Image Credits:<\/strong> Adobe<\/p>\n<\/div>\n

The neat thing here is that this integration allows Photoshop users to use natural language text prompts to describe the kind of image or object they want Firefly to create. As with all generative AI tools, the results can occasionally be somewhat unpredictable. By default, Adobe will provide users with three variations for every prompt, though unlike with the Firefly web app, there is currently no option to iterate on one of these to see similar variations on a given result.<\/p>\n

To do all of this, Photoshop sends parts of a given image to Firefly \u2014 not the entire image, though the company is also experimenting with that \u2014 and creates a new layer for the results.<\/p>\n

Maria Yap, the vice president of Digital Imaging at Adobe, gave me a demo of these new features ahead of today\u2019s announcement. As with all things generative AI, it\u2019s often hard to predict what the model will return, but some of the results were surprisingly good. For instance, when requested to generate a puddle beneath a running corgi, Firefly appeared to take the overall lighting of the image into account, even generating a realistic reflection. Not every result worked quite as well\u00a0 \u2014 a bright purple puddle was also an option \u2014 but the model does seem to do a pretty good job at adding objects and especially at extending existing images beyond their frame.<\/p>\n

Given that Firefly was trained on the photos available in Adobe Stock (as well as other commercially safe images), it\u2019s maybe no surprise that it does especially well with landscapes. Similar to most generative image generators, Firefly struggles with text.<\/p>\n

Adobe also ensured that the model returns safe results. This is partly due to the training set used, but Adobe has also implemented additional safeguards. \u201cWe married that with a series of prompt engineering things that we know,\u201d explained Yap. \u201cWe exclude certain terms, certain words that we feel aren\u2019t safe. And then we\u2019re even looking into another hierarchy of \u2018if Maria selects an area that has a lot of skin in it,\u2019 maybe right now \u2014 and you\u2019ll actually see warning messages at times \u2014 we won\u2019t expand a prompt on that one, just because it\u2019s unpredictable. We just don\u2019t want to go into a place that doesn\u2019t feel comfortable for us.\u201d<\/p>\n

As with all Firefly images, Adobe will automatically apply its Content Credentials to any images utilizing these AI-based features.<\/p>\n

A lot of these features would also be quite useful in Lightroom. Yap agreed, and while she wouldn\u2019t commit to a timeline, she did confirm that the company is planning to bring Firefly to its photo management tool as well.<\/p>\n<\/p><\/div>\n

<\/br><\/br><\/br><\/p>\n