# Pushing the quality-cost frontier with MAI-Image-2.6 | Microsoft AI

Both models support multi-image reference editing, web grounding, dynamic aspect ratios, and output resolutions up to 1.5K.

- MAI-Image-2.6-Flash generates images 2.8x faster than GPT-Image-2-Medium with 72% greater efficiency.
- Multi-reference editing enables combining people, products, styles, and scenes across multiple source images.
- Web grounding pulls live information from across the web to inform generated visual content.

## Why it matters

Developers on Microsoft Foundry can deploy faster, lower-cost image generation and multi-reference editing directly into production workflows.

## Sources

- [Microsoft AI: Pushing the quality-cost frontier with MAI-Image-2.6 | Microsoft AI](https://microsoft.ai/news/pushing-the-quality-cost-frontier-with-mai-image-2-6)

---

Summarized by dstilled on 2026-09-04. https://dstilled.ai/story/d7ebbc98-1ceb-4fa4-82fa-611e05ae2b06