# Open-Source Image Editing Models Are Zero-Shot Vision Learners

Source: [Open-Source Image Editing Models Are Zero-Shot Vision Learners](<https://www.sota2.com/research/paper/69fc1cb05497b3b670c8865c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-08T05:00:04.262Z

Authors: Wei Liu, Jiaxin Lin, Rui Chen

Published: 2026-05-06T07:11:50.000Z

## Abstract

Recent studies have shown that large generative models can solve vision tasks they were not explicitly trained for. However, existing evidence relies on closed-source models~(Veo~3, Nano Banana Pro) or requires task-specific instruction tuning, leaving open whether publicly available image-editing models possess zero-shot vision abilities out of the box.   We conduct a systematic evaluation of three open-source image-editing models -- Qwen-Image-Edit, FireRed-Image-Edit, and LongCat-Image-Edit -- on dense visual prediction tasks \\emph{without any fine-tuning}. We benchmark monocular depth estimation on NYUv2 and DIODE, surface normal estimation on NYUv2, and semantic segmentation on Cityscapes, covering both geometric and semantic scene understanding.   Results show that open-source image-editing models exhibit non-trivial zero-shot visual understanding. On NYUv2 surface normals, FireRed-Image-Edit achieves a mean angular error of $17.69^\\circ$, surpassing the fine-tuned Marigold ($20.86^\\circ$) and matching the instruction-tuned Vision Banana ($17.78^\\circ$) without any task-specific training. On NYUv2 depth estimation, LongCat-Image-Edit obtains $\\delta\_1{=}0.822$ with affine alignment, and Qwen-Image-Edit leads on DIODE Indoor ($\\delta\_1{=}0.868$). On Cityscapes semantic segmentation, Qwen-Image-Edit reaches 25.7 mIoU at the 19-class level and 49.5 mIoU at a coarser 7-category level. By comparing three independently trained editors, we test whether zero-shot vision ability is an emergent property of image-editing pretraining rather than a model-specific artifact. Code, evaluation scripts, and all results are publicly released to serve as a reproducible baseline for future work.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.04566>)

[PDF](<https://arxiv.org/pdf/2605.04566.pdf>)