EXPLORING THE AI WORLD 
Last week at an industry event, Adobe showcased Project Gingerbread. This new and impressive generative AI application combines 3D modeling with synthetic image generation to create photorealistic pictures like never before.
While Project Gingerbread is still in the development phase and has no projected release date, the preview has been enough to cause waves across the creative industry.
Read on and find out why!
Last June 22nd, during the last day of Figma’s Config 2023 event in San Francisco, Adobe wowed attendants to the “AI and the future of design” panel with a preview of Gingerbread, a feature that takes AI image generator up a notch, to produce the most photorealistic AI images yet.
How? It starts with letting users drag and drop 3D models into an image to serve as the base of an AI-generated visual element; the user can adjust details such as the angle and perspective of the object to ensure a perfect fit into the original image. Then, via text prompt, generate the desired visual element with the correct dimensions to look as realistic as possible within the composition.
By loading the video, you agree to YouTube's privacy policy.
Learn more
This functionality offers much more customization and seems more efficient than the current generative models, where you create content using written descriptions and hope for the best or spend time refining your prompt or manually editing the image to get the desired look –the kind of functionality that Adobe Firefly models have provided so far.
The promising results from Gingerbread –which is still a work in progress– are attractive not only because of the photography-like results it can produce but also because it gives the creator a lot more control over the generation process to make sure the aesthetics of the final image are exactly what they want and need.
This is not only what every designer wishes for to produce visuals that genuinely meet their requirements and standards, but it could also be beneficial once the legal frame for AI-generated visuals is defined.
By loading the tweet, you agree to Twitter's privacy policy.
Learn more
Why? So far, competing authorities like the USCO have stated that images created with AI cannot be copyrighted, and the reason behind this stance is that they are machine-made, lacking the human-creator factor necessary to be intellectual property. However, the same organism said that AI-generated images could be subject to copyright if enough human intervention can be proven to have taken part in the creative process.
In this context, tools like Gingerbread that put decisive customization edits in the hands of the human creator would undoubtedly be interesting to explore.
As cool and conversation-worthy as Gingerbread’s preview was on social media and the physical world, it was only that, a preview.
As of right now, Adobe hasn’t disclosed a release date of this model to the public, not even confirmed that it will be released eventually.
Its capabilities, however, have created great interest and excitement in the creative community, so we’ll have to wait and see what comes out of it.
Do you think it’ll be a proper AI feature of Adobe in the future?
THE AUTHOR
Ivanna Attie
I am an experienced author with expertise in digital communication, stock media, design, and creative tools. I have closely followed and reported on AI developments in this field since its early days. I have gained valuable industry insight through my work with leading digital media professionals since 2014.
AI Secrets is a platform for tech decision-makers to learn about AI technology. Our team includes experts such as Amos Struck (20+ yrs ICT, Stock Photo, AI), Ivanna Attie (expert in digital comms, design, stock media), and more who share their views on AI.
Get AI news in your inbox & join thousands of engineers and managers using AI to boost sales and grow market share
