Adobe stated on Tuesday that it’s launching the newest iteration of its picture era mannequin, Firefly Picture 5. The corporate can also be including extra options to the Firefly web site, help for extra third-party fashions, the flexibility to generate speech and soundtracks. Notably, the replace permits artists to give you their very own picture fashions utilizing their present artwork.
Picture 5 mannequin can now work at native resolutions of as much as 4 megapixels, a large enhance from the earlier gen mannequin, which may natively generate photographs at 1 megapixels however then would upscale them to 4 megapixels. The brand new mannequin can also be higher at rendering people, the corporate stated.
Picture 5 additionally permits layered and prompt-based modifying — the mannequin treats totally different objects as layers and permits you to edit them utilizing prompts, or use instruments like resize and rotate. The corporate stated it makes certain that whenever you edit these layers, the picture’s particulars and integrity aren’t compromised.
Adobe’s Firefly website has supported third-party fashions from AI labs like OpenAI, Google, Runway, Topaz, and Flu to reinforce its attraction to its artistic buyer base, and now the corporate is taking {that a} step additional by letting customers create customized fashions primarily based on their artwork model. At present in a closed beta, this characteristic lets customers drag and drop property, equivalent to photographs, illustrations and sketches, to create a customized picture mannequin primarily based on their model.
The corporate can also be including some new options to its Firefly web site, which was redesigned earlier this yr. The location now enables you to use the immediate field to modify between producing photographs or movies, select which AI mannequin you need to work with, change side ratios, and extra. The location’s residence web page now options your information and up to date era historical past, and also you additionally get shortcuts to different Adobe apps (these have been beforehand housed in a menu).
Adobe has additionally redesigned the video era and modifying device to help layers and timeline-based modifying. This design change is presently solely out there in a non-public beta, and will probably be rolled out to customers finally.
Firefly can also be getting two new audio options: Customers can now make use of AI prompts to generate whole soundtracks and speech — utilizing fashions from ElevenLabs — for movies. There’s additionally a brand new option to simply give you prompts: simply add key phrases and sections by deciding on phrases from a phrase cloud.
Techcrunch occasion
San Francisco
|
October 27-29, 2025
As its rivals like Canva add AI to their platforms, Adobe is making an attempt to cater to new-age creators who’re more and more utilizing AI of their workflows. “We’re considering of the audience for Firefly as what we name creators or next-generation artistic professionals. I feel there are these emergent creatives which are GenAI-oriented. They love to make use of GenAI in all their workloads,” Alexandru Costin, the corporate’s VP of generative AI, advised TechCrunch over a name.
He added that with Firefly, the corporate now has extra freedom so as to add new options and mess around with the interface because it doesn’t have to stick to the muscle reminiscence of artistic professionals who may be used to sure workflows in Adobe’s present Inventive Cloud instruments.
