Last updated: Aug-12-2024
New features
Generative background replace
Take advantage of generative AI to remove unwanted backgrounds and replace them with something more suitable to your needs. Key features include:
- Auto background generation: Automatically decides what to generate in the background based on the foreground elements.
- Prompt guided: Enables more specific changes and uses natural language prompts to guide background generations.
- Variations: Generate background variations or return to previously generated variations, using a seed parameter.
AI content extraction
Extract and transform image content using natural language prompts. Ideal for background swaps, overlays, and complex compositions. Enables you to perform multi-element extractions quickly with no special setup, enhancing creative workflows for various use cases. Key features include:
- Natural language prompts: Describe the content to extract using prompts.
- Multi-extraction: Detect and extract multiple content elements or instances from an image.
- Modes: Choose to get either the extracted visual content or a mask layer representing the extracted areas.
- Inversion: Invert the selection to retain everything except the extracted areas.
Android sample app
A brand-new sample app is available for the Cloudinary Android SDK. The app demonstrates a variety of capabilities, including:
- Uploading
- Optimization
- Transformations
- Delivery
- Video player widget and video feeds
- Upload widget and image widget implementations
- Use cases such as localization, branding, and background normalization
We invite you to fork or clone, run, and start playing with the app yourself: Android Sample App GitHub repo
Enhancements
Improved image upscaling
Our image upscaling feature is now even better, with improved resolution and clarity of images, making them suitable for high-quality displays and prints. Deliver sharp, detailed images on all devices, enhancing visual appeal and engagement on websites and apps.
The maximum image size limit for upscaling is now 2048x2048 pixels (4.2MP), a significant increase from the previous limit of 0.25MP. This allows for the upscaling of larger images, covering a wider range of use cases while maintaining the same 4x upscaling factor for enhanced detail.
Transformation builder improvements
We've made some improvements to our Transformation Builder, including:
- A better integration into the Media Library, allowing the builder to be opened contextually from an asset.
- The ability to select all assets from the asset picker.
Multi-language support for video transcription
We've now added support for 100 different languages when using automatic transcription for videos. The primary language spoken in the video is automatically identified, and your transcript is generated the detected language. Transcription gives access to valuable features such as sentiment analysis, translation, content summarization, moderation tools, classification, and more.
Register for notifications
Make sure you always know when new release notes are published:
Programmable Media release notes RSS feed: Grab this RSS link to watch for new Programmable Media release notes in your favorite RSS reader.
Cloudinary Discord: Join the Cloudinary Discord server and keep an eye on the #cloudinary-news channel. Our RSS feeds will automatically be pushed there whenever new release notes are published.