Allowing Image Input and Analysis in Microsoft Copilot Studio
Microsoft Copilot Studio now allows users to upload images for analysis and response. Enabling image input in Copilot agents has two main benefits: information retrieval and image-based queries. To ensure efficient analysis, it is important to encourage users to upload clear and high-quality images in supported formats (JPG, PNG, WebP, non-animated GIFs). Content moderation should be implemented, and the total size of uploaded images in a single chat should not exceed 15 MB. Enabling the AI's general knowledge can help improve responses from images. To enable image input, access the agent's Settings page, choose Generative AI, modify content moderation if desired, and turn on Image input. Testing the agent's image analysis is crucial before publishing. Microsoft is committed to responsible AI and checks content for harmful or offensive material. Enabling image input in Copilot Studio enhances user interactions and allows for accurate and informative responses based on visual content.
Article 3m
Login now to access my digest by 365.Training
Learn how my digest works
Features
- Articles, blogs, podcasts, training, and videos
- Quick read TL;DRs for each item
- Advanced filtering to prioritize what you care about
- Quick views to isolate what you are looking for right now
- Save your favorite items
- Share your favorites
- Snooze items you want to revisit when you have more time