Adobe Firefly Image 5 brings support for layers, will let creators make custom models

Adobe said Tuesday it is introducing the latest iteration of its image generation model, Firefly Image 5. The company is adding more features to the Firefly website, including support for more third-party models, the ability to create speech and soundtracks. Notably, the update allows artists to come up with their own image models using their existing art.

The Image 5 model can now work at up to 4 megapixels native resolution, which is a huge increase from the previous-gen model, which could natively produce images at 1 megapixels but would then upscale them to 4 megapixels. The new model is also better at rendering people, the company said.

Figure 5 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 company says it ensures that when you edit these layers, the detail and integrity of the image is not compromised.

Adobe’s Firefly site has supported third-party models from AI labs like OpenAI, Google, Runway, Topaz and Flu to increase appeal to its creative customer base, and now the company is taking it a step further by letting users create custom models based on their art style. Currently in a closed beta, this feature allows users to drag and drop assets such as photos, images, and sketches to create a custom image model based on their style.

The company is adding some new features to its Firefly website, which was Redesigned earlier this year. The site now lets you create images or videos using prompt boxes, choose which AI model you want to work with, change the aspect ratio, and more. The site’s home page now includes your files and recent generation history, and you’ll also find shortcuts to other Adobe apps (they were previously housed in a menu).

Adobe also redesigned the video generation and editing tools to support layer and timeline-based editing. This design change is currently only available in a private beta, and will eventually be rolled out to users.

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

As do its competitors Canva adds AI to their platformAdobe is trying to cater to the new age of creators who are using AI in their workflows. “We’re thinking about the target audience for Firefly is what we call creators or next-generation creative professionals. I think there are these emerging creatives who are GenAI-oriented. They like to use GenAI in all their workloads,” Alexandru Costin, the company’s VP of generative AI, told TechCrunch in a call.

He added that with Firefly, the company now has more freedom to add new features and play with the interface because it doesn’t have to adhere to the muscle memory of creative professionals who may be accustomed to specific workflows in Adobe’s existing Creative Cloud tools.