Generator is releasing several updates on the AI front, including a new text-to-image tool. what is different about The thing is that it has an interface that features “expressive chips”. The idea here is that these will help you “quickly experiment with adjacent dimensions of your creations and ideas.”
With the introduction of ImageFX, Google says it has improved MusicFX and TextFX. The company claims that it has upgraded the MusicLM model with new features that include louder music and higher quality audio. Generated songs can now play up to 70 seconds. related to Google has released a usability update aimed at improving navigation and overall user experience.
Images created with ImageFX and audio created with MusicFX are tagged by SynthID, The aim is to make it clear that these are forged using AI, especially when they appear in search or Chrome. ImageFX compositions will also include IPTC metadata. According to Google, this will “provide people with more information whenever they encounter our AI-generated images”.
People in the US, Kenya, New Zealand, and Australia can try out these new and revised tools in the AI Test Kitchen starting today. They are currently only available in English.
The Imagen 2 model is powering ImageFX’s new image creation features. This is also the technology that is driving new generative AI options at Bard, ,Advertising, Duet AI and Vertex AI in the Workspace. Google says Imagen 2 helps deliver the highest quality AI-generated images ever. The company notes that the model helps keep images clear of artifacts and improves areas of image generation that such devices have struggled with until now.
Additionally, Google says it has made a “significant investment” in Imagen 2 training data security…