Interesting Product - sivi.ai

sivi.ai

The concept of blending image/text and providing ad variations is very impressive :)

The next question comes up / How does it compete against other models? Text to image generator options?

Current State of Art models struggle with creating the right mix of design with image and text content.

My Understanding

• Have variations for text
• Have Variations for image
• Leverage past data
• Position according to domain/data
• Generate variations

30% image variations

30% text variations

40% templates and positioning based on domain / data / templates

Keep Exploring!!!