Introducing vision to the fine-tuning API

What changed

Developers can now fine-tune GPT-4o with images and text to improve vision capabilities

Why it matters

A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.

How it compares

Related prior coverage to compare against:

• Building smarter maps with GPT-4o vision fine-tuning
• Fine-tuning now available for GPT-4o
• Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

• Building smarter maps with GPT-4o vision fine-tuning similarity 0.49
• Fine-tuning now available for GPT-4o similarity 0.47
• Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models similarity 0.33