Generative Fill and Generative Expand in Photoshop
Use a simple text prompt to add or remove content from any image. Click and drag beyond the image border to seamlessly fill the expanded canvas with matching content. Powered by Adobe Firefly.
Generative Fill and Text to Template in Adobe Express
With the all-in-one content creation app for social posts, videos, PDFs, and more, you can use Generative Fill to add, remove, or replace any part of your image. Plus, generate a template from a prompt with Text to Template.
Adobe Firefly is a standalone web application available at firefly.adobe.com. It offers new ways to ideate, create, and communicate while significantly improving creative workflows using generative AI. In addition to the Firefly web app, Adobe also has the broader Firefly family of creative generative AI models, along with features powered by Firefly in Adobe’s flagship apps and Adobe Stock.
Firefly is the natural extension of the technology Adobe has produced over the past 40 years, driven by the belief that people should be empowered to bring their ideas into the world precisely as they imagine them.
Generative AI is a type of artificial intelligence that can translate text and other inputs into extraordinary results. While the conversation around this technology has centered on AI image and art generation, generative AI can do much more than generate static images from text prompts. With a few simple words and the right AI generator, anyone can create videos, documents, and digital experiences, as well as rich images and art. AI art generators can also be useful for producing “creative building blocks” like brushes, vectors, and textures that can add to or form the foundation of pieces of content.
As part of Adobe’s effort to design Firefly to be commercially safe, we’re training our initial commercial Firefly model on licensed content, such as Adobe Stock, and public domain content where copyright has expired. Additionally, as a founding collaborator of the Content Authenticity Initiative (CAI), Adobe is setting the industry standard for responsible generative AI. The CAI is a community of media and tech companies, NGOs, academics, and others working to promote adoption of an open industry standard for content authenticity and provenance.
This is in conjunction with the Coalition for Content Provenance and Authenticity (C2PA), which has developed an open technical standard providing publishers, creators, and consumers the ability to understand the origin of different types of media, including the ability to add a Content Credential that allows creators to indicate that generative AI was used. Find out more about content credentials.
AI generators like Firefly can enhance creativity by giving people new ways to imagine, experiment, and bring their ideas to life. Firefly is unique because Adobe intends it to be more than an AI text-to-image generator. As part of Creative Cloud, we’re building Firefly to supplement the tools Adobe creators know and love with text-based editing and generation of a variety of media, from still images to video to 3D, as well as “creative building blocks” like brushes, vectors, textures, and more.
For Firefly, the future vision is for creators to be able to use everyday language and other inputs to quickly be able to test out design variations, remove distractions from photos, add elements to an illustration, change the mood of a video, add texture to 3D objects, create digital experiences, and more — then seamlessly customize and edit their content using a combination of Firefly and other Creative Cloud tools.
As a type of generative AI technology, AI art generators work similarly to other types of artificial intelligence, which use a machine learning model and large datasets to be able to produce a specific type of result. With generative AI, anybody can use everyday language and other inputs to produce images, videos, documents, digital experiences, and more. Adobe Firefly is being built into Creative Cloud to give people the tools to both generate results quickly and customize them to fit their unique vision.
The Firefly standalone web application on firefly.adobe.com has a free and premium plan — opening up creativity to anyone at any design skill level by using everyday language to get extraordinary results with generative AI. Find out more or sign up for the Firefly Premium plan.
Your Creative Cloud, Adobe Express, Firefly, or Adobe Stock subscription now includes monthly generative credits that give you access to content creation features powered by Firefly. Find out more about generative credits.
Firefly is bringing the power of generative AI to global audiences by supporting over 100 languages for text prompt inputs, as well as localizing the Firefly website for more than 20 languages, starting with Japanese, French, German, Spanish, Brazilian Portuguese, Korean, Italian, Danish, Dutch, Norwegian, Swedish, Finnish, Chinese Simplified, and Chinese Traditional.
We currently support prompts in over 100 languages using machine translation to English provided by Microsoft Translator. Because of the nuances of each language, it’s possible certain generations based on translated prompts may be inaccurate or unexpected. We are working hard to identify and resolve any issues. To report incorrect translation results, hover over a generated image and click on the Report tool.
Adobe Firefly Image 2 is the next version of the image generation model within the Firefly family of models.
Like Firefly Image 1, Firefly Image 2 is trained on licensed content, such as Adobe Stock, and public domain content where copyright has expired. However, the capacity of Firefly Image 2 will be larger, and it will generate higher quality images — with better human rendering — and users will have more control over content and depth of field.
You can try Firefly Image 2 Model within the Text to Image module on the Firefly web app. Toggle from Firefly Image 1 to Firefly Image 2 to generate images with the new model.
The current Firefly generative AI model is trained on a dataset of licensed content, such as Adobe Stock, and public domain content where copyright has expired.
As Firefly evolves, Adobe is exploring ways for creators to be able to train the machine learning model with their own assets so they can generate content that matches their unique style, branding, and design language without the influence of other creators’ content. Adobe will continue to listen to and work with the creative community to address future developments to the Firefly training models.
No, copies of customer content are not included in the Firefly models.
No. We do not train on any Creative Cloud subscribers’ personal content. For Adobe Stock contributors, the content is part of the Firefly training dataset, in accordance with Stock Contributor license agreements.
We have developed and deployed generative AI at Adobe in accordance with our AI ethics principles of accountability, responsibility, and transparency. Read our blog post to learn more about our approach and commitment to developing generative AI in a way that respects our customers and aligns with our company values.
As part of Adobe’s effort to design Firefly to be commercially safe, we are training our initial commercial Firefly model on licensed content, such as Adobe Stock, and public domain content where copyright has expired.
Sensei Gen AI is Adobe’s new generative AI service that is being integrated natively in Adobe Experience Cloud to power end-to-end marketing workflows, dramatically improving enterprise productivity and efficiency. Firefly is a separate family of creative generative AI models coming to Adobe products, with an initial focus on image and text effect generation. Learn more about our generative AI efforts.