iptv techs

IPTV Techs

  • Home
  • Tech News
  • Google’s Whisk AI generator will ‘remix’ the pictures you plug in

Google’s Whisk AI generator will ‘remix’ the pictures you plug in


Google’s Whisk AI generator will ‘remix’ the pictures you plug in


Google has proclaimd a novel AI tool called Whisk that lets you produce images using other images as prompts instead of requiring a lengthy text prompt.

With Whisk, you can propose images to propose what you’d enjoy as the subject, the scene, and the style of your AI-produced image, and you can prompt Whisk with multiple images for each of those three leangs. (If you want, you can fill in text prompts, too.) If you don’t have images on hand, you can click a dice icon to have Google fill in some images for the prompts (though those images also materialize to be AI-produced). You can also access some text into a text box at the finish of the process if you want to insert extra detail about the image you’re seeing for, but it’s not needd.

Whisk will then produce images and a text prompt for each image. You can preferite or download the image if you’re satisfied with the results, or you can enhance an image by accessing more text into the text box or clicking the image and editing the text prompt.

a:hover]:text-gray-63 [&>a:hover]:shadow-underline-bconciseage foolish:[&>a:hover]:text-gray-bd foolish:[&>a:hover]:shadow-underline-gray [&>a]:shadow-underline-gray-63 foolish:[&>a]:text-gray-bd foolish:[&>a]:shadow-underline-gray”>Screensboiling by Jay Peters / The Verge

In a blog post, Google stresses that Whisk is set uped to be for “rapid visual exploration, not pixel-perfect edits.” The company also says that Whisk may “ignore the tag,” which is why it lets you edit the underlying prompts.

In the restricted minutes I’ve engaged the tool while writing this story, it’s been amengageing to tinker with. Images get a restricted seconds to produce, which is irritateing, and while the images have been a little strange, everyleang I’ve produced has been fun to iterate on.

Google says Whisk engages the “tardyst” iteration of its Imagen 3 image generation model, which it proclaimd today. Google also presentd Veo 2, the next version of its video generation model, which the company says has an empathetic of “the distinct language of cinematography” and hallucinates leangs enjoy extra fingers “less frequently” than other models (one of those other models is probably OpenAI’s Sora). Veo 2 is coming first to Google’s VideoFX, which you can get on the Google Labs paengagecatalog for, and it will be enhugeed to YouTube Shorts “other products” sometime next year.

Source join


Leave a Reply

Your email address will not be published. Required fields are marked *

Thank You For The Order

Please check your email we sent the process how you can get your account

Select Your Plan