OpenAI | Introducing Vision to the Fine-Tuning API

Enabling Image and Text Fine-Tuning for GPT-4o OpenAI has introduced vision fine-tuning for GPT-4o, allowing developers to customize the model with both images and text. This enhances the model’s visual understanding capabilities, enabling improved visual search functionality, better object detection for autonomous systems, and more accurate medical image analysis. Companies like Grab and Automat have already used this feature to enhance their mapping accuracy and automate business processes more effectively.

Source: Introducing vision to the fine-tuning API | OpenAI