Adobe launches new models to generate Firefly Images and a revised web application for Firefly

Adobe on Thursday launched the latest iteration of its Firefly family of image generation models, vectors generation model and a A revised web application This has all his AI models, plus some of his competitors. The work also has a mobile app for Firefly.

The new image model of Firefly, says Adobe, is improving in its predecessors in terms of quality, speed and size of control over the structure and style of outputs, camera angles and increase. It can generate images with separation capabilities up to 2K. There is also a pinch, a more capable version of this model called Image Model 4 Ultra, which can depict complex scenes consisting of small structures and many details.

Alexandru Kostin, Vice President of Generation AI in Adobe, said the company has trained the models with a higher order of computing to allow them to generate more detailed images. He added that, compared to previous generation models, new models improve text generation and have features that allow users to use images of their own choice to make the model generate photos in this style.

The company also makes its video model of Firefly, which Started at Limited Beta last yearAt all. It allows users to generate videos from a text prompt or image, to use camera angles, to indicate the start and end of frame control frames, generating atmospheric elements, and customization of motion design elements. The model can generate videos from text with resolutions up to 1080p.

Meanwhile, the model of the Firefly vector can create editing works of art based on a vector, repeats and generate variations of logos, packaging of products, icons, scenes and models.

In particular, Firefly’s web application gives you access to all these models, as well as several image models and video generation from Openai (GPT images), Google (Imagen 3 and Veo 2) and Flux (Flux 1.1 Pro). Users can switch between each of these models at any time, and the images generated by each model will have their content identification data attached to them. The company has hinted that other AI models can be added to the web application in the future.

Adobe also publicly tests a new product called Firefly Boards, a canvas for an idea or mood. It allows users to generate or import images, remix them and collaborate with others-like what you can do with other AI-based ideas Visual electric., Bay or SpaceS Boards are available through the Firefly web application.

The company said these new models will soon be integrated into its product portfolio, but do not give a time line to deploy.

Adobe also makes its API and API on Text-to-Exi and Avatar API as a whole and said a new API has already been available on a text to a video for use in beta. These APIs are available through the API’s Firefly Services collection, tools and services.

Adobe also tests a web application called Authenticity of Adobe content To allow users to attach credentials to their work to indicate property and attribution through metadata. Users can also indicate whether AI companies can use AI Model training images.