Adobe said on Tuesday that it’s launching the newest iteration of its image generation model, Firefly Image 5. The corporate can be adding more features to the Firefly website, support for more third-party models, the flexibility to generate speech and soundtracks. Notably, the update allows artists to provide you with their very own image models using their existing art.
Image 5 model can now work at native resolutions of as much as 4 megapixels, an enormous increase from the previous gen model, which could natively generate images at 1 megapixels but then would upscale them to 4 megapixels. The brand new model can be higher at rendering humans, the corporate said.
Image 5 also enables layered and prompt-based editing — the model treats different objects as layers and lets you edit them using prompts, or use tools like resize and rotate. The corporate said it makes sure that whenever you edit these layers, the image’s details and integrity usually are not compromised.
Adobe’s Firefly site has supported third-party models from AI labs like OpenAI, Google, Runway, Topaz, and Flu to reinforce its appeal to its creative customer base, and now the corporate is taking that a step further by letting users create custom models based on their art style. Currently in a closed beta, this feature lets users drag and drop assets, comparable to images, illustrations and sketches, to create a custom image model based on their style.
The corporate can be adding some latest features to its Firefly website, which was redesigned earlier this yr. The positioning now helps you to use the prompt box to modify between generating images or videos, select which AI model you must work with, change aspect ratios, and more. The positioning’s home page now features your files and up to date generation history, and you furthermore mght get shortcuts to other Adobe apps (these were previously housed in a menu).
Adobe has also redesigned the video generation and editing tool to support layers and timeline-based editing. This design change is currently only available in a personal beta, and will probably be rolled out to users eventually.
Firefly can be getting two latest audio features: Users can now employ AI prompts to generate entire soundtracks and speech — using models from ElevenLabs — for videos. There’s also a brand new approach to easily provide you with prompts: just add keywords and sections by choosing words from a word cloud.
Techcrunch event
San Francisco
|
October 27-29, 2025
As its competitors like Canva add AI to their platforms, Adobe is attempting to cater to new-age creators who’re increasingly using AI of their workflows. “We’re considering of the audience for Firefly as what we call creators or next-generation creative 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, told TechCrunch over a call.
He added that with Firefly, the corporate now has more freedom so as to add latest features and mess around with the interface because it doesn’t must adhere to the muscle memory of creative professionals who is perhaps used to certain workflows in Adobe’s existing Creative Cloud tools.