Generate Better AI Images in Adobe Photoshop🎉

Adobe is rolling out new generative AI tools for Photoshop, powered by its Firefly Image 3 model. These tools, available in the Photoshop beta desktop app, offer users more control over their designs. 

Adobe added The Reference Image tool that allows users to upload images to guide AI output, reducing the need for manual prompt adjustments. Users must have rights to use referenced images, and Adobe is working on a “do not train” tag to block unauthorized use. 

Despite this, Adobe claims the tool is safe for commercial use. Other new AI tools include Generate Background, Enhance Detail, Generate Similar, and Generate Image. Firefly Image 3, available in a public beta, offers higher-quality image generation and better text understanding. In addition to AI tools, Photoshop is getting new features like Adjustment Brush, Adjustment Presets, and an improved Font Browser to streamline creative processes.

Now, Meta AI Eyeglasses Can See What You’re Seeing and Answer Your Questions

Ray-Ban Meta smart glasses now offer the ability to share views on video calls via WhatsApp and Messenger, hands-free. Gradual rollout of this feature is ongoing. 

Furthermore, the integration of Meta AI enhances the glasses’ capabilities, allowing users to access real-time information and receive intelligent assistance through voice commands. A multimodal AI update enables the glasses to provide smart answers or suggestions based on what the user sees, enhancing functionality in various scenarios such as language translation.

Check the video here

Looking for a Compact AI Model for Your Tailored AI Solution? Give Microsoft’s Phi-3 a Try!

Microsoft researchers found inspiration in children’s books for solving complex problems, leading to the development of smaller yet more powerful language models. These models, known as Small Language Models (SLMs), offer similar capabilities to Large Language Models (LLMs) but are more accessible and require fewer resources to operate. 

The Phi-3 family of open models, including Phi-3-mini with 3.8 billion parameters, outperform larger models in various benchmarks. Microsoft aims to offer a portfolio of models to meet diverse needs, with SLMs suitable for tasks requiring simpler reasoning or quick responses. SLMs also present opportunities for applications in offline environments, such as rural areas lacking network connectivity. 

By focusing on high-quality data and innovative training approaches, Microsoft achieved significant advancements in SLM development, demonstrating that model size isn’t the sole determinant of performance.

Get Free AI E-Book

Do you want to learn more about AI? Get this FREE AI E-Book to guide you in using AI effectively. Download it here.