Adobe Firefly Image 5 provides support for layers, and will allow creators to create custom forms

Adobe said Tuesday it will release the latest version of its image generation model, Firefly Image 5. The company is also adding more features to the Firefly website, support for more third-party models, and the ability to create speech and soundtracks. It is worth noting that the update allows artists to create their own image templates using their existing artwork.

The Image 5 model can now work at a native resolution of up to 4MP, which is a huge increase over the previous year’s model, which could create 1MP images but then upscale them to 4MP. The new model is also better at serving humans, the company said.

Image 5 also allows for layered and prompt-based editing – the form treats different objects as layers and allows you to edit them using prompts, or using tools such as resizing and rotating. The company said that it makes sure that when editing these layers, the details and integrity of the image will not be compromised.

Adobe’s Firefly supports third-party models from AI labs like OpenAI, Google, Runway, Topaz, and Flu to increase its appeal to its creative customer base, and now the company is taking that a step further by allowing users to create custom models based on their artistic style. Currently in closed beta, this feature allows users to drag and drop assets, such as photos, illustrations, and graphics, to create a custom image template based on their style.

The company is also adding some new features to its Firefly website, which was redesigned earlier this year. The site now lets you use the prompt box to switch between creating images or videos, choose the AI ​​model you want to work with, change aspect ratios, and more. The site’s home page now displays your files and recent creation history, and you can also get shortcuts to other Adobe applications (they were previously in the menu).

Adobe has also redesigned its video creation and editing tool to support layers and timeline-based editing. This design change is currently only available in private beta, and will be rolled out to users eventually.

Firefly is also getting two new audio features: Users can now use AI prompts to create audio clips and full speech — using templates from ElevenLabs — for videos. There’s also a new way to easily come up with prompts: simply add keywords and sections by selecting words from the word cloud.

As its competitors, like Canva, add AI to their platforms, Adobe is trying to meet the needs of new-age creators who are increasingly using AI in their workflow. “We think of the target audience for Firefly as what we call next-gen creators or creative professionals. I think there are these emerging creators who are moving towards GenAI. They love using GenAI in all of their workloads,” Alexandru Costin, vice president of generative AI at the company, told TechCrunch over a call Telephone.

He added that with Firefly, the company now has more freedom to add new features and play with the interface because it doesn’t need to commit to the muscle memory of creative professionals who might be used to a particular workflow in Adobe’s existing Creative Cloud tools.