Adobe on Thursday launched the latest recurrence of the image generation AI model’s latest repetition, a model to create a vector, and A RE: Web app designed It is from all its AI models, as well as some of its rivals. There is also a mobile app for firefly in work.
The new firefly image model 4, Adobe says, improves the quality, speed and output, camera angle and the composition and style of zoom in terms of its predecessors in terms of the amount of control over the structure and style. It can produce images in resolutions up to 2K. The image model 4 is also a tick of this model called 4 Ultra, there is also a more competent version that can present small structures and a lot of detailed complex scenes.
Alexandroo Costin, VP of Generic AI at Adobe, said the company trained the model with a high order of compute magnitude to enable them to generate more detailed pictures. He said that, compared to the model of the previous generation, new model images improve text generations and have characteristics that allow users to use images of their choice to get models to generate pictures in that style.
The company is also making its own firefly video model, which was launched in Limited Beta last year, which was available to all. It allows users to generate video clips from a text prompt or image, use camera angles, specify start and and frames to control shots, generate atmospheric elements and optimize motion design elements. The model can generate video clips from the text on resolutions up to 1080p.
Meanwhile, the firefly vector model can create editable vector-based artwork, recurring and using logo, product packaging, icons, scenes and patterns.
In particular, the web app of Jugnu provides you with all these models -Openai (GPT Image Generation), Google (Imagene 3 and Veo 2), and flux (flux 1.1 Pro) provides some image and access to video generation models. Users can switch between any of these models at any point, and the images generated by any model will have the material credentials associated with them. The company indicated that other AI models could be added to the future web apps.
Adobe is publicly testing a new product, called firefly boards, which is a canvas for ideas or moodboarding. This allows users to generate or import images, remixes or import them, and collaborate with others-as you can do visual electric, coves or cosmic with other AI-based ideas. The board is available through the Jugnu web app.
The company said that these new models would soon be integrated into their product portfolio, but did not give a time -line for the rollout.
Adobe is also providing its text-to-image API and avatar API, and said that a new text-to-video API is now available for use in beta. These APIs are available through APIs, equipment of equipment and services through the fire collection of the company.
Adobe is also testing a web app Adobe material authenticity Let users attach credentials for your work to indicate ownership and attention through metadata. Users may also indicate whether AI companies can use any images for AI model training.
