The Firefly Text to Image and Text to Video features transform detailed text prompts into images or videos by interpreting the words and phrases included in a description such as “a cartoon dog riding a skateboard”. It identifies the subject, action, style, and object or setting within the phrase. Including descriptive words such as “cartoon” helps to inform the outcome, producing results such as exaggerated proportions and bold lines. Additional inputs, such as adjusting the settings or uploading a Reference Image, further inform the generated artwork.
While Firefly does not transform pre-existing images into cartoons like a filter, you can use a Reference Image to guide the outcome of your generated image, creating cartoon versions of selfies and other photos. You can use a prompt to create cartoon images of scenes and environments, characters, objects, and more.
Yes, you can create a cartoon from text only using the Text to Image or Text to Video feature. These features allow you to generate cartoon-style images or videos entirely from written descriptions; you do not need to upload an image. Simply write a description of the image you want to create, and the Firefly web app will generate cartoon-style images based on that prompt.
Yes, you can use the Text to Image and Text to Video features to create cartoons for commercial use, provided you adhere to
Adobe guidelines and the content is produced using the commercially released version of Firefly. All Firefly tools are designed to be safe for commercial use, as they are trained on Adobe Stock, licensed content, and public domain materials.
Adobe Firefly currently supports downloading generated images in JPEG and PNG formats. These formats are available when using the Text to Image feature, and the maximum resolution for downloaded images is 2000x2000 pixels. Currently, videos created by Text to Video are five seconds in duration, at 1080p resolution and can be downloaded as an mp4 file.