Apple researchers have collaborated with the University of California, Santa Barbara to create a new model that allows users to describe desired changes in a photo using plain language. The MGIE model, short for MLLM-Guided Image Editing, enables users to crop, resize, flip, and add filters to images through text prompts. It can handle both simple and complex editing tasks, such as modifying specific objects or enhancing brightness. The model combines the interpretation of user prompts with the generation of corresponding edits. Users can simply type out their desired changes to edit a photo with MGIE.
Apple researchers released a new model that lets users describe in plain language what they want to change in a photo without ever touching photo editing software. The MGIE model, which Apple worked on with the University of California, Santa Barbara , can crop, resize, flip, and add filters to images all through text prompts .
MGIE, which stands for MLLM-Guided Image Editing, can be applied to simple and more complex image editing tasks like modifying specific objects in a photo to make them a different shape or come off brighter. The model blends two different uses of multimodal language models. First, it learns how to interpret user prompts. Then it “imagines” what the edit would look like . When editing a photo with MGIE, users just have to type out what they want to change about the picture. The paper used the example of editing an image of a pepperoni pizza. Typing the prompt “make it more healthy” adds vegetable toppings. A photo of tigers in the Sahara looks dark, but after telling the model to “add more contrast to simulate more light,” the picture appears brighter. “Instead of brief but ambiguous guidance, MGIE derives explicit visual-aware intention and leads to reasonable image editing. We conduct extensive studies from various editing aspects and demonstrate that our MGIE effectively improves performance while maintaining competitive efficiency. We also believe the MLLM-guided framework can contribute to future vision-and-language research,” the researchers said in the paper. Apple made MGIE available through GitHub for download, but it also released a web demo on Hugging Face Spaces, reports VentureBeat. The company did not say what its plans for the model are beyond research. Some image generation platforms, like OpenAI’s DALL-E 3, can perform simple photo editing tasks on pictures they create through text inputs. Photoshop creator Adobe, which most people turn to for image editing, also has its own AI editing model. Its Firefly AI model powers generative fill, which adds generated backgrounds to photos. Apple has not been a big player in the generative AI space, unlike Microsoft, Meta, or Google, but Apple CEO Tim Cook has said the company wants to add more AI features to its devices this year. In December, Apple researchers released an open-source machine learning framework called MLX to make it easier to train AI models on Apple Silicon chips.
Apple Researchers Model Photo Editing Plain Language MGIE MLLM-Guided Image Editing University Of California Santa Barbara Crop Resize Flip Filters Text Prompts Interpretation Edits Brightness
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Apple Loop: Disappointing iPhone Leaks, Cheaper Apple Vision Plans, iPad Pro DelayedI am known for my strong views on mobile technology, online media, and the effect this has on the public conscious and existing businesses.
Read more »
Apple Cancelled Brilliant Apple Watch Ultra Innovation In New U-Turn, Report SaysI’ve been writing about technology for two decades and am routinely struck by how the sector swings from startling innovation to persistent repetitiveness. My areas of specialty are wearable tech, cameras, home entertainment and mobile technology.
Read more »
Apple might be testing a new Apple Pencil for Vision ProTsveta, a passionate technology enthusiast and accomplished playwright, combines her love for mobile technologies and writing to explore and reveal the transformative power of tech.
Read more »
Apple Online Services Experience OutageApple’s online services, including the App Store, Apple TV, and Apple Music, are currently experiencing an outage. The issue is also affecting other services such as Arcade, Audiobooks, Books, Podcasts, Fitness Plus, and Apple Sports app. Users have reported problems with accessing TestFlight and Apple Business Manager as well. Apple is aware of the issue and is investigating.
Read more »
Apple apps reporting outages: What you need to knowThe impacted apps included the App Store, Apple TV, Apple TV+ and Apple Music.
Read more »
Apple releases visionOS 1.1.2 to Apple Vision Pro usersA couple of weeks after releasing visionOS 1.1.1 to everyone, Apple is now seeding visionOS 1.1.2. Like the previous update.
Read more »