Generate a detailed image caption with highlighted entities
Tag furry images using thresholds
Label text in images using selected model and threshold
Upload images and get detailed descriptions
Generate text from an image and prompt
Generate a detailed description from an image
Generate images captions with CPU
Score image-text similarity using CLIP or SigLIP models
Describe images using text
Generate multiple captions for an image using various models
Extract Japanese text from manga images
Image Caption
Caption images with detailed descriptions using Danbooru tags
Kosmos 2 is an advanced AI-powered tool designed for image captioning. It generates detailed and accurate captions for images while highlighting key entities such as objects, actions, and scenes. This makes it ideal for applications requiring precise image descriptions.
• Entity Highlighting: Automatically identifies and highlights key entities in the image, such as people, places, and objects.
• Detailed Captions: Produces comprehensive and context-rich captions for images.
• Multi-Format Support: Compatible with various image formats, including JPG, PNG, and more.
• Customization: Allows users to fine-tune caption generation based on specific needs.
• Multilingual Support: Generates captions in multiple languages for global accessibility.
What formats does Kosmos 2 support?
Kosmos 2 supports JPG, PNG, BMP, and TIFF image formats.
Can I customize the captions?
Yes, Kosmos 2 allows users to customize captions by adjusting settings like language and caption length.
Is Kosmos 2 available in multiple languages?
Yes, Kosmos 2 supports multiple languages, making it accessible for global users.