Home Architecture News Apple released its new instruction-based AI image editing tool
Architecture News

Apple released its new instruction-based AI image editing tool

Share
Apple released its new instruction-based AI image editing tool
Share
image
[ICLR’24] Guiding Instruction-based Image Editing via Multimodal Large Language Models via Huggin Face

Apple has recently developed a new artificial intelligence model with the University of California, Santa Barbara. With the help of this model, named MGIE (MLLM-Guided Image Editing), users can easily edit their photos by simply providing plain-language text commands.

The model can perform tasks such as cropping, resizing, rotating, and adding filters to images. First, the model learns how to interpret user commands and then “imagines” what the image would look like after the edit. For instance, if a user asks for a bluer sky, the model increases the brightness in the sky portion of the image. This makes the photo editing process quite simple and straightforward, as the user only needs to mention what they want to change about the image.

“Multimodal large language models (MLLMs) show promising capabilities in cross-modal understanding and visual-aware response generation via LMs. We investigate how MLLMs facilitate edit instructions and present MLLM-Guided Image Editing (MGIE). MGIE learns to derive expressive instructions and provides explicit guidance. The editing model jointly captures this visual imagination and performs manipulation through end-to-end training. We evaluate various aspects of Photoshop-style modification, global photo optimization, and local editing. Extensive experimental results demonstrate that expressive instructions are crucial to instruction-based image editing, and our MGIE can lead to a notable improvement in automatic metrics and human evaluation while maintaining competitive inference efficiency.” states the research paper, which is published as a conference paper at ICLR, 2024 (International Conference on Learning Representations 2024).

Apple has made MGIE available for download on GitHub and also released a web demo on Hugging Face. However, when compared to its competitors, such as Adobe’s Firefly and OpenAI’s ChatGPT, Apple still lags behind in artificial intelligence products.

Share
Written by
Serra Utkum Ikiz

Serra is passionate about researching and discussing cities, with a particular love for writing on urbanism, politics, and emerging design trends.

Leave a comment

Leave a Reply

Related Articles
Photography Seoul Museum of Art Opens in Dobong-gu, Seoul
Architecture News

Photography Seoul Museum of Art Opens in Dobong-gu, Seoul

Seoul, South Korea: The Photography Seoul Museum of Art (PhotoSeMA) is now...

Foster + Partners’ Marine Life Institute Takes Shape at Saudi Arabia’s AMAALA
Architecture News

Foster + Partners’ Marine Life Institute Takes Shape at Saudi Arabia’s AMAALA

On Saudi Arabia’s Red Sea shores, the Corallium Marine Life Institute is...

Design Shanghai 2025 to Return in June, Focusing on 'Design for Humanity'
Architecture News

Design Shanghai 2025 to Return in June, Focusing on ‘Design for Humanity’

Design Shanghai returns from June 4–7, 2025, at the Shanghai World Expo...

Disney to Open First Middle East Theme Park on Yas Island in Abu Dhabi
Architecture News

Disney to Open First Middle East Theme Park on Yas Island in Abu Dhabi

The Walt Disney Company has officially announced that Disneyland is coming to...

Subscribe to all newsletters

Join our community to receive the latest insights and updates!

© 2025 ParametricArchitecture. All Rights Reserved. By utilizing this website, you are consenting to our User Agreement, Privacy Policy, and Cookie Statement. In compliance with the privacy laws of Turkey and the United States, we recognize and respect your rights. Please be aware that we may receive commissions for products bought through our affiliate links. Unauthorized reproduction, distribution, or transmission of any material from this site is strictly forbidden without prior written permission from ParametricArchitecture.

ad blocker mark

AdBlocker Detected!

Help Us Keep Our Content Free

Your support helps us continue delivering high-quality resources at no cost to you.

We’ve detected that you are using an AdBlocker. We completely understand the need for a clean browsing experience, but ads help us keep this platform running and continue providing you with high-quality content at no cost.

If you enjoy our content, please consider disabling your AdBlocker or adding our site to your whitelist. Your support allows us to create more valuable articles, tutorials, and resources for you.

Thank you for being a part of our community!