Personalizing Your Images with AI-Powered Features
summary
A demo app uses Cloudinary to auto-analyze uploads with faces=true, colors=true, OCR and moderation via AWS Rekognition and Google object tagging at a 70% confidence threshold, saving tags and metadata to each asset. Uploaded images are filtered by moderation, categorized (people vs shoes), transformed via URL params to outpaint to square canvases, overlay sunglasses on detected faces, add a predominant-color border, and deliver optimized images (quality=auto, fetch_format=auto). The code is on GitHub and the demo works end to end.
AI-written summary · about
chapters (7)
- 0:00intro
- 0:20preamble
- 0:30how do you handle your images?
- 1:06what if you have too many images to handle manually?
- 1:57ai can help you manage your images
- 5:31demo
- 23:32get the code on github, learn more, be in touch
related talks
36mApps That See 👀 Practical AI Vision for Developers
44mCan AI See You? Your Introduction to Computer Vision and GenAI
27mAI-eye in Augmented Reality
46mBuild apps with state-of-the-art computer vision
38mHow Artificial Intelligence has changed your life
37mAnalyzing Images with Google’s Cloud Vision API
25mHow Mixbook leveraged genAI to offer personalized experiences
26mSelf-Portraits in JavaScript