Meta launches standalone AI image generator Imagine

According to Android Authority , Imagine is a standalone service that users can use on their PCs or smartphones to create unique images that perfectly reflect their thoughts. Essentially, it's identical to the Reimagine feature that Meta recently launched on Messenger and Instagram, but Imagine is a standalone service, meaning it's "open" to all platforms.

Unlike Reimagine, Imagine is available for all platforms.

Imagine is developed using Emu technology, Meta's image generation model, and is an AI-based text-to-speech image generation tool. It will compete with image generation models like DALL-E or Midjourney. Its advantages are ease of use and it is offered free of charge to everyone.

Imagina's interface is quite simple. Users will find a text box where they can express their ideas and a "Generate" button above it so the AI ​​can illustrate the text. Meta will add a watermark to all images created using Imagine to promote transparency and track all images generated by the AI ​​model.

The watermark will be applied to a deep learning model and can be detected by the corresponding model. It also has the ability to recover common image manipulations such as cropping, color shifting, screenshots, etc. Meta plans to incorporate this watermark into other AI-generated image products.

Like Meta AI, Imagine is currently only available to users in the US, and Meta's plans for rolling this feature out to global users are unclear.

Source link: https://thanhnien.vn/meta-ra-mat-trinh-tao-anh-ai-doc-lap-imagine-185231209183030666.htm