 directly, but will rely on the existing "sora-turbo" model. In addition, industry insiders also pointed out that ChatGPT has not yet launched the multimodal image generation function based on GPT-4o, so the launch of the Sora project will be a new progress worthy of attention.
It is worth noting that the code name of the text-to-image generator in Sora is called "papaya", which makes people curious and expectant about this project. One and a half years after the release of DALL-E3, what kind of innovation will the next generation model bring is something that makes people want to find out.
In short, Sora's image generation function is about to be launched, providing users with more creative possibilities, which is worth looking forward to.