---
format: "aidr-story-markdown/v1"
id: "ae259ea106d48229fba45d97e98f7399834d369110701d3dd684e5776eb25a58"
canonical_url: "https://aidr.today/ae259ea1?lang=en"
title: "FunAI Lab's Open Vision Model Beats Google's Vision Banana on Cityscapes Benchmark"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-13T14:38:23.000Z"
category: "Open Source"
topics: ["open-source"]
source_urls: ["https://huggingnews.com/ai/funai-labs-open-vision-model-beats-googles-vision-banana-on-cityscapes-b-3b79262b","https://marketbrief.now/ai/funai-labs-open-vision-model-beats-googles-vision-banana-on-cityscapes-b-3b79262b"]
summary: "FunAI Lab published the training code and weights for a computer vision finetune of the FLUX.2 Klein 4B and 9B image generators. The new model achieved a 73.9 mIoU score on the Cityscapes benchmark, surpassing Google DeepMind's Vision Banana's 69.9 mIoU. The project was developed using only public data and released 148 checkpoints for the community."
---

# FunAI Lab's Open Vision Model Beats Google's Vision Banana on Cityscapes Benchmark

> [Open the canonical story](<https://aidr.today/ae259ea1?lang=en>)

**Published:** 2026-11-13T14:38:23.000Z
**Category:** Open Source
**Topics:** open\-source

## Summary

FunAI Lab published the training code and weights for a computer vision finetune of the FLUX\.2 Klein 4B and 9B image generators\. The new model achieved a 73\.9 mIoU score on the Cityscapes benchmark, surpassing Google DeepMind's Vision Banana's 69\.9 mIoU\. The project was developed using only public data and released 148 checkpoints for the community\.

## Sources

- [Story source](<https://huggingnews.com/ai/funai-labs-open-vision-model-beats-googles-vision-banana-on-cityscapes-b-3b79262b>)
- [Story source](<https://marketbrief.now/ai/funai-labs-open-vision-model-beats-googles-vision-banana-on-cityscapes-b-3b79262b>)