Google ’s latestAI toolhelps you automatise image generation even further . The tool is calledWhisk , and it ’s based on Google ’s latestImagen 3 image coevals poser . Rather than relying exclusively on text prompts , Whisk serve you make your desired mental image using other image as the base prompt .
Whisk is presently in an experimental form , but once put up it ’s evenhandedly soft to pilot . Googledetailed in a blog postintroducing Whisk that it is mean for “ rapid visual exploration , not pixel - perfect edits . ”
Exploring the tool has a fast - pace flavor , in equivalence to other text - based cock , that are more contingent on the particular and accuracy of the words to bring forth an image .
After plump through the Welcome page , which number the of import details you should know about how the tool functions , the page asking if you ’d like to sign up for email , and the privateness insurance , you ’ll lade flop into the primary page of Whisk . I escort a command prompt with a dinosaur plushie as the image style , but the other options are an enamel pin and sticker . I just went with the first .
Next , you ’re directed to upload an image for the subject . I uploaded a photograph of a smartwatch on my wrist joint and apace realized this was n’t go to work . The third pick on the right was in a unending loading way , so I seek again , with a more cartoonish figure I find on my hard cause , and this loaded decent away into plushie statuette of three fabulous creatures .
Once the figure was generated , I was able to go into an editing section , with a text prompt area . Simply using the suggested command prompt “ the part is run through ice cream , ” I generated additional figure with the same creature holding ice emollient cones .
or else , you’re able to scroll down below the main straightaway section and select start from scratch line . This will allow you to upload all of your own image or infix your own textual matter . you may also add additional text from the origin so that your character can do an action . If you ’re lost for what images to add or text edition to typecast , you could chatter the Inspire Me push , and Whisk will fill in images .
The prick also allows you to get at a My Library section , where you could view all of the mental image you ’ve created . In this section , you’re able to enable or turn off the library if you ’d prefer to not preserve your creations . you’re able to also download figure of speech , delete images individually , or delete library data as a whole . Additionally , you’re able to select the quick stimulant choice on each image to see the total text prompt for the generated image . There is a copy option usable for sharing to other tools and programs .
I later discovered Whisk did generate an image fuse the plushie and smartwatch images and bring through it in My Library . So , my recommendation is , if you have mishap with the tool , check in your library to see if any image have develop in the background .
The Whisk tool is remindful of the Microsoft Designer prompt that allow user to createFunko Pop ! figures . As a whole , you could use Microsoft Designer to generate a range of whimsical or naturalistic double . However , the AI source – which currently uses the DALL - due east 3 image generation theoretical account develop by OpenAI , ply solely on schoolbook command prompt .
To experiment , I took the text command prompt for the plushie smartwatch to Microsoft Designer . get ’s just say the results were not as elaborate and were a little flake haunting , with the results delivering human faces on a watch body instead of a elaborated watch aspect . This suggests that the Imagen 3 modeling in Whisk can more closely decipher context when analyzing the images than the DALL - E 3 model can when processing text .
As said , Whisk still includes the opportunity to impart school text prompts , which Google noted is include due to the tool ’s potential difference to “ lack the mark , ” so you always have the pick to fill in prompts when need .
